{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NZSZSOPCPH5KRYUJFG2UJVC4AA","short_pith_number":"pith:NZSZSOPC","schema_version":"1.0","canonical_sha256":"6e659939e279faa8e28929b544d45c000906e84475f83d6566d7ab46b90d19f0","source":{"kind":"arxiv","id":"2210.07677","version":1},"attestation_state":"computed","paper":{"title":"TransFusion: Transcribing Speech with Multinomial Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Herman Kamper, Kevin Eloff, Matthew Baas","submitted_at":"2022-10-14T10:01:43Z","abstract_excerpt":"Diffusion models have shown exceptional scaling properties in the image synthesis domain, and initial attempts have shown similar benefits for applying diffusion to unconditional text synthesis. Denoising diffusion models attempt to iteratively refine a sampled noise signal until it resembles a coherent signal (such as an image or written sentence). In this work we aim to see whether the benefits of diffusion models can also be realized for speech recognition. To this end, we propose a new way to perform speech recognition using a diffusion model conditioned on pretrained speech features. Spec"},"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":"2210.07677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-14T10:01:43Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ce68306724577c0613613c78dc044e914ac9b60b1e4592ec7efa78dd70ae9f6c","abstract_canon_sha256":"57870e9b70abc28357c8a5959c6f877277deae7cee081248a5089afcc22a26e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:40.008406Z","signature_b64":"WJ9XGLJAdIGNOIMxQ+oDgt5kDTAzHqHenOky/KsXV1uMdeqHMlIJuXVhSoPddcnW/R7q13B6TOYcw1qfoqo0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e659939e279faa8e28929b544d45c000906e84475f83d6566d7ab46b90d19f0","last_reissued_at":"2026-07-05T05:06:40.008053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:40.008053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransFusion: Transcribing Speech with Multinomial Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Herman Kamper, Kevin Eloff, Matthew Baas","submitted_at":"2022-10-14T10:01:43Z","abstract_excerpt":"Diffusion models have shown exceptional scaling properties in the image synthesis domain, and initial attempts have shown similar benefits for applying diffusion to unconditional text synthesis. Denoising diffusion models attempt to iteratively refine a sampled noise signal until it resembles a coherent signal (such as an image or written sentence). In this work we aim to see whether the benefits of diffusion models can also be realized for speech recognition. To this end, we propose a new way to perform speech recognition using a diffusion model conditioned on pretrained speech features. Spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07677","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/2210.07677/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":"2210.07677","created_at":"2026-07-05T05:06:40.008108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07677v1","created_at":"2026-07-05T05:06:40.008108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07677","created_at":"2026-07-05T05:06:40.008108+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZSZSOPCPH5K","created_at":"2026-07-05T05:06:40.008108+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZSZSOPCPH5KRYUJ","created_at":"2026-07-05T05:06:40.008108+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZSZSOPC","created_at":"2026-07-05T05:06:40.008108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10368","citing_title":"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZSZSOPCPH5KRYUJFG2UJVC4AA","json":"https://pith.science/pith/NZSZSOPCPH5KRYUJFG2UJVC4AA.json","graph_json":"https://pith.science/api/pith-number/NZSZSOPCPH5KRYUJFG2UJVC4AA/graph.json","events_json":"https://pith.science/api/pith-number/NZSZSOPCPH5KRYUJFG2UJVC4AA/events.json","paper":"https://pith.science/paper/NZSZSOPC"},"agent_actions":{"view_html":"https://pith.science/pith/NZSZSOPCPH5KRYUJFG2UJVC4AA","download_json":"https://pith.science/pith/NZSZSOPCPH5KRYUJFG2UJVC4AA.json","view_paper":"https://pith.science/paper/NZSZSOPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07677&json=true","fetch_graph":"https://pith.science/api/pith-number/NZSZSOPCPH5KRYUJFG2UJVC4AA/graph.json","fetch_events":"https://pith.science/api/pith-number/NZSZSOPCPH5KRYUJFG2UJVC4AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZSZSOPCPH5KRYUJFG2UJVC4AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZSZSOPCPH5KRYUJFG2UJVC4AA/action/storage_attestation","attest_author":"https://pith.science/pith/NZSZSOPCPH5KRYUJFG2UJVC4AA/action/author_attestation","sign_citation":"https://pith.science/pith/NZSZSOPCPH5KRYUJFG2UJVC4AA/action/citation_signature","submit_replication":"https://pith.science/pith/NZSZSOPCPH5KRYUJFG2UJVC4AA/action/replication_record"}},"created_at":"2026-07-05T05:06:40.008108+00:00","updated_at":"2026-07-05T05:06:40.008108+00:00"}