{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:665U3VY5CS6ZLDMM4R6OI56I6W","short_pith_number":"pith:665U3VY5","canonical_record":{"source":{"id":"2203.16512","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T17:50:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1fdadcc8e2e3ae9b9b2e2b451b43feae8b39171b9814cf5d58f1b5ef8e3992a0","abstract_canon_sha256":"6b04add8297e79f74ef2a627cdc239f4192dde068cf5d4719eabb90c38679f1a"},"schema_version":"1.0"},"canonical_sha256":"f7bb4dd71d14bd958d8ce47ce477c8f586199c7648137218c74c41f583caa229","source":{"kind":"arxiv","id":"2203.16512","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16512","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16512v2","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16512","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"665U3VY5CS6Z","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"665U3VY5CS6ZLDMM","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"665U3VY5","created_at":"2026-07-05T04:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:665U3VY5CS6ZLDMM4R6OI56I6W","target":"record","payload":{"canonical_record":{"source":{"id":"2203.16512","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T17:50:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1fdadcc8e2e3ae9b9b2e2b451b43feae8b39171b9814cf5d58f1b5ef8e3992a0","abstract_canon_sha256":"6b04add8297e79f74ef2a627cdc239f4192dde068cf5d4719eabb90c38679f1a"},"schema_version":"1.0"},"canonical_sha256":"f7bb4dd71d14bd958d8ce47ce477c8f586199c7648137218c74c41f583caa229","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:59.892289Z","signature_b64":"ZsCvapR2MdDf19Ta/rQ0Gwf5XUS4y7S0tPrtCR35ge/Eg2FNzkvRLFChcvaEHDr/VU6kR4duBQZMhJzB4aAzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7bb4dd71d14bd958d8ce47ce477c8f586199c7648137218c74c41f583caa229","last_reissued_at":"2026-07-05T04:31:59.891872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:59.891872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.16512","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":"2026-07-05T04:31:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mUE7MW1qNlD6P90bC4/WHP86tx18pUwTszp4+AVsxudD6JnXebNUTIU2WKa6PTRuspaDHRdVU7fjbV/q2NnXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:27:00.142318Z"},"content_sha256":"5409ce1929f4cf839917bfd171751e2ff4a637087947c1e0da998fd205ea7e9b","schema_version":"1.0","event_id":"sha256:5409ce1929f4cf839917bfd171751e2ff4a637087947c1e0da998fd205ea7e9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:665U3VY5CS6ZLDMM4R6OI56I6W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vakyansh: ASR Toolkit for Low Resource Indic languages","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":"2022-03-30T17:50:18Z","abstract_excerpt":"We present Vakyansh, an end to end toolkit for Speech Recognition in Indic languages. India is home to almost 121 languages and around 125 crore speakers. Yet most of the languages are low resource in terms of data and pretrained models. Through Vakyansh, we introduce automatic data pipelines for data creation, model training, model evaluation and deployment. We create 14,000 hours of speech data in 23 Indic languages and train wav2vec 2.0 based pretrained models. These pretrained models are then finetuned to create state of the art speech recognition models for 18 Indic languages which are fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16512","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/2203.16512/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":"0lyyy3QzUIezQEMmG9iQbQB6ochKzfSTOjD4RrcGoK+EnF2gQPgXtu/NQATerZj9jtktMFd1F9PdIx0otVipCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:27:00.142691Z"},"content_sha256":"de62a31c8dd0122e900d9889b428fd4810c289ee5040bd916c4bef0742954232","schema_version":"1.0","event_id":"sha256:de62a31c8dd0122e900d9889b428fd4810c289ee5040bd916c4bef0742954232"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/665U3VY5CS6ZLDMM4R6OI56I6W/bundle.json","state_url":"https://pith.science/pith/665U3VY5CS6ZLDMM4R6OI56I6W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/665U3VY5CS6ZLDMM4R6OI56I6W/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":"2026-08-03T18:27:00Z","links":{"resolver":"https://pith.science/pith/665U3VY5CS6ZLDMM4R6OI56I6W","bundle":"https://pith.science/pith/665U3VY5CS6ZLDMM4R6OI56I6W/bundle.json","state":"https://pith.science/pith/665U3VY5CS6ZLDMM4R6OI56I6W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/665U3VY5CS6ZLDMM4R6OI56I6W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:665U3VY5CS6ZLDMM4R6OI56I6W","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":"6b04add8297e79f74ef2a627cdc239f4192dde068cf5d4719eabb90c38679f1a","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T17:50:18Z","title_canon_sha256":"1fdadcc8e2e3ae9b9b2e2b451b43feae8b39171b9814cf5d58f1b5ef8e3992a0"},"schema_version":"1.0","source":{"id":"2203.16512","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16512","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16512v2","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16512","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"665U3VY5CS6Z","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"665U3VY5CS6ZLDMM","created_at":"2026-07-05T04:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"665U3VY5","created_at":"2026-07-05T04:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:de62a31c8dd0122e900d9889b428fd4810c289ee5040bd916c4bef0742954232","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/2203.16512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Vakyansh, an end to end toolkit for Speech Recognition in Indic languages. India is home to almost 121 languages and around 125 crore speakers. Yet most of the languages are low resource in terms of data and pretrained models. Through Vakyansh, we introduce automatic data pipelines for data creation, model training, model evaluation and deployment. We create 14,000 hours of speech data in 23 Indic languages and train wav2vec 2.0 based pretrained models. These pretrained models are then finetuned to create state of the art speech recognition models for 18 Indic languages which are fo","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":"2022-03-30T17:50:18Z","title":"Vakyansh: ASR Toolkit for Low Resource Indic languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16512","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":"sha256:5409ce1929f4cf839917bfd171751e2ff4a637087947c1e0da998fd205ea7e9b","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":"6b04add8297e79f74ef2a627cdc239f4192dde068cf5d4719eabb90c38679f1a","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T17:50:18Z","title_canon_sha256":"1fdadcc8e2e3ae9b9b2e2b451b43feae8b39171b9814cf5d58f1b5ef8e3992a0"},"schema_version":"1.0","source":{"id":"2203.16512","kind":"arxiv","version":2}},"canonical_sha256":"f7bb4dd71d14bd958d8ce47ce477c8f586199c7648137218c74c41f583caa229","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7bb4dd71d14bd958d8ce47ce477c8f586199c7648137218c74c41f583caa229","first_computed_at":"2026-07-05T04:31:59.891872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:31:59.891872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZsCvapR2MdDf19Ta/rQ0Gwf5XUS4y7S0tPrtCR35ge/Eg2FNzkvRLFChcvaEHDr/VU6kR4duBQZMhJzB4aAzBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:31:59.892289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16512","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5409ce1929f4cf839917bfd171751e2ff4a637087947c1e0da998fd205ea7e9b","sha256:de62a31c8dd0122e900d9889b428fd4810c289ee5040bd916c4bef0742954232"],"state_sha256":"ca14570fd51c3cf92b5b6b9d46c765a4a377a414aa6e0b37eb1009f818de6b2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsqVm+F+qH6Fr2EFNhjAx7AoH2PdzkpaBiQ6fZahVYDAOijfScleZGrcA5RRgsK7GoX4MinMNU1/BhHR0JCgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:27:00.145552Z","bundle_sha256":"3a5d20b7639b65405188a0b210e5e4cce8adae3d413ba33608d084f7609e985b"}}