{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:PYPTPORFIEBFAVWLPZWVUHNVT6","short_pith_number":"pith:PYPTPORF","canonical_record":{"source":{"id":"2212.10168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T11:15:24Z","cross_cats_sorted":[],"title_canon_sha256":"88dae25920430e91aea9a10eabccc5a539fa6cbe51819b62b22773e61263e71d","abstract_canon_sha256":"6340710a9b231b4bd63d9686a1072515ced629f6f52693e2485929910c111c1d"},"schema_version":"1.0"},"canonical_sha256":"7e1f37ba2541025056cb7e6d5a1db59f9fd0a9fcf6b8584fb86d8094517ae18a","source":{"kind":"arxiv","id":"2212.10168","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10168","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10168v2","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10168","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"PYPTPORFIEBF","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"PYPTPORFIEBFAVWL","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"PYPTPORF","created_at":"2026-07-05T06:14:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:PYPTPORFIEBFAVWLPZWVUHNVT6","target":"record","payload":{"canonical_record":{"source":{"id":"2212.10168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T11:15:24Z","cross_cats_sorted":[],"title_canon_sha256":"88dae25920430e91aea9a10eabccc5a539fa6cbe51819b62b22773e61263e71d","abstract_canon_sha256":"6340710a9b231b4bd63d9686a1072515ced629f6f52693e2485929910c111c1d"},"schema_version":"1.0"},"canonical_sha256":"7e1f37ba2541025056cb7e6d5a1db59f9fd0a9fcf6b8584fb86d8094517ae18a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:39.134557Z","signature_b64":"+xfddbrCcCfg35MWXPzhd1NMMEFUGpVHv4d0NObzOCu2OeQuk+eY7njIGU+VXSpuyB6SwO+2V43x/SK9C3uVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e1f37ba2541025056cb7e6d5a1db59f9fd0a9fcf6b8584fb86d8094517ae18a","last_reissued_at":"2026-07-05T06:14:39.134003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:39.134003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.10168","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:14:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QM6iwBShwXvRHebTHSHKOAZd9PZkp7ZOOewYaN20xUXzhJc8fH8I9pua8XaQ/MvdJ6lj87bQZpjf6d6ALRSfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:26:47.320472Z"},"content_sha256":"b7c835722c44498a2166153bb260fb8d342f8fa824b1b14f4981aeca7ebf53a9","schema_version":"1.0","event_id":"sha256:b7c835722c44498a2166153bb260fb8d342f8fa824b1b14f4981aeca7ebf53a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:PYPTPORFIEBFAVWLPZWVUHNVT6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Arnav Mhaske, Harshit Kedia, Mitesh M. Khapra, Pratyush Kumar, Rudra Murthy V, Sumanth Doddapaneni","submitted_at":"2022-12-20T11:15:24Z","abstract_excerpt":"We present, Naamapadam, the largest publicly available Named Entity Recognition (NER) dataset for the 11 major Indian languages from two language families. The dataset contains more than 400k sentences annotated with a total of at least 100k entities from three standard entity categories (Person, Location, and, Organization) for 9 out of the 11 languages. The training dataset has been automatically created from the Samanantar parallel corpus by projecting automatically tagged entities from an English sentence to the corresponding Indian language translation. We also create manually annotated t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10168","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/2212.10168/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":"2026-07-05T06:14:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XDocz29Add8+KyNf1Z8hPzJmoKeOgR5zpZLlrCVDs7plrjUIcX4zvEYr8EkPytUy5jG8z521FSu2oXa3jtiYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:26:47.320850Z"},"content_sha256":"7b674825746122c17137e00bc8f6a4580cd3e6ccd01caca4bc76a6188938745a","schema_version":"1.0","event_id":"sha256:7b674825746122c17137e00bc8f6a4580cd3e6ccd01caca4bc76a6188938745a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYPTPORFIEBFAVWLPZWVUHNVT6/bundle.json","state_url":"https://pith.science/pith/PYPTPORFIEBFAVWLPZWVUHNVT6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYPTPORFIEBFAVWLPZWVUHNVT6/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":"2026-07-08T16:26:47Z","links":{"resolver":"https://pith.science/pith/PYPTPORFIEBFAVWLPZWVUHNVT6","bundle":"https://pith.science/pith/PYPTPORFIEBFAVWLPZWVUHNVT6/bundle.json","state":"https://pith.science/pith/PYPTPORFIEBFAVWLPZWVUHNVT6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYPTPORFIEBFAVWLPZWVUHNVT6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PYPTPORFIEBFAVWLPZWVUHNVT6","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":"6340710a9b231b4bd63d9686a1072515ced629f6f52693e2485929910c111c1d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T11:15:24Z","title_canon_sha256":"88dae25920430e91aea9a10eabccc5a539fa6cbe51819b62b22773e61263e71d"},"schema_version":"1.0","source":{"id":"2212.10168","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10168","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10168v2","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10168","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"PYPTPORFIEBF","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"PYPTPORFIEBFAVWL","created_at":"2026-07-05T06:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"PYPTPORF","created_at":"2026-07-05T06:14:39Z"}],"graph_snapshots":[{"event_id":"sha256:7b674825746122c17137e00bc8f6a4580cd3e6ccd01caca4bc76a6188938745a","target":"graph","created_at":"2026-07-05T06:14:39Z","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/2212.10168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present, Naamapadam, the largest publicly available Named Entity Recognition (NER) dataset for the 11 major Indian languages from two language families. The dataset contains more than 400k sentences annotated with a total of at least 100k entities from three standard entity categories (Person, Location, and, Organization) for 9 out of the 11 languages. The training dataset has been automatically created from the Samanantar parallel corpus by projecting automatically tagged entities from an English sentence to the corresponding Indian language translation. We also create manually annotated t","authors_text":"Anoop Kunchukuttan, Arnav Mhaske, Harshit Kedia, Mitesh M. Khapra, Pratyush Kumar, Rudra Murthy V, Sumanth Doddapaneni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T11:15:24Z","title":"Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10168","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:b7c835722c44498a2166153bb260fb8d342f8fa824b1b14f4981aeca7ebf53a9","target":"record","created_at":"2026-07-05T06:14:39Z","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":"6340710a9b231b4bd63d9686a1072515ced629f6f52693e2485929910c111c1d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T11:15:24Z","title_canon_sha256":"88dae25920430e91aea9a10eabccc5a539fa6cbe51819b62b22773e61263e71d"},"schema_version":"1.0","source":{"id":"2212.10168","kind":"arxiv","version":2}},"canonical_sha256":"7e1f37ba2541025056cb7e6d5a1db59f9fd0a9fcf6b8584fb86d8094517ae18a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e1f37ba2541025056cb7e6d5a1db59f9fd0a9fcf6b8584fb86d8094517ae18a","first_computed_at":"2026-07-05T06:14:39.134003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:39.134003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+xfddbrCcCfg35MWXPzhd1NMMEFUGpVHv4d0NObzOCu2OeQuk+eY7njIGU+VXSpuyB6SwO+2V43x/SK9C3uVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:39.134557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10168","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7c835722c44498a2166153bb260fb8d342f8fa824b1b14f4981aeca7ebf53a9","sha256:7b674825746122c17137e00bc8f6a4580cd3e6ccd01caca4bc76a6188938745a"],"state_sha256":"4e6417346bfd54a1c90820160da77c11add7aea707a9adfd56978ad5308728ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OYiWE2FhxQQLqd1RrYISmycZFRK2F1M7riv7X6w4TW+vq2SbBRRnKcheTxhLVdK3M/vMwV7k9ZYJFBQqXyiZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T16:26:47.322890Z","bundle_sha256":"a5aaf32a33bae0dff34f026ca6ebf1acd07e4f1bc7bb4c40115130a34fdebdb6"}}