{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U2UVQ32KEQYC5XZEDWMB27W4PZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"08b79275b628f1841ca43a087b19ccb98360cc96e3b31610220b37b7464ae050","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T10:30:42Z","title_canon_sha256":"d8f14331ebbf345efdc7425bac209dcea96bb69254af095f2c9406f334a02c32"},"schema_version":"1.0","source":{"id":"2508.02271","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02271","created_at":"2026-07-05T11:48:28Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02271v2","created_at":"2026-07-05T11:48:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02271","created_at":"2026-07-05T11:48:28Z"},{"alias_kind":"pith_short_12","alias_value":"U2UVQ32KEQYC","created_at":"2026-07-05T11:48:28Z"},{"alias_kind":"pith_short_16","alias_value":"U2UVQ32KEQYC5XZE","created_at":"2026-07-05T11:48:28Z"},{"alias_kind":"pith_short_8","alias_value":"U2UVQ32K","created_at":"2026-07-05T11:48:28Z"}],"graph_snapshots":[{"event_id":"sha256:dc0ec29d7f34de5b5839131515237d9db3709d8c37acd6a35b980478d2ddb10a","target":"graph","created_at":"2026-07-05T11:48:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.02271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale datasets are foundational for research and development in natural language processing. However, current approaches face three key challenges: (1) reliance on ambiguously licensed sources restricting use, sharing, and derivative works; (2) static dataset releases that prevent community contributions and diminish longevity; and (3) quality assurance processes restricted to publishing teams rather than leveraging community expertise.\n  To address these limitations, we introduce two contributions: the Dynaword approach and Danish Dynaword. The Dynaword approach is a framework for creat","authors_text":"Andrea Blasi N\\'u\\~nez, Bal\\'azs Szab\\'o, Desmond Elliott, Gianluca Barmina, Jacob Nielsen, Jan Kostkan, Johan Heinsen, Kenneth Enevoldsen, Kirten Vad, Kristian N{\\o}rgaard Jensen, Kristoffer Nielbo, Lukas Galke, M\\'arton Kardos, Per M{\\o}ldrup Dalum, Peter Schneider-Kamp, Peter Vahlstrup, Rasmus Larsen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T10:30:42Z","title":"Dynaword: From One-shot to Continuously Developed Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02271","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:600d9bf11061c6da83eccb6ddbcda49044e3040de4dc7c6da8634c289fe7089d","target":"record","created_at":"2026-07-05T11:48:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"08b79275b628f1841ca43a087b19ccb98360cc96e3b31610220b37b7464ae050","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T10:30:42Z","title_canon_sha256":"d8f14331ebbf345efdc7425bac209dcea96bb69254af095f2c9406f334a02c32"},"schema_version":"1.0","source":{"id":"2508.02271","kind":"arxiv","version":2}},"canonical_sha256":"a6a9586f4a24302edf241d981d7edc7e7a8382d1358b4eb7ced475885f4132f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6a9586f4a24302edf241d981d7edc7e7a8382d1358b4eb7ced475885f4132f5","first_computed_at":"2026-07-05T11:48:28.749124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:28.749124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JHFSOdSDNBBLMA4qeSfQR04wdWVlwqiqGl/T3iTaHcfn90GsjwVd+ovyC36J5iR4ybS3BiVrD866VcmldnKuBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:28.749950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02271","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:600d9bf11061c6da83eccb6ddbcda49044e3040de4dc7c6da8634c289fe7089d","sha256:dc0ec29d7f34de5b5839131515237d9db3709d8c37acd6a35b980478d2ddb10a"],"state_sha256":"1681d1b300c6361247b16d826a45ebc7d717815a34ebd22b95656d71afc90162"}