{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Y2ZK2JQVFQIRMAFLF2AQSHX4SO","short_pith_number":"pith:Y2ZK2JQV","canonical_record":{"source":{"id":"2606.31259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T07:36:10Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"bfed3bf423af42196fb2bfd72de3e5ff39e42649c967b9da7d6c259bc37779e7","abstract_canon_sha256":"fa22713f5e97c8b608cc9100e699bfa12a03f91ec354e1013ed13916809420d1"},"schema_version":"1.0"},"canonical_sha256":"c6b2ad26152c111600ab2e81091efc938b9fede03dc4572cf4d9b19bcb9a14ba","source":{"kind":"arxiv","id":"2606.31259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31259","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31259v1","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31259","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"Y2ZK2JQVFQIR","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"Y2ZK2JQVFQIRMAFL","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"Y2ZK2JQV","created_at":"2026-07-01T01:17:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Y2ZK2JQVFQIRMAFLF2AQSHX4SO","target":"record","payload":{"canonical_record":{"source":{"id":"2606.31259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T07:36:10Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"bfed3bf423af42196fb2bfd72de3e5ff39e42649c967b9da7d6c259bc37779e7","abstract_canon_sha256":"fa22713f5e97c8b608cc9100e699bfa12a03f91ec354e1013ed13916809420d1"},"schema_version":"1.0"},"canonical_sha256":"c6b2ad26152c111600ab2e81091efc938b9fede03dc4572cf4d9b19bcb9a14ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:57.375489Z","signature_b64":"Gp3LfB9ItlEKpRBE9s4wuMzoXMgDyWHQLjwY0OMkB6G7irrKsIgDqIF0v4Z10cpi8ZctGP+9HuAXoKYioVIVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6b2ad26152c111600ab2e81091efc938b9fede03dc4572cf4d9b19bcb9a14ba","last_reissued_at":"2026-07-01T01:17:57.375076Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:57.375076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.31259","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r5eAEPPSpRxX7KjKomkt3tSt2aaXHX4bP3CM5eZOkqPCzQG2rcuGsASg3BCtIRp3PmVnOHz3VDiX6bpWbgqICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T13:01:57.940412Z"},"content_sha256":"4b5fd68569e1adaa91d4df1942104297d2bb195fec2af15ee257737179253b3b","schema_version":"1.0","event_id":"sha256:4b5fd68569e1adaa91d4df1942104297d2bb195fec2af15ee257737179253b3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Y2ZK2JQVFQIRMAFLF2AQSHX4SO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Binh Mai, Cong Tran, Hung Dinh, Tran Quoc Bao Le","submitted_at":"2026-06-30T07:36:10Z","abstract_excerpt":"Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step denoising. Existing one-step approaches alleviate this issue but still rely on paired text--audio data during distillation. To address these limitations, we propose SwiftAudio, a one-step TTA framework that performs audio-free distillation from a pretrained diffusion teacher using only text captions. Specifically, we adapt Variational Score Distillation (VSD) to the audio domain and introduce a temporal smoothness regularization objective to encoura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31259","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/2606.31259/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cV7ki/n9e/mZCTTZSHM1l/QtfFgNGytzsbYOmIx4YuE/+stP7sna0KINqwa6JMs5FtWlAdPKjBwNLuSk2dF+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T13:01:57.940801Z"},"content_sha256":"011e5be9b07cd912ee2c5431878b12301ac77dc97fc0d53d52d8b32344df56a1","schema_version":"1.0","event_id":"sha256:011e5be9b07cd912ee2c5431878b12301ac77dc97fc0d53d52d8b32344df56a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2ZK2JQVFQIRMAFLF2AQSHX4SO/bundle.json","state_url":"https://pith.science/pith/Y2ZK2JQVFQIRMAFLF2AQSHX4SO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2ZK2JQVFQIRMAFLF2AQSHX4SO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-24T13:01:57Z","links":{"resolver":"https://pith.science/pith/Y2ZK2JQVFQIRMAFLF2AQSHX4SO","bundle":"https://pith.science/pith/Y2ZK2JQVFQIRMAFLF2AQSHX4SO/bundle.json","state":"https://pith.science/pith/Y2ZK2JQVFQIRMAFLF2AQSHX4SO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2ZK2JQVFQIRMAFLF2AQSHX4SO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y2ZK2JQVFQIRMAFLF2AQSHX4SO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fa22713f5e97c8b608cc9100e699bfa12a03f91ec354e1013ed13916809420d1","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T07:36:10Z","title_canon_sha256":"bfed3bf423af42196fb2bfd72de3e5ff39e42649c967b9da7d6c259bc37779e7"},"schema_version":"1.0","source":{"id":"2606.31259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31259","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31259v1","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31259","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"Y2ZK2JQVFQIR","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"Y2ZK2JQVFQIRMAFL","created_at":"2026-07-01T01:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"Y2ZK2JQV","created_at":"2026-07-01T01:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:011e5be9b07cd912ee2c5431878b12301ac77dc97fc0d53d52d8b32344df56a1","target":"graph","created_at":"2026-07-01T01:17:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.31259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step denoising. Existing one-step approaches alleviate this issue but still rely on paired text--audio data during distillation. To address these limitations, we propose SwiftAudio, a one-step TTA framework that performs audio-free distillation from a pretrained diffusion teacher using only text captions. Specifically, we adapt Variational Score Distillation (VSD) to the audio domain and introduce a temporal smoothness regularization objective to encoura","authors_text":"Binh Mai, Cong Tran, Hung Dinh, Tran Quoc Bao Le","cross_cats":["cs.AI","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T07:36:10Z","title":"SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31259","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b5fd68569e1adaa91d4df1942104297d2bb195fec2af15ee257737179253b3b","target":"record","created_at":"2026-07-01T01:17:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fa22713f5e97c8b608cc9100e699bfa12a03f91ec354e1013ed13916809420d1","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T07:36:10Z","title_canon_sha256":"bfed3bf423af42196fb2bfd72de3e5ff39e42649c967b9da7d6c259bc37779e7"},"schema_version":"1.0","source":{"id":"2606.31259","kind":"arxiv","version":1}},"canonical_sha256":"c6b2ad26152c111600ab2e81091efc938b9fede03dc4572cf4d9b19bcb9a14ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6b2ad26152c111600ab2e81091efc938b9fede03dc4572cf4d9b19bcb9a14ba","first_computed_at":"2026-07-01T01:17:57.375076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:57.375076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gp3LfB9ItlEKpRBE9s4wuMzoXMgDyWHQLjwY0OMkB6G7irrKsIgDqIF0v4Z10cpi8ZctGP+9HuAXoKYioVIVBw==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:57.375489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b5fd68569e1adaa91d4df1942104297d2bb195fec2af15ee257737179253b3b","sha256:011e5be9b07cd912ee2c5431878b12301ac77dc97fc0d53d52d8b32344df56a1"],"state_sha256":"df8882aac495f77c7c9f25e9132eafcf8bdb20c3084754ddbd1b86c72d5c1e6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Y0iWiEVXISVkPUhHBicU3woXWD0xT9TvP2FxWjLjW0UbNdE0hDdFSA0Vg13W4ER/r1wEC243LpS6lXyjeHADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T13:01:57.943034Z","bundle_sha256":"642a1b81478089d53396853aedc7654559356bdd63a81a35a84635fd2e65f46c"}}