{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QVMVEHM2TW36UHPXOPYBLNOQCG","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":"8c5ad074f4a1114769b9430539cd57055f3552cf57b25fda46fb037ad8ae4c1d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-02T08:22:52Z","title_canon_sha256":"29449e5d031ee3c33485593aa6865d541577f71252267a31ee7d01684c8b4297"},"schema_version":"1.0","source":{"id":"2204.00806","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00806","created_at":"2026-07-05T08:22:29Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00806v2","created_at":"2026-07-05T08:22:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00806","created_at":"2026-07-05T08:22:29Z"},{"alias_kind":"pith_short_12","alias_value":"QVMVEHM2TW36","created_at":"2026-07-05T08:22:29Z"},{"alias_kind":"pith_short_16","alias_value":"QVMVEHM2TW36UHPX","created_at":"2026-07-05T08:22:29Z"},{"alias_kind":"pith_short_8","alias_value":"QVMVEHM2","created_at":"2026-07-05T08:22:29Z"}],"graph_snapshots":[{"event_id":"sha256:b043f696bea1fb8186ea8d52eb319cfe507ed192c68f56215fd726249740a78d","target":"graph","created_at":"2026-07-05T08:22:29Z","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/2204.00806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many populous countries including India are burdened with a considerable backlog of legal cases. Development of automated systems that could process legal documents and augment legal practitioners can mitigate this. However, there is a dearth of high-quality corpora that is needed to develop such data-driven systems. The problem gets even more pronounced in the case of low resource languages such as Hindi. In this resource paper, we introduce the Hindi Legal Documents Corpus (HLDC), a corpus of more than 900K legal documents in Hindi. Documents are cleaned and structured to enable the developm","authors_text":"Akshala Bhatnagar, Amul Agrawal, Anmol Goel, Arnab Bhattacharya, Arnav Kapoor, Ashutosh Modi, Mudit Dhawan, Ponnurangam Kumaraguru, T.H. Arjun, Vibhu Agrawal","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-02T08:22:52Z","title":"HLDC: Hindi Legal Documents Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00806","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":"sha256:9a276870c2bcded9f0c7f065f06ffff2978ecfc047c982c931f81ac712f11ebf","target":"record","created_at":"2026-07-05T08:22:29Z","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":"8c5ad074f4a1114769b9430539cd57055f3552cf57b25fda46fb037ad8ae4c1d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-02T08:22:52Z","title_canon_sha256":"29449e5d031ee3c33485593aa6865d541577f71252267a31ee7d01684c8b4297"},"schema_version":"1.0","source":{"id":"2204.00806","kind":"arxiv","version":2}},"canonical_sha256":"8559521d9a9db7ea1df773f015b5d011b7fa4b90f660206bfc3cc4c2ab458023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8559521d9a9db7ea1df773f015b5d011b7fa4b90f660206bfc3cc4c2ab458023","first_computed_at":"2026-07-05T08:22:29.842629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:29.842629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x55sa94BUEQ8hD/Vrw8ItspbDs5ORG+0UqiUilVmUhSu+xug2daGee3xPVCtXdIkciPcLp+fhJF/oVhrAqreBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:29.843157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00806","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a276870c2bcded9f0c7f065f06ffff2978ecfc047c982c931f81ac712f11ebf","sha256:b043f696bea1fb8186ea8d52eb319cfe507ed192c68f56215fd726249740a78d"],"state_sha256":"f34bb748d2f2ad8fb55da85bccb78847fbdc04885fd02ef9463522a4419d6043"}