{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7UNVWU3BJUCHBLTTGL67VKNEJP","short_pith_number":"pith:7UNVWU3B","schema_version":"1.0","canonical_sha256":"fd1b5b53614d0470ae7332fdfaa9a44bd0c35329c883a0f0b88dac4cd0247814","source":{"kind":"arxiv","id":"2607.13013","version":1},"attestation_state":"computed","paper":{"title":"Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.AI","authors_text":"Abhinav Kumar Singh, Harsha Vardhan Khurdula, Vineet Agarwal, Yoeven D Khemlani","submitted_at":"2026-07-14T17:53:22Z","abstract_excerpt":"Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a small number of denoising steps. We train an audio-native interface for DiffusionGemma, a 26B mixture-of-experts model that generates text by uniform, random-token discrete diffusion rather than the absorbing-mask scheme common to recent diffusion language models. A frozen Whisper encoder supplies acoustic features, a lightweight projector maps them into the model embe"},"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":"2607.13013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T17:53:22Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"2643fbd2193d8719a61ed4f40ce1a9fc9474d812489af944287abc258e5a6017","abstract_canon_sha256":"a753b44f8b8762f931df4faed0ded334daa8a0b444dd0e1ac4dd02d70274969f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:22:31.293912Z","signature_b64":"FT5MCvxvemXhEPv+9WycAghot6dVgv8s/wgZs8gsPsGAsJ8qczOleINGWTZ2HU0SQppn5QH3O7JYIbgrDG64Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd1b5b53614d0470ae7332fdfaa9a44bd0c35329c883a0f0b88dac4cd0247814","last_reissued_at":"2026-07-15T01:22:31.293103Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:22:31.293103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.AI","authors_text":"Abhinav Kumar Singh, Harsha Vardhan Khurdula, Vineet Agarwal, Yoeven D Khemlani","submitted_at":"2026-07-14T17:53:22Z","abstract_excerpt":"Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a small number of denoising steps. We train an audio-native interface for DiffusionGemma, a 26B mixture-of-experts model that generates text by uniform, random-token discrete diffusion rather than the absorbing-mask scheme common to recent diffusion language models. A frozen Whisper encoder supplies acoustic features, a lightweight projector maps them into the model embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13013","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/2607.13013/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":"2607.13013","created_at":"2026-07-15T01:22:31.293535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13013v1","created_at":"2026-07-15T01:22:31.293535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13013","created_at":"2026-07-15T01:22:31.293535+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UNVWU3BJUCH","created_at":"2026-07-15T01:22:31.293535+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UNVWU3BJUCHBLTT","created_at":"2026-07-15T01:22:31.293535+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UNVWU3B","created_at":"2026-07-15T01:22:31.293535+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/7UNVWU3BJUCHBLTTGL67VKNEJP","json":"https://pith.science/pith/7UNVWU3BJUCHBLTTGL67VKNEJP.json","graph_json":"https://pith.science/api/pith-number/7UNVWU3BJUCHBLTTGL67VKNEJP/graph.json","events_json":"https://pith.science/api/pith-number/7UNVWU3BJUCHBLTTGL67VKNEJP/events.json","paper":"https://pith.science/paper/7UNVWU3B"},"agent_actions":{"view_html":"https://pith.science/pith/7UNVWU3BJUCHBLTTGL67VKNEJP","download_json":"https://pith.science/pith/7UNVWU3BJUCHBLTTGL67VKNEJP.json","view_paper":"https://pith.science/paper/7UNVWU3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13013&json=true","fetch_graph":"https://pith.science/api/pith-number/7UNVWU3BJUCHBLTTGL67VKNEJP/graph.json","fetch_events":"https://pith.science/api/pith-number/7UNVWU3BJUCHBLTTGL67VKNEJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UNVWU3BJUCHBLTTGL67VKNEJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UNVWU3BJUCHBLTTGL67VKNEJP/action/storage_attestation","attest_author":"https://pith.science/pith/7UNVWU3BJUCHBLTTGL67VKNEJP/action/author_attestation","sign_citation":"https://pith.science/pith/7UNVWU3BJUCHBLTTGL67VKNEJP/action/citation_signature","submit_replication":"https://pith.science/pith/7UNVWU3BJUCHBLTTGL67VKNEJP/action/replication_record"}},"created_at":"2026-07-15T01:22:31.293535+00:00","updated_at":"2026-07-15T01:22:31.293535+00:00"}