{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HYR3DQTKF44YSZ53Z33XIZPHWF","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":"48a5562434eefa746e8f9d1f4b4c80e52d3104c2be758d3c035fed9d5fff49b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-05T09:57:40Z","title_canon_sha256":"3a5d9b2209fddbe46c79407c96c9ac228f23e244241f464531d6d11ba8d58325"},"schema_version":"1.0","source":{"id":"2510.04124","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.04124","created_at":"2026-05-20T00:00:25Z"},{"alias_kind":"arxiv_version","alias_value":"2510.04124v7","created_at":"2026-05-20T00:00:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.04124","created_at":"2026-05-20T00:00:25Z"},{"alias_kind":"pith_short_12","alias_value":"HYR3DQTKF44Y","created_at":"2026-05-20T00:00:25Z"},{"alias_kind":"pith_short_16","alias_value":"HYR3DQTKF44YSZ53","created_at":"2026-05-20T00:00:25Z"},{"alias_kind":"pith_short_8","alias_value":"HYR3DQTK","created_at":"2026-05-20T00:00:25Z"}],"graph_snapshots":[{"event_id":"sha256:99584c36521e3227544f29081919d43e9c5a256b05648710e65e04c08ac827b9","target":"graph","created_at":"2026-05-20T00:00:25Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The collection currently comprises of 263,545 documents (77.7 GB) across 26 datasets in Sinhala, Tamil, and English."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The source documents are legally accessible for bulk collection, accurately converted to machine-readable form, and free of major quality or licensing issues that would limit research use."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Releases 263,545 documents (77.7 GB) across 26 datasets from Sri Lanka in three languages, updated daily and mirrored on GitHub and Hugging Face for computational linguistics and policy research."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Sri Lanka now offers an open collection of 263,545 documents in Sinhala, Tamil, and English drawn from law, government, and news sources."}],"snapshot_sha256":"b2fccc7655cb263499740e853a804b4d4d078a4c96f2394c342073fb2ee7ac3d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"54208c8f30874fdd8452271b3483cad5821284955b873ef6d87893d4ee91dcd9"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.04124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a collection of open, machine-readable document datasets covering parliamentary proceedings, legal judgments, government publications, news, and tourism statistics from Sri Lanka. The collection currently comprises of 269,194 documents (79.5 GB) across 26 datasets in Sinhala, Tamil, and English. The datasets are updated daily and mirrored on GitHub and Hugging Face. These resources aim to support research in computational linguistics, legal analytics, socio-political studies, and multilingual natural language processing. We describe the data sources, collection pipeline, formats, an","authors_text":"Nuwan I. Senaratna","cross_cats":[],"headline":"Sri Lanka now offers an open collection of 263,545 documents in Sinhala, Tamil, and English drawn from law, government, and news sources.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-05T09:57:40Z","title":"Sri Lanka Document Datasets: A Large-Scale, Multilingual Resource for Law, News, and Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.04124","kind":"arxiv","version":7},"verdict":{"created_at":"2026-05-18T10:45:27.038829Z","id":"a8143388-4128-4b8d-865c-bb57f89923ad","model_set":{"reader":"grok-4.3"},"one_line_summary":"Releases 263,545 documents (77.7 GB) across 26 datasets from Sri Lanka in three languages, updated daily and mirrored on GitHub and Hugging Face for computational linguistics and policy research.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Sri Lanka now offers an open collection of 263,545 documents in Sinhala, Tamil, and English drawn from law, government, and news sources.","strongest_claim":"The collection currently comprises of 263,545 documents (77.7 GB) across 26 datasets in Sinhala, Tamil, and English.","weakest_assumption":"The source documents are legally accessible for bulk collection, accurately converted to machine-readable form, and free of major quality or licensing issues that would limit research use."}},"verdict_id":"a8143388-4128-4b8d-865c-bb57f89923ad"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8605a493cfc0e4f769eda44460184f495a530c9d06d83200cc5008bdcbbb8695","target":"record","created_at":"2026-05-20T00:00:25Z","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":"48a5562434eefa746e8f9d1f4b4c80e52d3104c2be758d3c035fed9d5fff49b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-05T09:57:40Z","title_canon_sha256":"3a5d9b2209fddbe46c79407c96c9ac228f23e244241f464531d6d11ba8d58325"},"schema_version":"1.0","source":{"id":"2510.04124","kind":"arxiv","version":7}},"canonical_sha256":"3e23b1c26a2f398967bbcef77465e7b16afe7e31bfa8fc48baf9236690b76e53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e23b1c26a2f398967bbcef77465e7b16afe7e31bfa8fc48baf9236690b76e53","first_computed_at":"2026-05-20T00:00:25.298086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:25.298086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bLuPAj3NYHrsLoPHQH16TSiSpCqE1uPPyGkITmLTpMgY0uV6hCHE62XmuIBs9Gaa+zT2mgvaNHfuE4KXVDY7DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:25.298753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.04124","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8605a493cfc0e4f769eda44460184f495a530c9d06d83200cc5008bdcbbb8695","sha256:99584c36521e3227544f29081919d43e9c5a256b05648710e65e04c08ac827b9"],"state_sha256":"bb2047c3ca796d1fcc796920540edde9a45763b7eecb1033a380002946b132d7"}