{
  "checked_at": "2026-10-09",
  "discussion_count": 115,
  "closed_or_merged_count": 112,
  "source": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions",
  "discussions": [
    {
      "number": 115,
      "author": "ppuzio",
      "title": "README: copied Wikipedia text and the Trędowata overlap (v2#80, for the v0.2.6 release commit)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/115"
    },
    {
      "number": 114,
      "author": "ppuzio",
      "title": "verify_paper_claims: read the v0.2.6 paper draft (v2#61)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/114"
    },
    {
      "number": 113,
      "author": "ppuzio",
      "title": "sejm_api_2011_2022: re-pin the parliamentary reference to Hub PR 111 (v2#54)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/113"
    },
    {
      "number": 112,
      "author": "ppuzio",
      "title": "parliamentary: record IPI PAN's answer on the Sejm Library documents (v2#54)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/112"
    },
    {
      "number": 111,
      "author": "ppuzio",
      "title": "parliamentary: repair cp1250 misdecoding, drop exact copies (v2#54, 1A/2A)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/111"
    },
    {
      "number": 110,
      "author": "ppuzio",
      "title": "sejm_api_2011_2022: re-pin the dedup to the PPC TEI parliamentary (v2#54, 5A)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/110"
    },
    {
      "number": 109,
      "author": "ppuzio",
      "title": "sejm_committee_transcripts: redact() counts only actual replacements; card corrects the 454",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/109"
    },
    {
      "number": 108,
      "author": "ppuzio",
      "title": "parliamentary: rebuild from IPI PAN's PPC TEI dump, official speakers only (v0.2.6 rights audit)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/108"
    },
    {
      "number": 107,
      "author": "ppuzio",
      "title": "sejm_committee_transcripts: card says fourteen exact labels, not eleven",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/107"
    },
    {
      "number": 106,
      "author": "ppuzio",
      "title": "sejm_committee_transcripts: keep only official speakers, cut guest speech and page blocks (v0.2.6 rights audit)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/106"
    },
    {
      "number": 105,
      "author": "ppuzio",
      "title": "Fix cards and NOTICE files citing paths that do not exist (cross-source, paths only)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/105"
    },
    {
      "number": 104,
      "author": "ppuzio",
      "title": "rock_pollub_pl: repair provenance evidence (checksums, cited paths)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/104"
    },
    {
      "number": 103,
      "author": "ppuzio",
      "title": "dziennik_ustaw: license_spdx CC0-1.0 -> LicenseRef-Polish-Official-Documents",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/103"
    },
    {
      "number": 102,
      "author": "ppuzio",
      "title": "uzp_orzeczenia_pl: state review status and quoted-material caveat (v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/102"
    },
    {
      "number": 101,
      "author": "ppuzio",
      "title": "parliamentary: drop the CC-BY-4.0 claim for the text; IPI PAN's CC BY covers only the PPC annotations (v2#54)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/101"
    },
    {
      "number": 100,
      "author": "ppuzio",
      "title": "added: set plwiki_user_talk, nkjp1m, global_voices, 1000_novels to their shard dates (v2#80)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/100"
    },
    {
      "number": 99,
      "author": "ppuzio",
      "title": "wolne_lektury: label each row with its own Wolne Lektury licence; drop 2 unlicensed rows (v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/99"
    },
    {
      "number": 98,
      "author": "ppuzio",
      "title": "worked-examples: cite the current wikibooks ids (v2#80)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/98"
    },
    {
      "number": 97,
      "author": "ppuzio",
      "title": "Stamp each source's registry added date; date the v0.2.0 sources 2026-06-15 (v2#80)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/97"
    },
    {
      "number": 96,
      "author": "ppuzio",
      "title": "Add a pinned NERGAL 2.0.1 post-pass for built shards (v2#60)",
      "status": "closed",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/96"
    },
    {
      "number": 95,
      "author": "ppuzio",
      "title": "kultura_bez_barier_pl: mask the coordinator phones, cite the PDF licence line (v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/95"
    },
    {
      "number": 94,
      "author": "ppuzio",
      "title": "sejm_interpellations: record the licence evidence, the SIS terms and quoted third-party text (v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/94"
    },
    {
      "number": 93,
      "author": "ppuzio",
      "title": "plwiki_user_talk: label each record CC-BY-SA-3.0 or 4.0 by last revision (v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/93"
    },
    {
      "number": 92,
      "author": "ppuzio",
      "title": "plwiki_talk: label each record CC-BY-SA-3.0 or 4.0 by last revision (v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/92"
    },
    {
      "number": 91,
      "author": "ppuzio",
      "title": "open_agh_chemistry_pl: cite the 2026-10-06 Wayback captures of the EPUB rights pages (v2#78)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/91"
    },
    {
      "number": 90,
      "author": "ppuzio",
      "title": "studia_bas: record the licence notices of the 17 issue PDFs (v2#79)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/90"
    },
    {
      "number": 89,
      "author": "ppuzio",
      "title": "plot_version_growth: v0.2.5 totals from the tagged CHANGELOG (20 sources)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/89"
    },
    {
      "number": 88,
      "author": "ppuzio",
      "title": "verify_paper_claims: check the polish-dynaword-v2 paper (v2#61)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/88"
    },
    {
      "number": 87,
      "author": "ppuzio",
      "title": "open_agh_chemistry_pl: record the 2026-10-06 rights-page recheck (no data change)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/87"
    },
    {
      "number": 86,
      "author": "ppuzio",
      "title": "Share one Polish-language gate (diacritic ratio, then langid vote); exempt plwiki and plwikivoyage (v2#77)",
      "status": "closed",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/86"
    },
    {
      "number": 85,
      "author": "ppuzio",
      "title": "Share one Polish-language gate (diacritic ratio, then langid vote); exempt plwiki and plwikivoyage (v2#77)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/85"
    },
    {
      "number": 84,
      "author": "ppuzio",
      "title": "sejm_api_2011_2022: cut the \"Przebieg posiedzenia\" trailers before the cross-source dedup (amends #76, v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/84"
    },
    {
      "number": 83,
      "author": "ppuzio",
      "title": "sejm_api: cut the \"Przebieg posiedzenia\" trailers, split appended statements (amends #69, v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/83"
    },
    {
      "number": 82,
      "author": "ppuzio",
      "title": "eurlex: drop the 92 IASB-notice documents (243,060 -> 242,968 docs, v0.2.6)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/82"
    },
    {
      "number": 81,
      "author": "ppuzio",
      "title": "biblioteka_nauki: per-record licence versions from the API (42,068 -> 42,055 docs, v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/81"
    },
    {
      "number": 80,
      "author": "ppuzio",
      "title": "studia_bas: licence version resolved to CC BY 3.0 PL (evidence + tests, no data change)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/80"
    },
    {
      "number": 79,
      "author": "ppuzio",
      "title": "wikibooks: label each page CC BY-SA 3.0 or 4.0 by its last revision, GFDL review (v0.2.6, v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/79"
    },
    {
      "number": 78,
      "author": "ppuzio",
      "title": "wikivoyage: label each page CC BY-SA 3.0 or 4.0 by its last revision (v0.2.6, v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/78"
    },
    {
      "number": 77,
      "author": "ppuzio",
      "title": "wikinews: label each page CC BY 2.5 or 4.0 by its last revision (v0.2.6, v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/77"
    },
    {
      "number": 76,
      "author": "ppuzio",
      "title": "sejm_api_2011_2022: relabel provenance, drop speeches contained in parliamentary / sejm_api (118,902 -> 32,460)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/76"
    },
    {
      "number": 75,
      "author": "ppuzio",
      "title": "ted_pl: cite both licence bases, rescrub missed e-mails and phones (v0.2.6, v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/75"
    },
    {
      "number": 74,
      "author": "ppuzio",
      "title": "edukacja_medialna_pl: drop 4 lessons with embedded third-party quotations (252 -> 248)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/74"
    },
    {
      "number": 73,
      "author": "ppuzio",
      "title": "nonsa: drop namespace 100 Cytaty and <poem> pages (12,304 -> 11,692 docs, v0.2.6 rights audit)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/73"
    },
    {
      "number": 72,
      "author": "ppuzio",
      "title": "open_agh_chemistry_pl: pin the four rights pages in a licence-evidence file (no data change)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/72"
    },
    {
      "number": 71,
      "author": "ppuzio",
      "title": "eurlex: relabel to LicenseRef-EU-Reuse-Policy, report third-party (IASB) material",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/71"
    },
    {
      "number": 70,
      "author": "ppuzio",
      "title": "1000_novels: drop texts already in wolne_lektury or eltec_pol (887 → 221 docs) (v2#45)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/70"
    },
    {
      "number": 69,
      "author": "ppuzio",
      "title": "sejm_api: state the contributor snapshot in provenance (v0.2.6, v2#57)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/69"
    },
    {
      "number": 68,
      "author": "ppuzio",
      "title": "wikipedia: rebuild from the official plwiki dump, CC BY-SA 3.0/4.0 per page (v0.2.6)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/68"
    },
    {
      "number": 67,
      "author": "ppuzio",
      "title": "wolne_lektury: drop 63 docs that duplicate eltec_pol novels (6,141 -> 6,078 docs)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/67"
    },
    {
      "number": 66,
      "author": "ppuzio",
      "title": "global_voices: drop 114 partner republications (2,040 -> 1,926 docs)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/66"
    },
    {
      "number": 65,
      "author": "ppuzio",
      "title": "1000_novels: rescreen with cited translator death years, pin the screen (837 -> 887 texts)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/65"
    },
    {
      "number": 64,
      "author": "ppuzio",
      "title": "samorzad_gov_pl: drop 144 third-party rows, relabel licence basis (v0.2.6, v2#49)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/64"
    },
    {
      "number": 63,
      "author": "ppuzio",
      "title": "govpl: drop 188 PAP reprints (gov.pl third-party carve-out), add URL sidecar",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/63"
    },
    {
      "number": 62,
      "author": "ppuzio",
      "title": "biblioteka_nauki: drop the 3 Public Domain Mark records",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/62"
    },
    {
      "number": 61,
      "author": "ppuzio",
      "title": "Correct european_hplt_v3_pl legal_note: withdrawn, licence unverified",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/61"
    },
    {
      "number": 60,
      "author": "ppuzio",
      "title": "Withdraw wikisource: one CC BY-SA label over mixed per-page licences",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/60"
    },
    {
      "number": 59,
      "author": "ppuzio",
      "title": "Withdraw wikiquote: most quotations are in copyright",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/59"
    },
    {
      "number": 58,
      "author": "ppuzio",
      "title": "Withdraw common_voice_pl: CC0 not established for its sentences",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/58"
    },
    {
      "number": 57,
      "author": "ppuzio",
      "title": "Withdraw fandom_pl: Fandom ToU bars scraping and AI training",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/57"
    },
    {
      "number": 56,
      "author": "ppuzio",
      "title": "Withdraw openstax_pl: OpenStax Poland states NC and an LLM-training ban",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/56"
    },
    {
      "number": 55,
      "author": "ppuzio",
      "title": "1000_novels: the CLARIN-PL record is metadata-only; fix licence wording",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/55"
    },
    {
      "number": 54,
      "author": "ppuzio",
      "title": "Remove parlamint_pl from the source registry",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/54"
    },
    {
      "number": 53,
      "author": "ppuzio",
      "title": "Card: parliamentary speakers come from PPC and the Sejm API",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/53"
    },
    {
      "number": 52,
      "author": "ppuzio",
      "title": "Add requirements-dev.txt for the test suite",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/52"
    },
    {
      "number": 51,
      "author": "ppuzio",
      "title": "nkjp1m: relabel CC BY 4.0 per the NKJP Consortium, add agreed attribution file",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/51"
    },
    {
      "number": 50,
      "author": "ppuzio",
      "title": "wiktionary_examples: drop quoted third-party lines, relabel CC BY-SA 4.0",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/50"
    },
    {
      "number": 49,
      "author": "ppuzio",
      "title": "1000_novels: keep only the public-domain texts",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/49"
    },
    {
      "number": 48,
      "author": "PiotrSty",
      "title": "Add Polish Fandom wikis dataset",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/48"
    },
    {
      "number": 47,
      "author": "PolskiAgentW",
      "title": "Add source: eli_pdf_acts — Dziennik Ustaw and Monitor Polski acts published only as PDF",
      "status": "open",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/47"
    },
    {
      "number": 46,
      "author": "PiotrSty",
      "title": "Update samorzad_gov_pl to de-identified upstream v0.2 (scoped from #15)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/46"
    },
    {
      "number": 45,
      "author": "PiotrSty",
      "title": "build_dynaword: preserve_id / preserve_created flags (split from #19)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/45"
    },
    {
      "number": 44,
      "author": "PiotrSty",
      "title": "studia_bas: Studia BAS policy articles (scoped from #19)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/44"
    },
    {
      "number": 43,
      "author": "PiotrSty",
      "title": "sejm_interpellations data files (scoped fix for #24)",
      "status": "closed",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/43"
    },
    {
      "number": 42,
      "author": "ppuzio",
      "title": "Separate source PRs from releases; add render_sample.py",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/42"
    },
    {
      "number": 41,
      "author": "PiotrSty",
      "title": "Add Nonsensopedia content (satirical wiki) - humorous Polish",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/41"
    },
    {
      "number": 40,
      "author": "PiotrSty",
      "title": "Add plwiki user-talk pages (ns 3) - conversational Polish",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/40"
    },
    {
      "number": 39,
      "author": "PiotrSty",
      "title": "Add UZP public-procurement rulings (KIO/SO/SA/SN)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/39"
    },
    {
      "number": 38,
      "author": "ppuzio",
      "title": "Move PII scrubbing to SlayerLab/NERGAL",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/38"
    },
    {
      "number": 37,
      "author": "PiotrSty",
      "title": "Add source: sejm_committee_transcripts - full Sejm committee zapis coverage (terms 9-10)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/37"
    },
    {
      "number": 36,
      "author": "PiotrSty",
      "title": "Add plwiki talk pages (ns 1+5) - conversational Polish",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/36"
    },
    {
      "number": 35,
      "author": "PiotrSty",
      "title": "Add CC BY-SA 4.0 Wiadomosci Statystyczne Polish articles",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/35"
    },
    {
      "number": 34,
      "author": "PiotrSty",
      "title": "Add permissively licensed OPEN ICM Polish publications pilot",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/34"
    },
    {
      "number": 33,
      "author": "PiotrSty",
      "title": "Add eight CC BY-SA 4.0 Polish academic books from ROCK",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/33"
    },
    {
      "number": 32,
      "author": "PiotrSty",
      "title": "Add Polish TED public-procurement notices",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/32"
    },
    {
      "number": 31,
      "author": "ppuzio",
      "title": "Tag releases",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/31"
    },
    {
      "number": 30,
      "author": "ppuzio",
      "title": "Only document sources that are actually committed",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/30"
    },
    {
      "number": 29,
      "author": "ppuzio",
      "title": "Make release totals registry-driven",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/29"
    },
    {
      "number": 28,
      "author": "ppuzio",
      "title": "Improve contextual PII masking and regression coverage",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/28"
    },
    {
      "number": 27,
      "author": "PiotrSty",
      "title": "Add CC BY-SA 3.0 Polish cultural-accessibility guides",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/27"
    },
    {
      "number": 26,
      "author": "PiotrSty",
      "title": "Add CC BY-SA 3.0 Polish media-literacy lessons",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/26"
    },
    {
      "number": 25,
      "author": "PiotrSty",
      "title": "Add CC BY-SA 4.0 Open AGH Polish chemistry textbooks",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/25"
    },
    {
      "number": 24,
      "author": "ppuzio",
      "title": "Add source: sejm_interpellations — 10th-term written Q&A",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/24"
    },
    {
      "number": 23,
      "author": "PiotrSty",
      "title": "Add CC BY 4.0 Polish OpenStax academic textbooks",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/23"
    },
    {
      "number": 22,
      "author": "PiotrSty",
      "title": "Add CC0 Polish Common Voice validated text (v26.0)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/22"
    },
    {
      "number": 21,
      "author": "PiotrSty",
      "title": "Add pinned SAOS Polish court judgments snapshot",
      "status": "open",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/21"
    },
    {
      "number": 20,
      "author": "ppuzio",
      "title": "Add in-tree PII scrub (no new parquet)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/20"
    },
    {
      "number": 19,
      "author": "gzawadzki",
      "title": "Add source: Studia BAS peer-reviewed policy articles",
      "status": "closed",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/19"
    },
    {
      "number": 18,
      "author": "PiotrSty",
      "title": "Add source: sejm_api_2011_2022 - remaining attributed Sejm speeches",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/18"
    },
    {
      "number": 17,
      "author": "ppuzio",
      "title": "Contributor guidance: source findings log + PR/normalization requirements",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/17"
    },
    {
      "number": 16,
      "author": "PiotrSty",
      "title": "Add source: sejm_api — contemporary parliamentary speeches (2023 onward)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/16"
    },
    {
      "number": 15,
      "author": "dawidmajewski",
      "title": "feat(data): update samorzad_gov_pl to upstream v0.2",
      "status": "closed",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/15"
    },
    {
      "number": 14,
      "author": "KateMajzel",
      "title": "feat(data): add wiktionary_examples (8.6k docs / 1.12M tok)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/14"
    },
    {
      "number": 13,
      "author": "dawidmajewski",
      "title": "feat(data): add samorzad.gov.pl institutional corpus",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/13"
    },
    {
      "number": 12,
      "author": "Maggio33",
      "title": "feat(data): european_hplt_v3_pl expansion WDS bins 10-5 (+1.49M docs / 2.04B tok)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/12"
    },
    {
      "number": 11,
      "author": "bartoszkobylinski1",
      "title": "feat(data): add biblioteka_nauki source (42,071 docs, per-document license + attribution)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/11"
    },
    {
      "number": 10,
      "author": "ppuzio",
      "title": "Complete v0.2.3 phrase-frequency report + register drifted sources + AGENTS.md",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/10"
    },
    {
      "number": 9,
      "author": "ppuzio",
      "title": "Add source: govpl (gov.pl government press releases)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/9"
    },
    {
      "number": 8,
      "author": "1am",
      "title": "Add source: nkjp1m",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/8"
    },
    {
      "number": 7,
      "author": "dawidmajewski",
      "title": "feat(data): add reviewed Global Voices Polish corpus",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/7"
    },
    {
      "number": 6,
      "author": "ktalik",
      "title": "SJP.PL",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/6"
    },
    {
      "number": 5,
      "author": "Maggio33",
      "title": "Add source: european_hplt_v3_pl (HPLT v3.0 Polish, top WDS bins, CC0)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/5"
    },
    {
      "number": 4,
      "author": "kacperwikiel",
      "title": "Release v0.3.1 Europeana preview shard",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/4"
    },
    {
      "number": 3,
      "author": "kacperwikiel",
      "title": "Document live source-gate validation",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/3"
    },
    {
      "number": 2,
      "author": "KennethEnevoldsen",
      "title": "An absolute joy to see!",
      "status": "open",
      "is_pull_request": false,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/2"
    },
    {
      "number": 1,
      "author": "bartoszkobylinski1",
      "title": "Add source: 1000_novels (1000 Novels Corpus, CLARIN-PL, CC BY 4.0)",
      "status": "merged",
      "is_pull_request": true,
      "url": "https://huggingface.co/datasets/SlayerLab/polish-dynaword/discussions/1"
    }
  ]
}