{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:R3ZPIC54S2KTX2QRY6XJWT7NCT","short_pith_number":"pith:R3ZPIC54","canonical_record":{"source":{"id":"2005.00085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T20:21:02Z","cross_cats_sorted":[],"title_canon_sha256":"a2143ec0f56c2ef48c1344dd2ebff4f8b459b211f02f6ac1521c1f58a22cf076","abstract_canon_sha256":"45560b3b5940e86ba12b1fd75603cca49f2713500b37f54e4056d6479715ce18"},"schema_version":"1.0"},"canonical_sha256":"8ef2f40bbc96953bea11c7ae9b4fed14cabc31df96562d563782f775927648a1","source":{"kind":"arxiv","id":"2005.00085","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00085","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00085v1","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00085","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"R3ZPIC54S2KT","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_16","alias_value":"R3ZPIC54S2KTX2QR","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_8","alias_value":"R3ZPIC54","created_at":"2026-07-05T00:59:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:R3ZPIC54S2KTX2QRY6XJWT7NCT","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T20:21:02Z","cross_cats_sorted":[],"title_canon_sha256":"a2143ec0f56c2ef48c1344dd2ebff4f8b459b211f02f6ac1521c1f58a22cf076","abstract_canon_sha256":"45560b3b5940e86ba12b1fd75603cca49f2713500b37f54e4056d6479715ce18"},"schema_version":"1.0"},"canonical_sha256":"8ef2f40bbc96953bea11c7ae9b4fed14cabc31df96562d563782f775927648a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:37.853593Z","signature_b64":"LuDE3GDw8RXIZe+XeA/NbrvTYvWLDDjNMr2yEv6qDR0nLasqjEZYByTuR+4daPjTmiZxaaQTYr9QJzUODkArBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ef2f40bbc96953bea11c7ae9b4fed14cabc31df96562d563782f775927648a1","last_reissued_at":"2026-07-05T00:59:37.853090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:37.853090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00085","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":"2026-07-05T00:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"URZ+pyeA9yrW3NLYNH6XMXmw51+KyToXHdEkrKXzAj3zSIREPBNQcadc4bORZtuPbpMVnzfMBIWD/Vn/Joq2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:03:00.912675Z"},"content_sha256":"5eac214101034ebb9165373920f655b0dea5326c590f06455dd5cdc582ae2bbe","schema_version":"1.0","event_id":"sha256:5eac214101034ebb9165373920f655b0dea5326c590f06455dd5cdc582ae2bbe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:R3ZPIC54S2KTX2QRY6XJWT7NCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Avik Bhattacharyya, Divyanshu Kakwani, Gokul N.C., Mitesh M. Khapra, Pratyush Kumar, Satish Golla","submitted_at":"2020-04-30T20:21:02Z","abstract_excerpt":"We present the IndicNLP corpus, a large-scale, general-domain corpus containing 2.7 billion words for 10 Indian languages from two language families. We share pre-trained word embeddings trained on these corpora. We create news article category classification datasets for 9 languages to evaluate the embeddings. We show that the IndicNLP embeddings significantly outperform publicly available pre-trained embedding on multiple evaluation tasks. We hope that the availability of the corpus will accelerate Indic NLP research. The resources are available at https://github.com/ai4bharat-indicnlp/indic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00085","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/2005.00085/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":"2026-07-05T00:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+fw4gUHGu514PzuWCKaDDGZazkYa+R2YNsySaftMc2Bv9UMEZ9pFoN4PoD4iYcMT82C52gFsEfFjYAQY5XL2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:03:00.913051Z"},"content_sha256":"3413a808b9187dc1b24217bec0b1194ce340385c90c8b1e4d05e72775e043cf3","schema_version":"1.0","event_id":"sha256:3413a808b9187dc1b24217bec0b1194ce340385c90c8b1e4d05e72775e043cf3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3ZPIC54S2KTX2QRY6XJWT7NCT/bundle.json","state_url":"https://pith.science/pith/R3ZPIC54S2KTX2QRY6XJWT7NCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3ZPIC54S2KTX2QRY6XJWT7NCT/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":"2026-07-09T06:03:00Z","links":{"resolver":"https://pith.science/pith/R3ZPIC54S2KTX2QRY6XJWT7NCT","bundle":"https://pith.science/pith/R3ZPIC54S2KTX2QRY6XJWT7NCT/bundle.json","state":"https://pith.science/pith/R3ZPIC54S2KTX2QRY6XJWT7NCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3ZPIC54S2KTX2QRY6XJWT7NCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:R3ZPIC54S2KTX2QRY6XJWT7NCT","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":"45560b3b5940e86ba12b1fd75603cca49f2713500b37f54e4056d6479715ce18","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T20:21:02Z","title_canon_sha256":"a2143ec0f56c2ef48c1344dd2ebff4f8b459b211f02f6ac1521c1f58a22cf076"},"schema_version":"1.0","source":{"id":"2005.00085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00085","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00085v1","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00085","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"R3ZPIC54S2KT","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_16","alias_value":"R3ZPIC54S2KTX2QR","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_8","alias_value":"R3ZPIC54","created_at":"2026-07-05T00:59:37Z"}],"graph_snapshots":[{"event_id":"sha256:3413a808b9187dc1b24217bec0b1194ce340385c90c8b1e4d05e72775e043cf3","target":"graph","created_at":"2026-07-05T00:59:37Z","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/2005.00085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the IndicNLP corpus, a large-scale, general-domain corpus containing 2.7 billion words for 10 Indian languages from two language families. We share pre-trained word embeddings trained on these corpora. We create news article category classification datasets for 9 languages to evaluate the embeddings. We show that the IndicNLP embeddings significantly outperform publicly available pre-trained embedding on multiple evaluation tasks. We hope that the availability of the corpus will accelerate Indic NLP research. The resources are available at https://github.com/ai4bharat-indicnlp/indic","authors_text":"Anoop Kunchukuttan, Avik Bhattacharyya, Divyanshu Kakwani, Gokul N.C., Mitesh M. Khapra, Pratyush Kumar, Satish Golla","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T20:21:02Z","title":"AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00085","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":"sha256:5eac214101034ebb9165373920f655b0dea5326c590f06455dd5cdc582ae2bbe","target":"record","created_at":"2026-07-05T00:59:37Z","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":"45560b3b5940e86ba12b1fd75603cca49f2713500b37f54e4056d6479715ce18","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T20:21:02Z","title_canon_sha256":"a2143ec0f56c2ef48c1344dd2ebff4f8b459b211f02f6ac1521c1f58a22cf076"},"schema_version":"1.0","source":{"id":"2005.00085","kind":"arxiv","version":1}},"canonical_sha256":"8ef2f40bbc96953bea11c7ae9b4fed14cabc31df96562d563782f775927648a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ef2f40bbc96953bea11c7ae9b4fed14cabc31df96562d563782f775927648a1","first_computed_at":"2026-07-05T00:59:37.853090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:37.853090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LuDE3GDw8RXIZe+XeA/NbrvTYvWLDDjNMr2yEv6qDR0nLasqjEZYByTuR+4daPjTmiZxaaQTYr9QJzUODkArBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:37.853593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5eac214101034ebb9165373920f655b0dea5326c590f06455dd5cdc582ae2bbe","sha256:3413a808b9187dc1b24217bec0b1194ce340385c90c8b1e4d05e72775e043cf3"],"state_sha256":"d2d67c1a84554984ec62d1eb9e13edaefb6945d5aaea21f229647e776edcc09a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p5PuW3BYXLdh5aRDJyBSC3OSLqkKOrF0YA1vaJKnRSuJQSrgAM2APhCJTcHiOGC2lZviFPUwPpRzXOCbtxVGDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:03:00.915273Z","bundle_sha256":"19dcfcf638e01abb942bd5fb041cdfd711ffef38d525cfaf858d50fd0ec18824"}}