{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y4MEET6IDWVAWPDSQDRQGKOJUC","short_pith_number":"pith:Y4MEET6I","schema_version":"1.0","canonical_sha256":"c718424fc81daa0b3c7280e30329c9a0b2f149d3c1c4ee0f4e0d128c0df017f2","source":{"kind":"arxiv","id":"2509.02503","version":1},"attestation_state":"computed","paper":{"title":"L3Cube-IndicHeadline-ID: A Dataset for Headline Identification and Semantic Evaluation in Low-Resource Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Darshan Gohad, Nishant Tanksale, Raviraj Joshi, Sarvadnyaa Barate, Tanmay Kokate","submitted_at":"2025-09-02T16:54:30Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.02503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T16:54:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b357da063459f8cab544047785b18a0190b6a171f63b7dde1c790b84aca76229","abstract_canon_sha256":"fc9f6a536d725d73c2458dc49e8a445eec2fc6cfcc9daceeb8599b6954639ec4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:39.742596Z","signature_b64":"XgT/5Q1IgsOkUM3yaAekQSYiUCD5kYuzvb2iEs15d9Tzg0d/wdt6EMcMa4cZZasIWKUaSEl7066HGe1a7FlkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c718424fc81daa0b3c7280e30329c9a0b2f149d3c1c4ee0f4e0d128c0df017f2","last_reissued_at":"2026-07-05T12:03:39.742089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:39.742089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L3Cube-IndicHeadline-ID: A Dataset for Headline Identification and Semantic Evaluation in Low-Resource Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Darshan Gohad, Nishant Tanksale, Raviraj Joshi, Sarvadnyaa Barate, Tanmay Kokate","submitted_at":"2025-09-02T16:54:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02503","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.02503/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.02503","created_at":"2026-07-05T12:03:39.742150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02503v1","created_at":"2026-07-05T12:03:39.742150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02503","created_at":"2026-07-05T12:03:39.742150+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4MEET6IDWVA","created_at":"2026-07-05T12:03:39.742150+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4MEET6IDWVAWPDS","created_at":"2026-07-05T12:03:39.742150+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4MEET6I","created_at":"2026-07-05T12:03:39.742150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y4MEET6IDWVAWPDSQDRQGKOJUC","json":"https://pith.science/pith/Y4MEET6IDWVAWPDSQDRQGKOJUC.json","graph_json":"https://pith.science/api/pith-number/Y4MEET6IDWVAWPDSQDRQGKOJUC/graph.json","events_json":"https://pith.science/api/pith-number/Y4MEET6IDWVAWPDSQDRQGKOJUC/events.json","paper":"https://pith.science/paper/Y4MEET6I"},"agent_actions":{"view_html":"https://pith.science/pith/Y4MEET6IDWVAWPDSQDRQGKOJUC","download_json":"https://pith.science/pith/Y4MEET6IDWVAWPDSQDRQGKOJUC.json","view_paper":"https://pith.science/paper/Y4MEET6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02503&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4MEET6IDWVAWPDSQDRQGKOJUC/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4MEET6IDWVAWPDSQDRQGKOJUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4MEET6IDWVAWPDSQDRQGKOJUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4MEET6IDWVAWPDSQDRQGKOJUC/action/storage_attestation","attest_author":"https://pith.science/pith/Y4MEET6IDWVAWPDSQDRQGKOJUC/action/author_attestation","sign_citation":"https://pith.science/pith/Y4MEET6IDWVAWPDSQDRQGKOJUC/action/citation_signature","submit_replication":"https://pith.science/pith/Y4MEET6IDWVAWPDSQDRQGKOJUC/action/replication_record"}},"created_at":"2026-07-05T12:03:39.742150+00:00","updated_at":"2026-07-05T12:03:39.742150+00:00"}