{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OS76LODZWDDPURYEDKXTWYTO22","short_pith_number":"pith:OS76LODZ","schema_version":"1.0","canonical_sha256":"74bfe5b879b0c6fa47041aaf3b626ed6b8aa18463e972f3875015df8181e7e3a","source":{"kind":"arxiv","id":"2606.20714","version":1},"attestation_state":"computed","paper":{"title":"A Generalized Formalism of Auto-Regressive Decoding for Speech Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Julia Gachot, Marie S. Bauer, Philipp Allgeuer, Stefan Wermter","submitted_at":"2026-06-16T13:31:39Z","abstract_excerpt":"In speech processing, most state-of-the-art sequence prediction models rely on auto-regressive (AR) strategies to generate output sequences based on the raw predictions of the model. Despite their crucial role in the inference process, a comprehensive overview of AR strategies as a unified field is lacking, due largely to implicit and multiple definitions of next-token decoding. This context complicates the choice, comparison, and evaluation of strategies, while creating inconsistencies in the characterization of approaches as auto-regressive or not. We begin by setting explicit inclusion crit"},"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":"2606.20714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-16T13:31:39Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"980e805ea5cf59b2498d203b29f96c238d1eba99bde60636b686704c5938a860","abstract_canon_sha256":"e0d4d2f653ca93a374d5c37fc17c6a9b07d71f5f4f589f7c69acec7284377274"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:54.490509Z","signature_b64":"r+b/H1+BYWPU5jHaVXK9LzFWX7M5MWxh3gRme2hWMwGp7dqfNTW3cQRUuIEtjZt09jv8W9hidt1CdmLsl35bCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74bfe5b879b0c6fa47041aaf3b626ed6b8aa18463e972f3875015df8181e7e3a","last_reissued_at":"2026-06-23T00:11:54.490105Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:54.490105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Generalized Formalism of Auto-Regressive Decoding for Speech Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Julia Gachot, Marie S. Bauer, Philipp Allgeuer, Stefan Wermter","submitted_at":"2026-06-16T13:31:39Z","abstract_excerpt":"In speech processing, most state-of-the-art sequence prediction models rely on auto-regressive (AR) strategies to generate output sequences based on the raw predictions of the model. Despite their crucial role in the inference process, a comprehensive overview of AR strategies as a unified field is lacking, due largely to implicit and multiple definitions of next-token decoding. This context complicates the choice, comparison, and evaluation of strategies, while creating inconsistencies in the characterization of approaches as auto-regressive or not. We begin by setting explicit inclusion crit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20714","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/2606.20714/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":"2606.20714","created_at":"2026-06-23T00:11:54.490164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20714v1","created_at":"2026-06-23T00:11:54.490164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20714","created_at":"2026-06-23T00:11:54.490164+00:00"},{"alias_kind":"pith_short_12","alias_value":"OS76LODZWDDP","created_at":"2026-06-23T00:11:54.490164+00:00"},{"alias_kind":"pith_short_16","alias_value":"OS76LODZWDDPURYE","created_at":"2026-06-23T00:11:54.490164+00:00"},{"alias_kind":"pith_short_8","alias_value":"OS76LODZ","created_at":"2026-06-23T00:11:54.490164+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/OS76LODZWDDPURYEDKXTWYTO22","json":"https://pith.science/pith/OS76LODZWDDPURYEDKXTWYTO22.json","graph_json":"https://pith.science/api/pith-number/OS76LODZWDDPURYEDKXTWYTO22/graph.json","events_json":"https://pith.science/api/pith-number/OS76LODZWDDPURYEDKXTWYTO22/events.json","paper":"https://pith.science/paper/OS76LODZ"},"agent_actions":{"view_html":"https://pith.science/pith/OS76LODZWDDPURYEDKXTWYTO22","download_json":"https://pith.science/pith/OS76LODZWDDPURYEDKXTWYTO22.json","view_paper":"https://pith.science/paper/OS76LODZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20714&json=true","fetch_graph":"https://pith.science/api/pith-number/OS76LODZWDDPURYEDKXTWYTO22/graph.json","fetch_events":"https://pith.science/api/pith-number/OS76LODZWDDPURYEDKXTWYTO22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OS76LODZWDDPURYEDKXTWYTO22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OS76LODZWDDPURYEDKXTWYTO22/action/storage_attestation","attest_author":"https://pith.science/pith/OS76LODZWDDPURYEDKXTWYTO22/action/author_attestation","sign_citation":"https://pith.science/pith/OS76LODZWDDPURYEDKXTWYTO22/action/citation_signature","submit_replication":"https://pith.science/pith/OS76LODZWDDPURYEDKXTWYTO22/action/replication_record"}},"created_at":"2026-06-23T00:11:54.490164+00:00","updated_at":"2026-06-23T00:11:54.490164+00:00"}