{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NRDKAQYIFQ42PZR35HUVQCFGIC","short_pith_number":"pith:NRDKAQYI","schema_version":"1.0","canonical_sha256":"6c46a043082c39a7e63be9e95808a6408f3c106c71b9381e7674d28eefb8dffa","source":{"kind":"arxiv","id":"2606.28732","version":1},"attestation_state":"computed","paper":{"title":"CTC-Seeded Token Edit Refinement for Non-Autoregressive Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Wanting Huang, Weiran Wang","submitted_at":"2026-06-27T04:48:09Z","abstract_excerpt":"Non-autoregressive automatic speech recognition (ASR) enables parallel decoding, but many refinement-based methods begin from random, fully masked, or fixed-length token sequences, requiring multiple iterations to reconstruct the complete transcript. We instead formulate ASR decoding as a variable-length edit refinement of a greedy connectionist temporal classification (CTC) hypothesis. An acoustic-conditioned Edit Flow decoder operates directly on the collapsed CTC hypothesis, predicting insertion, deletion, and substitution operations in parallel. The Edit Flow decoder is jointly trained wit"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.28732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-27T04:48:09Z","cross_cats_sorted":[],"title_canon_sha256":"550913f5d6d0a489c7c31eada6b8848e562efcb952874ead346ad4c48d97a364","abstract_canon_sha256":"9f28f87bd89f485afca21e645a0ba238f577d0b74203b27afc8d8910a7195eb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:49.683918Z","signature_b64":"mSkdaBjKDaoZQYycYZbc5Jp3/Ds2nwqnbtwczTgU50wO7KiS41B6OpRpJZiqHuRfHQjB0Ut4HH69gzOdA2qKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c46a043082c39a7e63be9e95808a6408f3c106c71b9381e7674d28eefb8dffa","last_reissued_at":"2026-06-30T01:16:49.683387Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:49.683387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CTC-Seeded Token Edit Refinement for Non-Autoregressive Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Wanting Huang, Weiran Wang","submitted_at":"2026-06-27T04:48:09Z","abstract_excerpt":"Non-autoregressive automatic speech recognition (ASR) enables parallel decoding, but many refinement-based methods begin from random, fully masked, or fixed-length token sequences, requiring multiple iterations to reconstruct the complete transcript. We instead formulate ASR decoding as a variable-length edit refinement of a greedy connectionist temporal classification (CTC) hypothesis. An acoustic-conditioned Edit Flow decoder operates directly on the collapsed CTC hypothesis, predicting insertion, deletion, and substitution operations in parallel. The Edit Flow decoder is jointly trained wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28732","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/2606.28732/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.28732","created_at":"2026-06-30T01:16:49.683471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28732v1","created_at":"2026-06-30T01:16:49.683471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28732","created_at":"2026-06-30T01:16:49.683471+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRDKAQYIFQ42","created_at":"2026-06-30T01:16:49.683471+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRDKAQYIFQ42PZR3","created_at":"2026-06-30T01:16:49.683471+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRDKAQYI","created_at":"2026-06-30T01:16:49.683471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NRDKAQYIFQ42PZR35HUVQCFGIC","json":"https://pith.science/pith/NRDKAQYIFQ42PZR35HUVQCFGIC.json","graph_json":"https://pith.science/api/pith-number/NRDKAQYIFQ42PZR35HUVQCFGIC/graph.json","events_json":"https://pith.science/api/pith-number/NRDKAQYIFQ42PZR35HUVQCFGIC/events.json","paper":"https://pith.science/paper/NRDKAQYI"},"agent_actions":{"view_html":"https://pith.science/pith/NRDKAQYIFQ42PZR35HUVQCFGIC","download_json":"https://pith.science/pith/NRDKAQYIFQ42PZR35HUVQCFGIC.json","view_paper":"https://pith.science/paper/NRDKAQYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28732&json=true","fetch_graph":"https://pith.science/api/pith-number/NRDKAQYIFQ42PZR35HUVQCFGIC/graph.json","fetch_events":"https://pith.science/api/pith-number/NRDKAQYIFQ42PZR35HUVQCFGIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRDKAQYIFQ42PZR35HUVQCFGIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRDKAQYIFQ42PZR35HUVQCFGIC/action/storage_attestation","attest_author":"https://pith.science/pith/NRDKAQYIFQ42PZR35HUVQCFGIC/action/author_attestation","sign_citation":"https://pith.science/pith/NRDKAQYIFQ42PZR35HUVQCFGIC/action/citation_signature","submit_replication":"https://pith.science/pith/NRDKAQYIFQ42PZR35HUVQCFGIC/action/replication_record"}},"created_at":"2026-06-30T01:16:49.683471+00:00","updated_at":"2026-06-30T01:16:49.683471+00:00"}