{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FWAHBW3JFXN5EEYFVXPENKWFJ7","short_pith_number":"pith:FWAHBW3J","canonical_record":{"source":{"id":"2606.12555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-10T18:06:27Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"3da7c0a56e8f32a4cb2321468904c9b1a2ca0e90e08dc53082b150de4ee69e56","abstract_canon_sha256":"a366d6915f6949b5654b7231d73aa2f3d2888fce66dfd6f172c844d7ffe1266a"},"schema_version":"1.0"},"canonical_sha256":"2d8070db692ddbd21305adde46aac54fe1c20fcae0fb7af161ab4ebe5ffcb9be","source":{"kind":"arxiv","id":"2606.12555","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12555","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12555v1","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12555","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"pith_short_12","alias_value":"FWAHBW3JFXN5","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"pith_short_16","alias_value":"FWAHBW3JFXN5EEYF","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"pith_short_8","alias_value":"FWAHBW3J","created_at":"2026-06-12T00:07:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FWAHBW3JFXN5EEYFVXPENKWFJ7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.12555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-10T18:06:27Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"3da7c0a56e8f32a4cb2321468904c9b1a2ca0e90e08dc53082b150de4ee69e56","abstract_canon_sha256":"a366d6915f6949b5654b7231d73aa2f3d2888fce66dfd6f172c844d7ffe1266a"},"schema_version":"1.0"},"canonical_sha256":"2d8070db692ddbd21305adde46aac54fe1c20fcae0fb7af161ab4ebe5ffcb9be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T00:07:54.556246Z","signature_b64":"7Vs9qunNf5+0Cm1nhBms3D37vhOD0SJAn8v0Ffh9uv4ZpMgPMHTxS6xzgUx9DdO8nxcms/mKwsc8NjYW/mxaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d8070db692ddbd21305adde46aac54fe1c20fcae0fb7af161ab4ebe5ffcb9be","last_reissued_at":"2026-06-12T00:07:54.555817Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T00:07:54.555817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.12555","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":"2026-06-12T00:07:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KmX3BemS4TgIFmC+RR3TABtiPrtYxYkNMZw5JKqACFK+aF15ys4pBY5eauNB7h6lv+7ZLMxof/iS2MLxzccgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T00:19:38.264244Z"},"content_sha256":"b717d5adcd8fac82d9d8f9dde720f8e3826f67404773a020ec95aa0bf5a8e3e5","schema_version":"1.0","event_id":"sha256:b717d5adcd8fac82d9d8f9dde720f8e3826f67404773a020ec95aa0bf5a8e3e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FWAHBW3JFXN5EEYFVXPENKWFJ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.SD","authors_text":"Lei Ke, Liumeng Xue, Qifeng Chen, Ruibin Yuan, Weijia Chen, Wei Xue, Xu Tan, Yike Guo, Yujiu Yang, Zeyue Tian, Zhaoyang Liu","submitted_at":"2026-06-10T18:06:27Z","abstract_excerpt":"Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework, 2) large-scale, high-quality training data, and 3) the prohibitive inference cost of multi-step diffusion sampling. As such, we propose AudioX-Turbo, a unified and efficient framework for anything-to-audio generation that integrates varied multimodal conditions (i.e., text, video, and audio signals) in this work. AudioX-Turbo follows a teacher-student paradigm. The teacher AudioX-Base is built on a Multimodal Diffus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12555","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/2606.12555/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":"2026-06-12T00:07:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vRvINJRuspqqissNj72MSE6yM4fbqEjnypYfvzeV+LPWF/3eAnoM0V4UUQ867KJWuJUEXeDV4XCe2ifL0X96Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T00:19:38.264641Z"},"content_sha256":"754f25aa5357de1e183e5bd002d9dffa594b32042661f062fb0d7d5e5d1b3519","schema_version":"1.0","event_id":"sha256:754f25aa5357de1e183e5bd002d9dffa594b32042661f062fb0d7d5e5d1b3519"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWAHBW3JFXN5EEYFVXPENKWFJ7/bundle.json","state_url":"https://pith.science/pith/FWAHBW3JFXN5EEYFVXPENKWFJ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWAHBW3JFXN5EEYFVXPENKWFJ7/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":"2026-07-03T00:19:38Z","links":{"resolver":"https://pith.science/pith/FWAHBW3JFXN5EEYFVXPENKWFJ7","bundle":"https://pith.science/pith/FWAHBW3JFXN5EEYFVXPENKWFJ7/bundle.json","state":"https://pith.science/pith/FWAHBW3JFXN5EEYFVXPENKWFJ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWAHBW3JFXN5EEYFVXPENKWFJ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FWAHBW3JFXN5EEYFVXPENKWFJ7","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":"a366d6915f6949b5654b7231d73aa2f3d2888fce66dfd6f172c844d7ffe1266a","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-10T18:06:27Z","title_canon_sha256":"3da7c0a56e8f32a4cb2321468904c9b1a2ca0e90e08dc53082b150de4ee69e56"},"schema_version":"1.0","source":{"id":"2606.12555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12555","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12555v1","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12555","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"pith_short_12","alias_value":"FWAHBW3JFXN5","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"pith_short_16","alias_value":"FWAHBW3JFXN5EEYF","created_at":"2026-06-12T00:07:54Z"},{"alias_kind":"pith_short_8","alias_value":"FWAHBW3J","created_at":"2026-06-12T00:07:54Z"}],"graph_snapshots":[{"event_id":"sha256:754f25aa5357de1e183e5bd002d9dffa594b32042661f062fb0d7d5e5d1b3519","target":"graph","created_at":"2026-06-12T00:07:54Z","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/2606.12555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework, 2) large-scale, high-quality training data, and 3) the prohibitive inference cost of multi-step diffusion sampling. As such, we propose AudioX-Turbo, a unified and efficient framework for anything-to-audio generation that integrates varied multimodal conditions (i.e., text, video, and audio signals) in this work. AudioX-Turbo follows a teacher-student paradigm. The teacher AudioX-Base is built on a Multimodal Diffus","authors_text":"Lei Ke, Liumeng Xue, Qifeng Chen, Ruibin Yuan, Weijia Chen, Wei Xue, Xu Tan, Yike Guo, Yujiu Yang, Zeyue Tian, Zhaoyang Liu","cross_cats":["cs.CV","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-10T18:06:27Z","title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12555","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:b717d5adcd8fac82d9d8f9dde720f8e3826f67404773a020ec95aa0bf5a8e3e5","target":"record","created_at":"2026-06-12T00:07:54Z","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":"a366d6915f6949b5654b7231d73aa2f3d2888fce66dfd6f172c844d7ffe1266a","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-10T18:06:27Z","title_canon_sha256":"3da7c0a56e8f32a4cb2321468904c9b1a2ca0e90e08dc53082b150de4ee69e56"},"schema_version":"1.0","source":{"id":"2606.12555","kind":"arxiv","version":1}},"canonical_sha256":"2d8070db692ddbd21305adde46aac54fe1c20fcae0fb7af161ab4ebe5ffcb9be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d8070db692ddbd21305adde46aac54fe1c20fcae0fb7af161ab4ebe5ffcb9be","first_computed_at":"2026-06-12T00:07:54.555817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T00:07:54.555817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Vs9qunNf5+0Cm1nhBms3D37vhOD0SJAn8v0Ffh9uv4ZpMgPMHTxS6xzgUx9DdO8nxcms/mKwsc8NjYW/mxaCA==","signature_status":"signed_v1","signed_at":"2026-06-12T00:07:54.556246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b717d5adcd8fac82d9d8f9dde720f8e3826f67404773a020ec95aa0bf5a8e3e5","sha256:754f25aa5357de1e183e5bd002d9dffa594b32042661f062fb0d7d5e5d1b3519"],"state_sha256":"5213afd0004923a46dcb7037912874b7f255e2f632c1241e79b69ba2b622a50c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+ZEEnmy9KYfXSLHoFs0rFQmQoZH2DN9PLQ786AI/GxTGdnI2lO9c90wei0P9r8TCYKZ/h9cg+1ikGJaMNrQAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T00:19:38.266792Z","bundle_sha256":"6e46a9108634a37860b217b5c50d97c086b0ec68e9c5a70466bf43f023d688fc"}}