{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OY2RJFU4FKLSCL2XGLQW6HIS6S","short_pith_number":"pith:OY2RJFU4","canonical_record":{"source":{"id":"2608.06900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-07T07:35:00Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fd53903dc7dbbe4ff3eed4b678aeabe8d82b11f21beb54e0cee04b9ffe5c12d4","abstract_canon_sha256":"0bff159bbeb6f1b2badc251b3d4ebed7256fc32af43861b2d99b5f5f4a1e81e5"},"schema_version":"1.0"},"canonical_sha256":"763514969c2a97212f5732e16f1d12f4b585a94ca491321fcb24e503bdae73fa","source":{"kind":"arxiv","id":"2608.06900","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06900","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06900v1","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06900","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"OY2RJFU4FKLS","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"OY2RJFU4FKLSCL2X","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"OY2RJFU4","created_at":"2026-08-10T01:12:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OY2RJFU4FKLSCL2XGLQW6HIS6S","target":"record","payload":{"canonical_record":{"source":{"id":"2608.06900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-07T07:35:00Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fd53903dc7dbbe4ff3eed4b678aeabe8d82b11f21beb54e0cee04b9ffe5c12d4","abstract_canon_sha256":"0bff159bbeb6f1b2badc251b3d4ebed7256fc32af43861b2d99b5f5f4a1e81e5"},"schema_version":"1.0"},"canonical_sha256":"763514969c2a97212f5732e16f1d12f4b585a94ca491321fcb24e503bdae73fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:12:27.502086Z","signature_b64":"eXpwPyCNAq6MyeJDeOD0LiVFtxZWHEv5nQUSZyo3eAB95ZpHUS/u0YVqbWR7LtZog/gPObLASADx18/vyDHdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"763514969c2a97212f5732e16f1d12f4b585a94ca491321fcb24e503bdae73fa","last_reissued_at":"2026-08-10T01:12:27.499430Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:12:27.499430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.06900","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":"2026-08-10T01:12:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2QNeHLYIVm7cAgH4IeeuovXT5mrVEr7Vk3gQqiqv1vYeKvSvZgHcApaVjRy9Q8GPjlAWMcxyFUyDcsgTOXTUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:38:56.351506Z"},"content_sha256":"d7d4094a98430c1952b5db125cedbba0173f003f13a329cecbb102322d3c6f1c","schema_version":"1.0","event_id":"sha256:d7d4094a98430c1952b5db125cedbba0173f003f13a329cecbb102322d3c6f1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OY2RJFU4FKLSCL2XGLQW6HIS6S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMAG: A Multi-Control Mixed Audio Generation Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Zhang, Jiahao Mei, Mengyue Wu, Minghao Lv, Wen Wu, Xuenan Xu, Yixuan Li, Zihao Zheng","submitted_at":"2026-08-07T07:35:00Z","abstract_excerpt":"Recent audio generation systems have progressed from single-modality synthesis to generating complex acoustic scenes containing speech, music, and sound effects. Therefore, evaluating these models requires assessing multiple interacting capabilities, including semantic fidelity, speaker consistency, and temporal control, yet existing benchmarks focus on isolated domains or coarse-grained descriptions. To address this gap, we introduce the Multi-control Mixed Audio Generation (MMAG) benchmark. MMAG contains approximately 4,000 manually verified audio clips with rich annotations covering speech "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06900","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/2608.06900/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":"2026-08-10T01:12:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lMERORwzSLoD+dwJxsfy6oQX+DznsIOTl7jopqFQk8VUSt22Fhx9BJC2auArJs3YjC2y1i17GaAPhe3PmQk4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:38:56.352385Z"},"content_sha256":"fb9413a8cff621fbc8a7505469cd47e114ca9b9388c17f30f902e86a5d8dae1f","schema_version":"1.0","event_id":"sha256:fb9413a8cff621fbc8a7505469cd47e114ca9b9388c17f30f902e86a5d8dae1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OY2RJFU4FKLSCL2XGLQW6HIS6S/bundle.json","state_url":"https://pith.science/pith/OY2RJFU4FKLSCL2XGLQW6HIS6S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OY2RJFU4FKLSCL2XGLQW6HIS6S/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":"2026-08-18T16:38:56Z","links":{"resolver":"https://pith.science/pith/OY2RJFU4FKLSCL2XGLQW6HIS6S","bundle":"https://pith.science/pith/OY2RJFU4FKLSCL2XGLQW6HIS6S/bundle.json","state":"https://pith.science/pith/OY2RJFU4FKLSCL2XGLQW6HIS6S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OY2RJFU4FKLSCL2XGLQW6HIS6S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OY2RJFU4FKLSCL2XGLQW6HIS6S","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":"0bff159bbeb6f1b2badc251b3d4ebed7256fc32af43861b2d99b5f5f4a1e81e5","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-07T07:35:00Z","title_canon_sha256":"fd53903dc7dbbe4ff3eed4b678aeabe8d82b11f21beb54e0cee04b9ffe5c12d4"},"schema_version":"1.0","source":{"id":"2608.06900","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06900","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06900v1","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06900","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"OY2RJFU4FKLS","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"OY2RJFU4FKLSCL2X","created_at":"2026-08-10T01:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"OY2RJFU4","created_at":"2026-08-10T01:12:27Z"}],"graph_snapshots":[{"event_id":"sha256:fb9413a8cff621fbc8a7505469cd47e114ca9b9388c17f30f902e86a5d8dae1f","target":"graph","created_at":"2026-08-10T01:12:27Z","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/2608.06900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent audio generation systems have progressed from single-modality synthesis to generating complex acoustic scenes containing speech, music, and sound effects. Therefore, evaluating these models requires assessing multiple interacting capabilities, including semantic fidelity, speaker consistency, and temporal control, yet existing benchmarks focus on isolated domains or coarse-grained descriptions. To address this gap, we introduce the Multi-control Mixed Audio Generation (MMAG) benchmark. MMAG contains approximately 4,000 manually verified audio clips with rich annotations covering speech ","authors_text":"Chao Zhang, Jiahao Mei, Mengyue Wu, Minghao Lv, Wen Wu, Xuenan Xu, Yixuan Li, Zihao Zheng","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-07T07:35:00Z","title":"MMAG: A Multi-Control Mixed Audio Generation Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06900","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:d7d4094a98430c1952b5db125cedbba0173f003f13a329cecbb102322d3c6f1c","target":"record","created_at":"2026-08-10T01:12:27Z","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":"0bff159bbeb6f1b2badc251b3d4ebed7256fc32af43861b2d99b5f5f4a1e81e5","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-07T07:35:00Z","title_canon_sha256":"fd53903dc7dbbe4ff3eed4b678aeabe8d82b11f21beb54e0cee04b9ffe5c12d4"},"schema_version":"1.0","source":{"id":"2608.06900","kind":"arxiv","version":1}},"canonical_sha256":"763514969c2a97212f5732e16f1d12f4b585a94ca491321fcb24e503bdae73fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"763514969c2a97212f5732e16f1d12f4b585a94ca491321fcb24e503bdae73fa","first_computed_at":"2026-08-10T01:12:27.499430Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:12:27.499430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eXpwPyCNAq6MyeJDeOD0LiVFtxZWHEv5nQUSZyo3eAB95ZpHUS/u0YVqbWR7LtZog/gPObLASADx18/vyDHdCw==","signature_status":"signed_v1","signed_at":"2026-08-10T01:12:27.502086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06900","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7d4094a98430c1952b5db125cedbba0173f003f13a329cecbb102322d3c6f1c","sha256:fb9413a8cff621fbc8a7505469cd47e114ca9b9388c17f30f902e86a5d8dae1f"],"state_sha256":"220e2fd5ff08f5b68e0a662e289e5b878e93a6a3708b80da67dc476238574ab7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d1UJp+v6gsDuq97w4C+tpEjLEqZ/e5RtMgS/bBs+MK2RrVgtlyGk8eiSCAhGzUk5/J2kXMI7NXoxpTyHvZ/mAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:38:56.359662Z","bundle_sha256":"75237fea9ec15589035a9e84a860d42aa53653e2112896cbfb7e149b455df114"}}