{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SJCU6OKIUCCCNLG4PELFMNEILU","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":"c615a3bf9550b0a2163200bf30c5d511237c9df3d606b0ad724c6221ad459e9e","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T06:48:11Z","title_canon_sha256":"6af1dbbd8d73cfb3db1a78397f0f8558b1321fdeacaa66bf24e55f3adee24b17"},"schema_version":"1.0","source":{"id":"2406.18108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18108","created_at":"2026-07-05T08:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18108v1","created_at":"2026-07-05T08:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18108","created_at":"2026-07-05T08:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"SJCU6OKIUCCC","created_at":"2026-07-05T08:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"SJCU6OKIUCCCNLG4","created_at":"2026-07-05T08:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"SJCU6OKI","created_at":"2026-07-05T08:36:55Z"}],"graph_snapshots":[{"event_id":"sha256:0d8a5a2d637c650e65538ba7de01e86c87952e63dde677aeb033419ffecc32d4","target":"graph","created_at":"2026-07-05T08:36:55Z","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/2406.18108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"ASR models are commonly trained with the cross-entropy criterion to increase the probability of a target token sequence. While optimizing the probability of all tokens in the target sequence is sensible, one may want to de-emphasize tokens that reflect transcription errors. In this work, we propose a novel token-weighted RNN-T criterion that augments the RNN-T objective with token-specific weights. The new objective is used for mitigating accuracy loss from transcriptions errors in the training data, which naturally appear in two settings: pseudo-labeling and human annotation errors. Experimen","authors_text":"Gil Keren, Ozlem Kalinli, Wei Zhou","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T06:48:11Z","title":"Token-Weighted RNN-T for Learning from Flawed Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18108","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:cea869922295668cc5de0a6ce91a0132cf4c16893b5f7589f23c090b2ac867c6","target":"record","created_at":"2026-07-05T08:36:55Z","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":"c615a3bf9550b0a2163200bf30c5d511237c9df3d606b0ad724c6221ad459e9e","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T06:48:11Z","title_canon_sha256":"6af1dbbd8d73cfb3db1a78397f0f8558b1321fdeacaa66bf24e55f3adee24b17"},"schema_version":"1.0","source":{"id":"2406.18108","kind":"arxiv","version":1}},"canonical_sha256":"92454f3948a08426acdc79165634885d16acb0130eed9882e62b720d70647099","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92454f3948a08426acdc79165634885d16acb0130eed9882e62b720d70647099","first_computed_at":"2026-07-05T08:36:55.348037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:55.348037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wx1HnWTeITPxniGUaFVz8GXX3Ya9kRGPVOpukbGoFiIjThSzr2XfQ4YDbBEl9hj/tMENzyHR60bDfWE8Sr56CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:55.348476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cea869922295668cc5de0a6ce91a0132cf4c16893b5f7589f23c090b2ac867c6","sha256:0d8a5a2d637c650e65538ba7de01e86c87952e63dde677aeb033419ffecc32d4"],"state_sha256":"7c6b5a800c7cf32dfedec5e2464829e7fb386dedb4378b62e6f0de447a0c1ba1"}