{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IKSESUBIDDMYATANFFD6VPQ3JX","short_pith_number":"pith:IKSESUBI","schema_version":"1.0","canonical_sha256":"42a449502818d9804c0d2947eabe1b4dc58851d994809229037528b556559e1d","source":{"kind":"arxiv","id":"2605.29613","version":1},"attestation_state":"computed","paper":{"title":"Decoding Strategies for Diffusion-Based ASR: A Systematic Evaluation of Confidence-Based Thresholding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hyeongseop Rha, Jeong Hun Yeo, Minsu Kim, Yong Man Ro","submitted_at":"2026-05-28T08:48:56Z","abstract_excerpt":"While LLM-based Automatic Speech Recognition (ASR) achieves high accuracy, its speed is limited by sequential autoregressive decoding. Diffusion Language Models (DLMs) offer a parallel alternative, yet their decoding strategies remain under-explored in ASR contexts. This paper analyzes three decoding schemes for DLM-based ASR: fixed-number, static confidence threshold, and dynamic confidence threshold. We propose measuring round-wise accuracy using Negative Log-Likelihood-based uncertainty as a proxy for decoding progress. Our results show that both threshold-based strategies significantly out"},"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":"2605.29613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-28T08:48:56Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1cf3a1bc0cc23b65f4b6bb19c9fbb3840bc8ed7f58bac5db093fa8028cb70705","abstract_canon_sha256":"08f3c2458f5752f1550abb8740694e38c221f2b5c90405ba5f809872df595e5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:51.020381Z","signature_b64":"9BHfGztmklwLDw+0vuKR/FbD35cSM2scwOLYuyTjt2LRjA/UYgWmQlhphPz7JHepISycUUUsOFisCErIUdZcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42a449502818d9804c0d2947eabe1b4dc58851d994809229037528b556559e1d","last_reissued_at":"2026-05-29T01:05:51.019220Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:51.019220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoding Strategies for Diffusion-Based ASR: A Systematic Evaluation of Confidence-Based Thresholding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hyeongseop Rha, Jeong Hun Yeo, Minsu Kim, Yong Man Ro","submitted_at":"2026-05-28T08:48:56Z","abstract_excerpt":"While LLM-based Automatic Speech Recognition (ASR) achieves high accuracy, its speed is limited by sequential autoregressive decoding. Diffusion Language Models (DLMs) offer a parallel alternative, yet their decoding strategies remain under-explored in ASR contexts. This paper analyzes three decoding schemes for DLM-based ASR: fixed-number, static confidence threshold, and dynamic confidence threshold. We propose measuring round-wise accuracy using Negative Log-Likelihood-based uncertainty as a proxy for decoding progress. Our results show that both threshold-based strategies significantly out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29613","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/2605.29613/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":"2605.29613","created_at":"2026-05-29T01:05:51.019308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29613v1","created_at":"2026-05-29T01:05:51.019308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29613","created_at":"2026-05-29T01:05:51.019308+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKSESUBIDDMY","created_at":"2026-05-29T01:05:51.019308+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKSESUBIDDMYATAN","created_at":"2026-05-29T01:05:51.019308+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKSESUBI","created_at":"2026-05-29T01:05:51.019308+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/IKSESUBIDDMYATANFFD6VPQ3JX","json":"https://pith.science/pith/IKSESUBIDDMYATANFFD6VPQ3JX.json","graph_json":"https://pith.science/api/pith-number/IKSESUBIDDMYATANFFD6VPQ3JX/graph.json","events_json":"https://pith.science/api/pith-number/IKSESUBIDDMYATANFFD6VPQ3JX/events.json","paper":"https://pith.science/paper/IKSESUBI"},"agent_actions":{"view_html":"https://pith.science/pith/IKSESUBIDDMYATANFFD6VPQ3JX","download_json":"https://pith.science/pith/IKSESUBIDDMYATANFFD6VPQ3JX.json","view_paper":"https://pith.science/paper/IKSESUBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29613&json=true","fetch_graph":"https://pith.science/api/pith-number/IKSESUBIDDMYATANFFD6VPQ3JX/graph.json","fetch_events":"https://pith.science/api/pith-number/IKSESUBIDDMYATANFFD6VPQ3JX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKSESUBIDDMYATANFFD6VPQ3JX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKSESUBIDDMYATANFFD6VPQ3JX/action/storage_attestation","attest_author":"https://pith.science/pith/IKSESUBIDDMYATANFFD6VPQ3JX/action/author_attestation","sign_citation":"https://pith.science/pith/IKSESUBIDDMYATANFFD6VPQ3JX/action/citation_signature","submit_replication":"https://pith.science/pith/IKSESUBIDDMYATANFFD6VPQ3JX/action/replication_record"}},"created_at":"2026-05-29T01:05:51.019308+00:00","updated_at":"2026-05-29T01:05:51.019308+00:00"}