{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y4MEET6IDWVAWPDSQDRQGKOJUC","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":"fc9f6a536d725d73c2458dc49e8a445eec2fc6cfcc9daceeb8599b6954639ec4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T16:54:30Z","title_canon_sha256":"b357da063459f8cab544047785b18a0190b6a171f63b7dde1c790b84aca76229"},"schema_version":"1.0","source":{"id":"2509.02503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02503","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02503v1","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02503","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"Y4MEET6IDWVA","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"Y4MEET6IDWVAWPDS","created_at":"2026-07-05T12:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"Y4MEET6I","created_at":"2026-07-05T12:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:c1f8685afc36a275818dbaa60652dd4c7bb4221262b176f35fb6edbdc5a4f848","target":"graph","created_at":"2026-07-05T12:03:39Z","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/2509.02503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic evaluation in low-resource languages remains a major challenge in NLP. While sentence transformers have shown strong performance in high-resource settings, their effectiveness in Indic languages is underexplored due to a lack of high-quality benchmarks. To bridge this gap, we introduce L3Cube-IndicHeadline-ID, a curated headline identification dataset spanning ten low-resource Indic languages: Marathi, Hindi, Tamil, Gujarati, Odia, Kannada, Malayalam, Punjabi, Telugu, Bengali and English. Each language includes 20,000 news articles paired with four headline variants: the original, a s","authors_text":"Darshan Gohad, Nishant Tanksale, Raviraj Joshi, Sarvadnyaa Barate, Tanmay Kokate","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T16:54:30Z","title":"L3Cube-IndicHeadline-ID: A Dataset for Headline Identification and Semantic Evaluation in Low-Resource Indian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02503","kind":"arxiv","version":1},"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":"sha256:87d02e521be52ff9ea3fb655fec01eff0f71ae916782bb1cd54e4378176dc95a","target":"record","created_at":"2026-07-05T12:03:39Z","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":"fc9f6a536d725d73c2458dc49e8a445eec2fc6cfcc9daceeb8599b6954639ec4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T16:54:30Z","title_canon_sha256":"b357da063459f8cab544047785b18a0190b6a171f63b7dde1c790b84aca76229"},"schema_version":"1.0","source":{"id":"2509.02503","kind":"arxiv","version":1}},"canonical_sha256":"c718424fc81daa0b3c7280e30329c9a0b2f149d3c1c4ee0f4e0d128c0df017f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c718424fc81daa0b3c7280e30329c9a0b2f149d3c1c4ee0f4e0d128c0df017f2","first_computed_at":"2026-07-05T12:03:39.742089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:39.742089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XgT/5Q1IgsOkUM3yaAekQSYiUCD5kYuzvb2iEs15d9Tzg0d/wdt6EMcMa4cZZasIWKUaSEl7066HGe1a7FlkDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:39.742596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87d02e521be52ff9ea3fb655fec01eff0f71ae916782bb1cd54e4378176dc95a","sha256:c1f8685afc36a275818dbaa60652dd4c7bb4221262b176f35fb6edbdc5a4f848"],"state_sha256":"503cbb90af69e1fa40e58e821f47c25262ad962cf486b2b030acdb2e1b7a4f28"}