{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3AGQ3LBDXIWKN3FGDO7YHG7CQG","short_pith_number":"pith:3AGQ3LBD","canonical_record":{"source":{"id":"2408.11440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T08:51:00Z","cross_cats_sorted":[],"title_canon_sha256":"985e12882e2ec9291994f940ae687567d4e4275ae10a910001406ef786a86f1e","abstract_canon_sha256":"45f35cb7c637e1b39217aa6bb32a344d9bc7eaa6ba42ac90bab757182071894b"},"schema_version":"1.0"},"canonical_sha256":"d80d0dac23ba2ca6eca61bbf839be281a38fe0bded031f90152866104caed766","source":{"kind":"arxiv","id":"2408.11440","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11440","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11440v1","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11440","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"3AGQ3LBDXIWK","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_16","alias_value":"3AGQ3LBDXIWKN3FG","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_8","alias_value":"3AGQ3LBD","created_at":"2026-07-05T08:57:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3AGQ3LBDXIWKN3FGDO7YHG7CQG","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T08:51:00Z","cross_cats_sorted":[],"title_canon_sha256":"985e12882e2ec9291994f940ae687567d4e4275ae10a910001406ef786a86f1e","abstract_canon_sha256":"45f35cb7c637e1b39217aa6bb32a344d9bc7eaa6ba42ac90bab757182071894b"},"schema_version":"1.0"},"canonical_sha256":"d80d0dac23ba2ca6eca61bbf839be281a38fe0bded031f90152866104caed766","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:44.187955Z","signature_b64":"ZcG0kipG7DtxXLln7BGu0DL7tYaL6zZ3bq0Wvn6t2x6i+e9zKCixHvVLX6V+aAZVUbr0qDc9zXhiy3QZfPb2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d80d0dac23ba2ca6eca61bbf839be281a38fe0bded031f90152866104caed766","last_reissued_at":"2026-07-05T08:57:44.187537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:44.187537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11440","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":"2026-07-05T08:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CmrZW0xS1dTJ4L7exNFeegkEzc0coIPEcG7d+kZ/L4CHdwHL6OOFdPHibJmLSz5bUrd8H90Fdr9m3niXgmzBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:37:08.275969Z"},"content_sha256":"ad7b75d934130ae5f91d994db253185bba129c516ac8e70a789901034bc43bab","schema_version":"1.0","event_id":"sha256:ad7b75d934130ae5f91d994db253185bba129c516ac8e70a789901034bc43bab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3AGQ3LBDXIWKN3FGDO7YHG7CQG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deovrat Mehendale, Eldho George, Janki Nawale, Kaushal Bhogale, Mitesh M. Khapra, Sakshi Joshi, Tahir Javed","submitted_at":"2024-08-21T08:51:00Z","abstract_excerpt":"Hindi, one of the most spoken language of India, exhibits a diverse array of accents due to its usage among individuals from diverse linguistic origins. To enable a robust evaluation of Hindi ASR systems on multiple accents, we create a benchmark, LAHAJA, which contains read and extempore speech on a diverse set of topics and use cases, with a total of 12.5 hours of Hindi audio, sourced from 132 speakers spanning 83 districts of India. We evaluate existing open-source and commercial models on LAHAJA and find their performance to be poor. We then train models using different datasets and find t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11440","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/2408.11440/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":"2026-07-05T08:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uPH6ey8sCR5eTTORG1Q4uzaEDtdwo70gbnhdQ+pToZ5uHayslSeoGFFdwthD/7mwIFK9K5IQwm+idH1/3AwdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:37:08.276679Z"},"content_sha256":"3e2983ba5060f195e8ed74c0a51ff9893af5f3a02884fd9d6852d505a95d3a6d","schema_version":"1.0","event_id":"sha256:3e2983ba5060f195e8ed74c0a51ff9893af5f3a02884fd9d6852d505a95d3a6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3AGQ3LBDXIWKN3FGDO7YHG7CQG/bundle.json","state_url":"https://pith.science/pith/3AGQ3LBDXIWKN3FGDO7YHG7CQG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3AGQ3LBDXIWKN3FGDO7YHG7CQG/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":"2026-08-18T09:37:08Z","links":{"resolver":"https://pith.science/pith/3AGQ3LBDXIWKN3FGDO7YHG7CQG","bundle":"https://pith.science/pith/3AGQ3LBDXIWKN3FGDO7YHG7CQG/bundle.json","state":"https://pith.science/pith/3AGQ3LBDXIWKN3FGDO7YHG7CQG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3AGQ3LBDXIWKN3FGDO7YHG7CQG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3AGQ3LBDXIWKN3FGDO7YHG7CQG","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":"45f35cb7c637e1b39217aa6bb32a344d9bc7eaa6ba42ac90bab757182071894b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T08:51:00Z","title_canon_sha256":"985e12882e2ec9291994f940ae687567d4e4275ae10a910001406ef786a86f1e"},"schema_version":"1.0","source":{"id":"2408.11440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11440","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11440v1","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11440","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"3AGQ3LBDXIWK","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_16","alias_value":"3AGQ3LBDXIWKN3FG","created_at":"2026-07-05T08:57:44Z"},{"alias_kind":"pith_short_8","alias_value":"3AGQ3LBD","created_at":"2026-07-05T08:57:44Z"}],"graph_snapshots":[{"event_id":"sha256:3e2983ba5060f195e8ed74c0a51ff9893af5f3a02884fd9d6852d505a95d3a6d","target":"graph","created_at":"2026-07-05T08:57:44Z","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/2408.11440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hindi, one of the most spoken language of India, exhibits a diverse array of accents due to its usage among individuals from diverse linguistic origins. To enable a robust evaluation of Hindi ASR systems on multiple accents, we create a benchmark, LAHAJA, which contains read and extempore speech on a diverse set of topics and use cases, with a total of 12.5 hours of Hindi audio, sourced from 132 speakers spanning 83 districts of India. We evaluate existing open-source and commercial models on LAHAJA and find their performance to be poor. We then train models using different datasets and find t","authors_text":"Deovrat Mehendale, Eldho George, Janki Nawale, Kaushal Bhogale, Mitesh M. Khapra, Sakshi Joshi, Tahir Javed","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T08:51:00Z","title":"LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11440","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:ad7b75d934130ae5f91d994db253185bba129c516ac8e70a789901034bc43bab","target":"record","created_at":"2026-07-05T08:57:44Z","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":"45f35cb7c637e1b39217aa6bb32a344d9bc7eaa6ba42ac90bab757182071894b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T08:51:00Z","title_canon_sha256":"985e12882e2ec9291994f940ae687567d4e4275ae10a910001406ef786a86f1e"},"schema_version":"1.0","source":{"id":"2408.11440","kind":"arxiv","version":1}},"canonical_sha256":"d80d0dac23ba2ca6eca61bbf839be281a38fe0bded031f90152866104caed766","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d80d0dac23ba2ca6eca61bbf839be281a38fe0bded031f90152866104caed766","first_computed_at":"2026-07-05T08:57:44.187537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:44.187537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZcG0kipG7DtxXLln7BGu0DL7tYaL6zZ3bq0Wvn6t2x6i+e9zKCixHvVLX6V+aAZVUbr0qDc9zXhiy3QZfPb2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:44.187955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad7b75d934130ae5f91d994db253185bba129c516ac8e70a789901034bc43bab","sha256:3e2983ba5060f195e8ed74c0a51ff9893af5f3a02884fd9d6852d505a95d3a6d"],"state_sha256":"cdfad39420d989875043df55b06781f14237cebae410c9f175eb31fa57fdb11e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewZ9o7040gOg0x5S6l/EPqL9dPPjfN3qQImW2USJx863qVy4UOuUqa3YXlxseXr3OG11SMr8F+VN4OaMDzFQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:37:08.283647Z","bundle_sha256":"4432dba8acf692ae146e62afcc11232a34136e60a4cbe93f5216c4b94b0c4dcb"}}