{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GNPJ3USG45XEHS26I2QQMF2VZX","short_pith_number":"pith:GNPJ3USG","schema_version":"1.0","canonical_sha256":"335e9dd246e76e43cb5e46a1061755cdf474075babd2b2833121f01507c51799","source":{"kind":"arxiv","id":"2305.08828","version":2},"attestation_state":"computed","paper":{"title":"PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashok Urlana, Barry Haddow, Manish Shrivastava, Pinzhen Chen, Shay B. Cohen, Zheng Zhao","submitted_at":"2023-05-15T17:41:15Z","abstract_excerpt":"This paper introduces PMIndiaSum, a multilingual and massively parallel summarization corpus focused on languages in India. Our corpus provides a training and testing ground for four language families, 14 languages, and the largest to date with 196 language pairs. We detail our construction workflow including data acquisition, processing, and quality assurance. Furthermore, we publish benchmarks for monolingual, cross-lingual, and multilingual summarization by fine-tuning, prompting, as well as translate-and-summarize. Experimental results confirm the crucial role of our data in aiding summari"},"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":"2305.08828","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T17:41:15Z","cross_cats_sorted":[],"title_canon_sha256":"64f3ba9b48f8d3eec7a4f80490ef36d359149ff714c75c8a291ecb81370ff866","abstract_canon_sha256":"ce60ad8ab9e4e1dcdc8a53df3a64aa6e7e97271b79769d0b446b0211056d9bfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:49.877666Z","signature_b64":"52d65EHuYkXlaBdE8IiI/7Plm+SMZ0cFAz+NtyZmsMcxdZLWXUmIPhASVpCHJTyF2QkKVCd//gEB3iYQI39sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"335e9dd246e76e43cb5e46a1061755cdf474075babd2b2833121f01507c51799","last_reissued_at":"2026-07-05T07:02:49.877182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:49.877182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashok Urlana, Barry Haddow, Manish Shrivastava, Pinzhen Chen, Shay B. Cohen, Zheng Zhao","submitted_at":"2023-05-15T17:41:15Z","abstract_excerpt":"This paper introduces PMIndiaSum, a multilingual and massively parallel summarization corpus focused on languages in India. Our corpus provides a training and testing ground for four language families, 14 languages, and the largest to date with 196 language pairs. We detail our construction workflow including data acquisition, processing, and quality assurance. Furthermore, we publish benchmarks for monolingual, cross-lingual, and multilingual summarization by fine-tuning, prompting, as well as translate-and-summarize. Experimental results confirm the crucial role of our data in aiding summari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08828","kind":"arxiv","version":2},"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/2305.08828/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":"2305.08828","created_at":"2026-07-05T07:02:49.877248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08828v2","created_at":"2026-07-05T07:02:49.877248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08828","created_at":"2026-07-05T07:02:49.877248+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNPJ3USG45XE","created_at":"2026-07-05T07:02:49.877248+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNPJ3USG45XEHS26","created_at":"2026-07-05T07:02:49.877248+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNPJ3USG","created_at":"2026-07-05T07:02:49.877248+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/GNPJ3USG45XEHS26I2QQMF2VZX","json":"https://pith.science/pith/GNPJ3USG45XEHS26I2QQMF2VZX.json","graph_json":"https://pith.science/api/pith-number/GNPJ3USG45XEHS26I2QQMF2VZX/graph.json","events_json":"https://pith.science/api/pith-number/GNPJ3USG45XEHS26I2QQMF2VZX/events.json","paper":"https://pith.science/paper/GNPJ3USG"},"agent_actions":{"view_html":"https://pith.science/pith/GNPJ3USG45XEHS26I2QQMF2VZX","download_json":"https://pith.science/pith/GNPJ3USG45XEHS26I2QQMF2VZX.json","view_paper":"https://pith.science/paper/GNPJ3USG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08828&json=true","fetch_graph":"https://pith.science/api/pith-number/GNPJ3USG45XEHS26I2QQMF2VZX/graph.json","fetch_events":"https://pith.science/api/pith-number/GNPJ3USG45XEHS26I2QQMF2VZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNPJ3USG45XEHS26I2QQMF2VZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNPJ3USG45XEHS26I2QQMF2VZX/action/storage_attestation","attest_author":"https://pith.science/pith/GNPJ3USG45XEHS26I2QQMF2VZX/action/author_attestation","sign_citation":"https://pith.science/pith/GNPJ3USG45XEHS26I2QQMF2VZX/action/citation_signature","submit_replication":"https://pith.science/pith/GNPJ3USG45XEHS26I2QQMF2VZX/action/replication_record"}},"created_at":"2026-07-05T07:02:49.877248+00:00","updated_at":"2026-07-05T07:02:49.877248+00:00"}