{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VBEKGOOLLEJ3P7TRFCTW6QFZNA","short_pith_number":"pith:VBEKGOOL","canonical_record":{"source":{"id":"2103.10730","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-19T11:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"e6b06769904e7a34baad5fab7a66ddc47781977ca94f2715cce0d89a03a8304c","abstract_canon_sha256":"e5db59bfb2d07aefdef66e94e7893e98b4b3c0f15b2eeebd46dcd430adc901b7"},"schema_version":"1.0"},"canonical_sha256":"a848a339cb5913b7fe7128a76f40b9681ea3ca5f5c93a564864e8ae4b93491ed","source":{"kind":"arxiv","id":"2103.10730","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10730","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10730v2","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10730","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"pith_short_12","alias_value":"VBEKGOOLLEJ3","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"pith_short_16","alias_value":"VBEKGOOLLEJ3P7TR","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"pith_short_8","alias_value":"VBEKGOOL","created_at":"2026-07-05T02:28:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VBEKGOOLLEJ3P7TRFCTW6QFZNA","target":"record","payload":{"canonical_record":{"source":{"id":"2103.10730","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-19T11:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"e6b06769904e7a34baad5fab7a66ddc47781977ca94f2715cce0d89a03a8304c","abstract_canon_sha256":"e5db59bfb2d07aefdef66e94e7893e98b4b3c0f15b2eeebd46dcd430adc901b7"},"schema_version":"1.0"},"canonical_sha256":"a848a339cb5913b7fe7128a76f40b9681ea3ca5f5c93a564864e8ae4b93491ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:34.512087Z","signature_b64":"EleBkALcbfwlXxZ2/ulM6AFQKsWVneEKs7+laHkqppEv06RaiKPw/RtjEUycOQCqzTtHPrhypfFCfe+HgLatAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a848a339cb5913b7fe7128a76f40b9681ea3ca5f5c93a564864e8ae4b93491ed","last_reissued_at":"2026-07-05T02:28:34.511481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:34.511481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.10730","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":"2026-07-05T02:28:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zhZN1fXQvbveMvQEJd0BcWEPjAeq7IKhxlqTVDdAgjJyfyq9ksi7CiqGkAU34/QrXo27kfgMRnW3kXM2Yt/ABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T07:23:39.213682Z"},"content_sha256":"f71a445d4040431f5a4b89b845301675b12a934269e243a09ade2ee0827f325c","schema_version":"1.0","event_id":"sha256:f71a445d4040431f5a4b89b845301675b12a934269e243a09ade2ee0827f325c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VBEKGOOLLEJ3P7TRFCTW6QFZNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MuRIL: Multilingual Representations for Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Atreyee Dey, Balaji Gopalan, Diksha Bansal, Dilip Kumar Margam, Partha Talukdar, Pooja Aggarwal, Rajiv Teja Nagipogu, Sarvesh Mehtani, Savya Khosla, Shachi Dave, Shruti Gupta, Simran Khanuja, Subhash Chandra Bose Gali, Vish Subramanian","submitted_at":"2021-03-19T11:06:37Z","abstract_excerpt":"India is a multilingual society with 1369 rationalized languages and dialects being spoken across the country (INDIA, 2011). Of these, the 22 scheduled languages have a staggering total of 1.17 billion speakers and 121 languages have more than 10,000 speakers (INDIA, 2011). India also has the second largest (and an ever growing) digital footprint (Statista, 2020). Despite this, today's state-of-the-art multilingual systems perform suboptimally on Indian (IN) languages. This can be explained by the fact that multilingual language models (LMs) are often trained on 100+ languages together, leadin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10730","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/2103.10730/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":"2026-07-05T02:28:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NMaPSU5lPnN+0Ub0ZQD7UIu1+DinHS5oRaYHAaYdfv9IkxZljVQHcCb1VhtvTMNSSq3GHCRbDEjpby2PkSBpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T07:23:39.214045Z"},"content_sha256":"92937d887c06d0be184bab1b99b7320c5205b8d5316326ae60f184c3e5cf9dfa","schema_version":"1.0","event_id":"sha256:92937d887c06d0be184bab1b99b7320c5205b8d5316326ae60f184c3e5cf9dfa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/bundle.json","state_url":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/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":"2026-07-10T07:23:39Z","links":{"resolver":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA","bundle":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/bundle.json","state":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VBEKGOOLLEJ3P7TRFCTW6QFZNA","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":"e5db59bfb2d07aefdef66e94e7893e98b4b3c0f15b2eeebd46dcd430adc901b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-19T11:06:37Z","title_canon_sha256":"e6b06769904e7a34baad5fab7a66ddc47781977ca94f2715cce0d89a03a8304c"},"schema_version":"1.0","source":{"id":"2103.10730","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10730","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10730v2","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10730","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"pith_short_12","alias_value":"VBEKGOOLLEJ3","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"pith_short_16","alias_value":"VBEKGOOLLEJ3P7TR","created_at":"2026-07-05T02:28:34Z"},{"alias_kind":"pith_short_8","alias_value":"VBEKGOOL","created_at":"2026-07-05T02:28:34Z"}],"graph_snapshots":[{"event_id":"sha256:92937d887c06d0be184bab1b99b7320c5205b8d5316326ae60f184c3e5cf9dfa","target":"graph","created_at":"2026-07-05T02:28:34Z","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/2103.10730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"India is a multilingual society with 1369 rationalized languages and dialects being spoken across the country (INDIA, 2011). Of these, the 22 scheduled languages have a staggering total of 1.17 billion speakers and 121 languages have more than 10,000 speakers (INDIA, 2011). India also has the second largest (and an ever growing) digital footprint (Statista, 2020). Despite this, today's state-of-the-art multilingual systems perform suboptimally on Indian (IN) languages. This can be explained by the fact that multilingual language models (LMs) are often trained on 100+ languages together, leadin","authors_text":"Atreyee Dey, Balaji Gopalan, Diksha Bansal, Dilip Kumar Margam, Partha Talukdar, Pooja Aggarwal, Rajiv Teja Nagipogu, Sarvesh Mehtani, Savya Khosla, Shachi Dave, Shruti Gupta, Simran Khanuja, Subhash Chandra Bose Gali, Vish Subramanian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-19T11:06:37Z","title":"MuRIL: Multilingual Representations for Indian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10730","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:f71a445d4040431f5a4b89b845301675b12a934269e243a09ade2ee0827f325c","target":"record","created_at":"2026-07-05T02:28:34Z","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":"e5db59bfb2d07aefdef66e94e7893e98b4b3c0f15b2eeebd46dcd430adc901b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-19T11:06:37Z","title_canon_sha256":"e6b06769904e7a34baad5fab7a66ddc47781977ca94f2715cce0d89a03a8304c"},"schema_version":"1.0","source":{"id":"2103.10730","kind":"arxiv","version":2}},"canonical_sha256":"a848a339cb5913b7fe7128a76f40b9681ea3ca5f5c93a564864e8ae4b93491ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a848a339cb5913b7fe7128a76f40b9681ea3ca5f5c93a564864e8ae4b93491ed","first_computed_at":"2026-07-05T02:28:34.511481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:34.511481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EleBkALcbfwlXxZ2/ulM6AFQKsWVneEKs7+laHkqppEv06RaiKPw/RtjEUycOQCqzTtHPrhypfFCfe+HgLatAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:34.512087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.10730","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f71a445d4040431f5a4b89b845301675b12a934269e243a09ade2ee0827f325c","sha256:92937d887c06d0be184bab1b99b7320c5205b8d5316326ae60f184c3e5cf9dfa"],"state_sha256":"2d6540598532e3e676bf5a700faf3fe13d6134172a21cee8d8fdc98f283cc871"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUAvUco0EVHWVpUki5UeLmcY6H3Fea3AcF5wvDag4LEluPU+0ZUzZZmnFklBwlQY1dmNWwHl1QsUx7icktDGDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T07:23:39.215879Z","bundle_sha256":"9a8fa2cca0565bb85b3ecf6281d28be85665e4bd6800693acb166af4de356633"}}