{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WRPY4NMEBPVVHRANWAGMZV7A62","short_pith_number":"pith:WRPY4NME","canonical_record":{"source":{"id":"2305.05858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-10T03:07:17Z","cross_cats_sorted":[],"title_canon_sha256":"155616cdd75fbb14e9d7b40ed3d8093259a6eb65ae9289e0ca26aeccf4dfdae2","abstract_canon_sha256":"3f254309a04969ee32eebd3b66eaf8425d7d130c7167c094a1fd03467e7fa439"},"schema_version":"1.0"},"canonical_sha256":"b45f8e35840beb53c40db00cccd7e0f6bb6d858d0bc8cbdb145663b98a258328","source":{"kind":"arxiv","id":"2305.05858","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05858","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05858v1","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05858","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"WRPY4NMEBPVV","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"WRPY4NMEBPVVHRAN","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"WRPY4NME","created_at":"2026-07-05T06:08:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WRPY4NMEBPVVHRANWAGMZV7A62","target":"record","payload":{"canonical_record":{"source":{"id":"2305.05858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-10T03:07:17Z","cross_cats_sorted":[],"title_canon_sha256":"155616cdd75fbb14e9d7b40ed3d8093259a6eb65ae9289e0ca26aeccf4dfdae2","abstract_canon_sha256":"3f254309a04969ee32eebd3b66eaf8425d7d130c7167c094a1fd03467e7fa439"},"schema_version":"1.0"},"canonical_sha256":"b45f8e35840beb53c40db00cccd7e0f6bb6d858d0bc8cbdb145663b98a258328","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:56.845067Z","signature_b64":"JUbhzSD48P3KaiGXwepospMc3yZqULym7pM0ZSITWMRruWsWCc6zQRfvmLMRWQInyLAG0TBiWv14l+W9rKBkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b45f8e35840beb53c40db00cccd7e0f6bb6d858d0bc8cbdb145663b98a258328","last_reissued_at":"2026-07-05T06:08:56.844692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:56.844692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.05858","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iPOu+pPN7Ko2DxpbG/WphDSbbHBPtH848MCJKC7hB82ZqK3paJGfG384ak7dLpU19C1+duGMHgf9WOPLzYZBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:00:19.674577Z"},"content_sha256":"dbdd25a0e95290c1c191e76635fc0ecdfba3ded7b932037e9714c34c16a7c3df","schema_version":"1.0","event_id":"sha256:dbdd25a0e95290c1c191e76635fc0ecdfba3ded7b932037e9714c34c16a7c3df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WRPY4NMEBPVVHRANWAGMZV7A62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"V\\=arta: A Large-Scale Headline-Generation Dataset for Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jackie Chi Kit Cheung, Rahul Aralikatte, Sumanth Doddapaneni, Ziling Cheng","submitted_at":"2023-05-10T03:07:17Z","abstract_excerpt":"We present V\\=arta, a large-scale multilingual dataset for headline generation in Indic languages. This dataset includes 41.8 million news articles in 14 different Indic languages (and English), which come from a variety of high-quality sources. To the best of our knowledge, this is the largest collection of curated articles for Indic languages currently available. We use the data collected in a series of experiments to answer important questions related to Indic NLP and multilinguality research in general. We show that the dataset is challenging even for state-of-the-art abstractive models an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05858","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/2305.05858/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jev53LDNAGsQ9Hvl89z2/0gVI76dseEQBq4g1+JCApIGEfQsRIp3y6YHw5cKNdVh2uAQYwgmYLmpuGNbh/8vDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:00:19.675461Z"},"content_sha256":"39d36c8c853a2099f58be52d5ac6f30170a634bf26810ea410a45041a8f0e895","schema_version":"1.0","event_id":"sha256:39d36c8c853a2099f58be52d5ac6f30170a634bf26810ea410a45041a8f0e895"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62/bundle.json","state_url":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WRPY4NMEBPVVHRANWAGMZV7A62/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T14:00:19Z","links":{"resolver":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62","bundle":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62/bundle.json","state":"https://pith.science/pith/WRPY4NMEBPVVHRANWAGMZV7A62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WRPY4NMEBPVVHRANWAGMZV7A62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WRPY4NMEBPVVHRANWAGMZV7A62","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":"3f254309a04969ee32eebd3b66eaf8425d7d130c7167c094a1fd03467e7fa439","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-10T03:07:17Z","title_canon_sha256":"155616cdd75fbb14e9d7b40ed3d8093259a6eb65ae9289e0ca26aeccf4dfdae2"},"schema_version":"1.0","source":{"id":"2305.05858","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05858","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05858v1","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05858","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"WRPY4NMEBPVV","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"WRPY4NMEBPVVHRAN","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"WRPY4NME","created_at":"2026-07-05T06:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:39d36c8c853a2099f58be52d5ac6f30170a634bf26810ea410a45041a8f0e895","target":"graph","created_at":"2026-07-05T06:08:56Z","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/2305.05858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present V\\=arta, a large-scale multilingual dataset for headline generation in Indic languages. This dataset includes 41.8 million news articles in 14 different Indic languages (and English), which come from a variety of high-quality sources. To the best of our knowledge, this is the largest collection of curated articles for Indic languages currently available. We use the data collected in a series of experiments to answer important questions related to Indic NLP and multilinguality research in general. We show that the dataset is challenging even for state-of-the-art abstractive models an","authors_text":"Jackie Chi Kit Cheung, Rahul Aralikatte, Sumanth Doddapaneni, Ziling Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-10T03:07:17Z","title":"V\\=arta: A Large-Scale Headline-Generation Dataset for Indic Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05858","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:dbdd25a0e95290c1c191e76635fc0ecdfba3ded7b932037e9714c34c16a7c3df","target":"record","created_at":"2026-07-05T06:08:56Z","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":"3f254309a04969ee32eebd3b66eaf8425d7d130c7167c094a1fd03467e7fa439","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-10T03:07:17Z","title_canon_sha256":"155616cdd75fbb14e9d7b40ed3d8093259a6eb65ae9289e0ca26aeccf4dfdae2"},"schema_version":"1.0","source":{"id":"2305.05858","kind":"arxiv","version":1}},"canonical_sha256":"b45f8e35840beb53c40db00cccd7e0f6bb6d858d0bc8cbdb145663b98a258328","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b45f8e35840beb53c40db00cccd7e0f6bb6d858d0bc8cbdb145663b98a258328","first_computed_at":"2026-07-05T06:08:56.844692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:56.844692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JUbhzSD48P3KaiGXwepospMc3yZqULym7pM0ZSITWMRruWsWCc6zQRfvmLMRWQInyLAG0TBiWv14l+W9rKBkBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:56.845067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05858","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbdd25a0e95290c1c191e76635fc0ecdfba3ded7b932037e9714c34c16a7c3df","sha256:39d36c8c853a2099f58be52d5ac6f30170a634bf26810ea410a45041a8f0e895"],"state_sha256":"20647761f046e3ae797bff702cb6bc7a6ec19b539750dd7cf50cfef1b682ec3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FTpLWv2Kw8MghortV7ICdfjMar2JYlbT9RD8EUSxfGmi/vvHz9xwZAJ6VqqXp6d4fuQZoiS8UoGJiPpZuKunAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:00:19.687092Z","bundle_sha256":"bdb5eae711d0638756a519ddb7ab84ef51ed6039c6d39bf08243c0efa1eb9ae5"}}