{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ETH6I3R5KCCQRIC5B4HTNT5IA3","short_pith_number":"pith:ETH6I3R5","canonical_record":{"source":{"id":"2203.16595","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T18:22:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"36b09071a168680f998dc3b63e4747154c405fa93e9c737c25ba19bb852f3346","abstract_canon_sha256":"8193229ae8bf7acdb38eee5ed5961ee3552f6b8954a57e0aee6ee4c0126d6ba2"},"schema_version":"1.0"},"canonical_sha256":"24cfe46e3d508508a05d0f0f36cfa806f36b08edef91c0a8c5a29a092364d527","source":{"kind":"arxiv","id":"2203.16595","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16595","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16595v3","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16595","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"ETH6I3R5KCCQ","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ETH6I3R5KCCQRIC5","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ETH6I3R5","created_at":"2026-07-05T04:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ETH6I3R5KCCQRIC5B4HTNT5IA3","target":"record","payload":{"canonical_record":{"source":{"id":"2203.16595","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T18:22:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"36b09071a168680f998dc3b63e4747154c405fa93e9c737c25ba19bb852f3346","abstract_canon_sha256":"8193229ae8bf7acdb38eee5ed5961ee3552f6b8954a57e0aee6ee4c0126d6ba2"},"schema_version":"1.0"},"canonical_sha256":"24cfe46e3d508508a05d0f0f36cfa806f36b08edef91c0a8c5a29a092364d527","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:59.926832Z","signature_b64":"3pMhDrGJ2gjAeN+9xZLNcoYNBXALCDpMqouSENbHioy88A2+2Yqa9k2DMB/9RbLvOdmsmzrGQ/LsjQytfrCYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24cfe46e3d508508a05d0f0f36cfa806f36b08edef91c0a8c5a29a092364d527","last_reissued_at":"2026-07-05T04:31:59.926393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:59.926393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.16595","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:31:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zpLNrBkrqDcj5UHFhCrFssiDmYPh41G3f4bWSiwsoHcSq8MVblPdWPeq5KOowVzDzuV5G+hZ5WmpMj8gVRkdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:06:25.752585Z"},"content_sha256":"7a29d0055fdde449aed0c2d23333ab701f0a509867afdfbd99cc28e53c92d16b","schema_version":"1.0","event_id":"sha256:7a29d0055fdde449aed0c2d23333ab701f0a509867afdfbd99cc28e53c92d16b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ETH6I3R5KCCQRIC5B4HTNT5IA3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Speech Recognition for Indic Languages using Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Anirudh Gupta, Ankur Dhuriya, Harveen Singh Chadha, Neeraj Chhimwal, Priyanshi Shah, Rishabh Gaur, Vivek Raghavan","submitted_at":"2022-03-30T18:22:12Z","abstract_excerpt":"We study the effect of applying a language model (LM) on the output of Automatic Speech Recognition (ASR) systems for Indic languages. We fine-tune wav2vec $2.0$ models for $18$ Indic languages and adjust the results with language models trained on text derived from a variety of sources. Our findings demonstrate that the average Character Error Rate (CER) decreases by over $28$ \\% and the average Word Error Rate (WER) decreases by about $36$ \\% after decoding with LM. We show that a large LM may not provide a substantial improvement as compared to a diverse one. We also demonstrate that high q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16595","kind":"arxiv","version":3},"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/2203.16595/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":"2026-07-05T04:31:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbWZvIGl1m6f6P/8vXsKfBQL2JaQrtIOV7MLYwVgQ0cPOYwjzRC5SFCDtnM1m0iXk3wvSLtiGL2ZXupP6ZaSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:06:25.752992Z"},"content_sha256":"bd0f7fa2a22a6765458beadf87f103c5d7342319531cdb7458e9e7426ca14628","schema_version":"1.0","event_id":"sha256:bd0f7fa2a22a6765458beadf87f103c5d7342319531cdb7458e9e7426ca14628"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/bundle.json","state_url":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/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":"2026-07-08T16:06:25Z","links":{"resolver":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3","bundle":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/bundle.json","state":"https://pith.science/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETH6I3R5KCCQRIC5B4HTNT5IA3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ETH6I3R5KCCQRIC5B4HTNT5IA3","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":"8193229ae8bf7acdb38eee5ed5961ee3552f6b8954a57e0aee6ee4c0126d6ba2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T18:22:12Z","title_canon_sha256":"36b09071a168680f998dc3b63e4747154c405fa93e9c737c25ba19bb852f3346"},"schema_version":"1.0","source":{"id":"2203.16595","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16595","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16595v3","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16595","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"ETH6I3R5KCCQ","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ETH6I3R5KCCQRIC5","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ETH6I3R5","created_at":"2026-07-05T04:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:bd0f7fa2a22a6765458beadf87f103c5d7342319531cdb7458e9e7426ca14628","target":"graph","created_at":"2026-07-05T04:31:59Z","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/2203.16595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the effect of applying a language model (LM) on the output of Automatic Speech Recognition (ASR) systems for Indic languages. We fine-tune wav2vec $2.0$ models for $18$ Indic languages and adjust the results with language models trained on text derived from a variety of sources. Our findings demonstrate that the average Character Error Rate (CER) decreases by over $28$ \\% and the average Word Error Rate (WER) decreases by about $36$ \\% after decoding with LM. We show that a large LM may not provide a substantial improvement as compared to a diverse one. We also demonstrate that high q","authors_text":"Anirudh Gupta, Ankur Dhuriya, Harveen Singh Chadha, Neeraj Chhimwal, Priyanshi Shah, Rishabh Gaur, Vivek Raghavan","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T18:22:12Z","title":"Improving Speech Recognition for Indic Languages using Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16595","kind":"arxiv","version":3},"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":"sha256:7a29d0055fdde449aed0c2d23333ab701f0a509867afdfbd99cc28e53c92d16b","target":"record","created_at":"2026-07-05T04:31:59Z","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":"8193229ae8bf7acdb38eee5ed5961ee3552f6b8954a57e0aee6ee4c0126d6ba2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T18:22:12Z","title_canon_sha256":"36b09071a168680f998dc3b63e4747154c405fa93e9c737c25ba19bb852f3346"},"schema_version":"1.0","source":{"id":"2203.16595","kind":"arxiv","version":3}},"canonical_sha256":"24cfe46e3d508508a05d0f0f36cfa806f36b08edef91c0a8c5a29a092364d527","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24cfe46e3d508508a05d0f0f36cfa806f36b08edef91c0a8c5a29a092364d527","first_computed_at":"2026-07-05T04:31:59.926393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:31:59.926393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3pMhDrGJ2gjAeN+9xZLNcoYNBXALCDpMqouSENbHioy88A2+2Yqa9k2DMB/9RbLvOdmsmzrGQ/LsjQytfrCYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:31:59.926832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16595","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a29d0055fdde449aed0c2d23333ab701f0a509867afdfbd99cc28e53c92d16b","sha256:bd0f7fa2a22a6765458beadf87f103c5d7342319531cdb7458e9e7426ca14628"],"state_sha256":"18ab0febf0e36e9bee7d610870e66d1b1fc4a0bd00d0003fd301c3cfd4cede67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgyWSU4QF6RWsG0PFWertK1L6YxRYiCksm/M0P8WGRP6aP9SpVHNBN7aXQ72dVpGcUzVKPs4bjqqH4RZriAkBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T16:06:25.755073Z","bundle_sha256":"6b8a549fc519de3deeabed625ea5b231c437246c985c749d2f9a1f187703d0d8"}}