{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VJDDRG4QQHKAIU4J7XCFW4DBMI","short_pith_number":"pith:VJDDRG4Q","schema_version":"1.0","canonical_sha256":"aa46389b9081d4045389fdc45b7061621210f950e111f33c967127942e9e66b8","source":{"kind":"arxiv","id":"2606.23080","version":1},"attestation_state":"computed","paper":{"title":"AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bin Ma, Huadai Liu, Kaicheng Luo, Qian Chen, Wei Xue, Wen Wang, Xiangang Li","submitted_at":"2026-06-22T09:30:02Z","abstract_excerpt":"Unifying speech, sound, and music generation in one model is hindered by tradeoffs between fidelity, end-to-end training, in-context conditioning, and variable-length synthesis that no current paradigm fully resolves. To address this challenge, we present AudioCALM, a universal audio generation framework that extends autoregressive (AR) next-token prediction from discrete tokens to continuous audio latents: a thin flow-matching head replaces the softmax to predict rectified-flow velocities at each position, and a block-causal AR-Flow attention pattern produces arbitrary-length output. Joint tr"},"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":"2606.23080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T09:30:02Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a7b4ba98bd44104fc6575455e105a6fe023a75c8bd6d28fb0a0cd2a5cb8d0aca","abstract_canon_sha256":"7f23aeaefc5d68c2bfbad74073acb42b645582bbe5186337b06d9f1c4b534f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:09.298266Z","signature_b64":"/0hTQ8OVlGFEf5ynTLaUv3HBkiBAQj1EitmhAljIfSfesRgoM6hplWUFtKzWZN7QexkpJhTO1CWrwFsxU4PPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa46389b9081d4045389fdc45b7061621210f950e111f33c967127942e9e66b8","last_reissued_at":"2026-06-23T03:14:09.297855Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:09.297855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bin Ma, Huadai Liu, Kaicheng Luo, Qian Chen, Wei Xue, Wen Wang, Xiangang Li","submitted_at":"2026-06-22T09:30:02Z","abstract_excerpt":"Unifying speech, sound, and music generation in one model is hindered by tradeoffs between fidelity, end-to-end training, in-context conditioning, and variable-length synthesis that no current paradigm fully resolves. To address this challenge, we present AudioCALM, a universal audio generation framework that extends autoregressive (AR) next-token prediction from discrete tokens to continuous audio latents: a thin flow-matching head replaces the softmax to predict rectified-flow velocities at each position, and a block-causal AR-Flow attention pattern produces arbitrary-length output. Joint tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23080","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/2606.23080/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":"2606.23080","created_at":"2026-06-23T03:14:09.297915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23080v1","created_at":"2026-06-23T03:14:09.297915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23080","created_at":"2026-06-23T03:14:09.297915+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJDDRG4QQHKA","created_at":"2026-06-23T03:14:09.297915+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJDDRG4QQHKAIU4J","created_at":"2026-06-23T03:14:09.297915+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJDDRG4Q","created_at":"2026-06-23T03:14:09.297915+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/VJDDRG4QQHKAIU4J7XCFW4DBMI","json":"https://pith.science/pith/VJDDRG4QQHKAIU4J7XCFW4DBMI.json","graph_json":"https://pith.science/api/pith-number/VJDDRG4QQHKAIU4J7XCFW4DBMI/graph.json","events_json":"https://pith.science/api/pith-number/VJDDRG4QQHKAIU4J7XCFW4DBMI/events.json","paper":"https://pith.science/paper/VJDDRG4Q"},"agent_actions":{"view_html":"https://pith.science/pith/VJDDRG4QQHKAIU4J7XCFW4DBMI","download_json":"https://pith.science/pith/VJDDRG4QQHKAIU4J7XCFW4DBMI.json","view_paper":"https://pith.science/paper/VJDDRG4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23080&json=true","fetch_graph":"https://pith.science/api/pith-number/VJDDRG4QQHKAIU4J7XCFW4DBMI/graph.json","fetch_events":"https://pith.science/api/pith-number/VJDDRG4QQHKAIU4J7XCFW4DBMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJDDRG4QQHKAIU4J7XCFW4DBMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJDDRG4QQHKAIU4J7XCFW4DBMI/action/storage_attestation","attest_author":"https://pith.science/pith/VJDDRG4QQHKAIU4J7XCFW4DBMI/action/author_attestation","sign_citation":"https://pith.science/pith/VJDDRG4QQHKAIU4J7XCFW4DBMI/action/citation_signature","submit_replication":"https://pith.science/pith/VJDDRG4QQHKAIU4J7XCFW4DBMI/action/replication_record"}},"created_at":"2026-06-23T03:14:09.297915+00:00","updated_at":"2026-06-23T03:14:09.297915+00:00"}