{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QEZEF4QE2WIF7SZ7AE6ZTFJ7YJ","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":"06df57536c0fb4885d1b43917162ef4dff842fe5c14b38462d06f52a01fdc59b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-26T13:37:45Z","title_canon_sha256":"9b58758d382a1c1b7ce327406a772605fbc40f5b56ab3099c8524eabdae2d162"},"schema_version":"1.0","source":{"id":"2208.12666","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12666","created_at":"2026-07-05T04:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12666v1","created_at":"2026-07-05T04:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12666","created_at":"2026-07-05T04:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"QEZEF4QE2WIF","created_at":"2026-07-05T04:51:48Z"},{"alias_kind":"pith_short_16","alias_value":"QEZEF4QE2WIF7SZ7","created_at":"2026-07-05T04:51:48Z"},{"alias_kind":"pith_short_8","alias_value":"QEZEF4QE","created_at":"2026-07-05T04:51:48Z"}],"graph_snapshots":[{"event_id":"sha256:fa3c285d323df91258a2fe00b4a61fc2d9736404ed3d505ebcf2c856e0cf805f","target":"graph","created_at":"2026-07-05T04:51:48Z","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/2208.12666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end (E2E) models have become the default choice for state-of-the-art speech recognition systems. Such models are trained on large amounts of labelled data, which are often not available for low-resource languages. Techniques such as self-supervised learning and transfer learning hold promise, but have not yet been effective in training accurate models. On the other hand, collecting labelled datasets on a diverse set of domains and speakers is very expensive. In this work, we demonstrate an inexpensive and effective alternative to these approaches by ``mining'' text and audio pairs for I","authors_text":"Abhigyan Raman, Anoop Kunchukuttan, Kaushal Santosh Bhogale, Mitesh M. Khapra, Pratyush Kumar, Sumanth Doddapaneni, Tahir Javed","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-26T13:37:45Z","title":"Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12666","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:e0f20f921fd5e1f3db695d1020eea740fbfb94c2bc4c8e90a8598039f21b0601","target":"record","created_at":"2026-07-05T04:51:48Z","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":"06df57536c0fb4885d1b43917162ef4dff842fe5c14b38462d06f52a01fdc59b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-26T13:37:45Z","title_canon_sha256":"9b58758d382a1c1b7ce327406a772605fbc40f5b56ab3099c8524eabdae2d162"},"schema_version":"1.0","source":{"id":"2208.12666","kind":"arxiv","version":1}},"canonical_sha256":"813242f204d5905fcb3f013d99953fc2610c718db1abdb867e108a51516c6d1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"813242f204d5905fcb3f013d99953fc2610c718db1abdb867e108a51516c6d1c","first_computed_at":"2026-07-05T04:51:48.481897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:48.481897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PqfjJQIgHmbi+z8xcGOAMpXLijWTMOo4kC6Bg75fSEjz2O4+7q8/dP8svUSVZ9dAwl6iOHKNVz+5DLQ7tmtzDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:48.482380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.12666","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0f20f921fd5e1f3db695d1020eea740fbfb94c2bc4c8e90a8598039f21b0601","sha256:fa3c285d323df91258a2fe00b4a61fc2d9736404ed3d505ebcf2c856e0cf805f"],"state_sha256":"49c16da086d198f0429236add718e46697369408c65e26b9f938b0458d6875cb"}