{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QLXW7DYTYXURAK55MGNVLPMFUG","short_pith_number":"pith:QLXW7DYT","canonical_record":{"source":{"id":"2305.15386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:46:03Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"31891d7b96d31392bb89651cb997f29ff19701cb4960a72c54de3d871143ee4e","abstract_canon_sha256":"8284dabc2ff770d3f51c10e0ddf16710878bf9f57c314285cd2e24d5a6456938"},"schema_version":"1.0"},"canonical_sha256":"82ef6f8f13c5e9102bbd619b55bd85a1a80a21339772225f2c0a8c7b93b2ffb5","source":{"kind":"arxiv","id":"2305.15386","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15386","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15386v2","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15386","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"pith_short_12","alias_value":"QLXW7DYTYXUR","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"pith_short_16","alias_value":"QLXW7DYTYXURAK55","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"pith_short_8","alias_value":"QLXW7DYT","created_at":"2026-07-05T06:37:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QLXW7DYTYXURAK55MGNVLPMFUG","target":"record","payload":{"canonical_record":{"source":{"id":"2305.15386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:46:03Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"31891d7b96d31392bb89651cb997f29ff19701cb4960a72c54de3d871143ee4e","abstract_canon_sha256":"8284dabc2ff770d3f51c10e0ddf16710878bf9f57c314285cd2e24d5a6456938"},"schema_version":"1.0"},"canonical_sha256":"82ef6f8f13c5e9102bbd619b55bd85a1a80a21339772225f2c0a8c7b93b2ffb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:04.164275Z","signature_b64":"oBkIrtKkDuxIZVnxRF2DcX3Z5/+3PK21VsAplwfLMMCH1Q3RK0VSOxyhjdGMBrNNEnG6+VQ9GKCtJAg+X5kYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82ef6f8f13c5e9102bbd619b55bd85a1a80a21339772225f2c0a8c7b93b2ffb5","last_reissued_at":"2026-07-05T06:37:04.163767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:04.163767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.15386","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":"2026-07-05T06:37:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D4Ce0pAvVV1v4d1yyZNsi1fUaULJ95ez0w+RwbUCHRushBMolSmCYNTy+g021mx36YPXFPX4QvXUSvNJTaSXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:03:45.669005Z"},"content_sha256":"5ed1017fc9b1aba014283e18e3fe9c866621c188537bebda278ba378d47f2286","schema_version":"1.0","event_id":"sha256:5ed1017fc9b1aba014283e18e3fe9c866621c188537bebda278ba378d47f2286"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QLXW7DYTYXURAK55MGNVLPMFUG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abhigyan Raman, Kaushal Santosh Bhogale, Mitesh M. Khapra, Pratyush Kumar, Sai Sundaresan, Tahir Javed","submitted_at":"2023-05-24T17:46:03Z","abstract_excerpt":"Improving ASR systems is necessary to make new LLM-based use-cases accessible to people across the globe. In this paper, we focus on Indian languages, and make the case that diverse benchmarks are required to evaluate and improve ASR systems for Indian languages. To address this, we collate Vistaar as a set of 59 benchmarks across various language and domain combinations, on which we evaluate 3 publicly available ASR systems and 2 commercial systems. We also train IndicWhisper models by fine-tuning the Whisper models on publicly available training datasets across 12 Indian languages totalling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15386","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/2305.15386/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":"2026-07-05T06:37:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b/kTEXtVHNChH8HhFx6EDx0Go7pMSCKxfiNTwxrxcWvfO4AEJXgR1DAxWlhN9YAd+GAttylg12PSzNfcK5YQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:03:45.669398Z"},"content_sha256":"3c2adee112fc16850e41755eee9b6a064a9e4d898f4b28fe8e1581985a1344ec","schema_version":"1.0","event_id":"sha256:3c2adee112fc16850e41755eee9b6a064a9e4d898f4b28fe8e1581985a1344ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG/bundle.json","state_url":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QLXW7DYTYXURAK55MGNVLPMFUG/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":"2026-07-09T01:03:45Z","links":{"resolver":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG","bundle":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG/bundle.json","state":"https://pith.science/pith/QLXW7DYTYXURAK55MGNVLPMFUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QLXW7DYTYXURAK55MGNVLPMFUG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QLXW7DYTYXURAK55MGNVLPMFUG","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":"8284dabc2ff770d3f51c10e0ddf16710878bf9f57c314285cd2e24d5a6456938","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:46:03Z","title_canon_sha256":"31891d7b96d31392bb89651cb997f29ff19701cb4960a72c54de3d871143ee4e"},"schema_version":"1.0","source":{"id":"2305.15386","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15386","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15386v2","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15386","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"pith_short_12","alias_value":"QLXW7DYTYXUR","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"pith_short_16","alias_value":"QLXW7DYTYXURAK55","created_at":"2026-07-05T06:37:04Z"},{"alias_kind":"pith_short_8","alias_value":"QLXW7DYT","created_at":"2026-07-05T06:37:04Z"}],"graph_snapshots":[{"event_id":"sha256:3c2adee112fc16850e41755eee9b6a064a9e4d898f4b28fe8e1581985a1344ec","target":"graph","created_at":"2026-07-05T06:37:04Z","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/2305.15386/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Improving ASR systems is necessary to make new LLM-based use-cases accessible to people across the globe. In this paper, we focus on Indian languages, and make the case that diverse benchmarks are required to evaluate and improve ASR systems for Indian languages. To address this, we collate Vistaar as a set of 59 benchmarks across various language and domain combinations, on which we evaluate 3 publicly available ASR systems and 2 commercial systems. We also train IndicWhisper models by fine-tuning the Whisper models on publicly available training datasets across 12 Indian languages totalling ","authors_text":"Abhigyan Raman, Kaushal Santosh Bhogale, Mitesh M. Khapra, Pratyush Kumar, Sai Sundaresan, Tahir Javed","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:46:03Z","title":"Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15386","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":"sha256:5ed1017fc9b1aba014283e18e3fe9c866621c188537bebda278ba378d47f2286","target":"record","created_at":"2026-07-05T06:37:04Z","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":"8284dabc2ff770d3f51c10e0ddf16710878bf9f57c314285cd2e24d5a6456938","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:46:03Z","title_canon_sha256":"31891d7b96d31392bb89651cb997f29ff19701cb4960a72c54de3d871143ee4e"},"schema_version":"1.0","source":{"id":"2305.15386","kind":"arxiv","version":2}},"canonical_sha256":"82ef6f8f13c5e9102bbd619b55bd85a1a80a21339772225f2c0a8c7b93b2ffb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82ef6f8f13c5e9102bbd619b55bd85a1a80a21339772225f2c0a8c7b93b2ffb5","first_computed_at":"2026-07-05T06:37:04.163767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:37:04.163767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oBkIrtKkDuxIZVnxRF2DcX3Z5/+3PK21VsAplwfLMMCH1Q3RK0VSOxyhjdGMBrNNEnG6+VQ9GKCtJAg+X5kYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:37:04.164275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15386","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ed1017fc9b1aba014283e18e3fe9c866621c188537bebda278ba378d47f2286","sha256:3c2adee112fc16850e41755eee9b6a064a9e4d898f4b28fe8e1581985a1344ec"],"state_sha256":"0157f4e4306fb1efc11c7ac32ac5e608c8f6aea298c76ada37a6921a021b5def"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"242hRMXEINy0X6uZII8FsxaNjUkIpjEF1IT4H7fuztYdgdS7NxEVxCpc6SzIvg44r6FLPgW4Sp/JDJiXnPKXBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T01:03:45.671572Z","bundle_sha256":"c4d5f80f0428aea9179894dd79adcc08a9ba1d8bdd4bb79c919fee32994f66e8"}}