{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4DZXKYCDCZSYF7LYKLU27JYP4I","short_pith_number":"pith:4DZXKYCD","canonical_record":{"source":{"id":"2505.22053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:23:53Z","cross_cats_sorted":["cs.MA","cs.MM","eess.AS"],"title_canon_sha256":"bb2d19e082e8df8f56b390d412d4abf4d5ac4f4605b1591e5191abb603878384","abstract_canon_sha256":"cee09050b21d7d7d01a867d883f8b24c17f38c8843b452ba155ad39e80dfe1c5"},"schema_version":"1.0"},"canonical_sha256":"e0f3756043166582fd7852e9afa70fe23c2c83d42f2906e0760394faa7950ea4","source":{"kind":"arxiv","id":"2505.22053","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22053","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22053v2","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22053","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"4DZXKYCDCZSY","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_16","alias_value":"4DZXKYCDCZSYF7LY","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_8","alias_value":"4DZXKYCD","created_at":"2026-07-05T11:48:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4DZXKYCDCZSYF7LYKLU27JYP4I","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:23:53Z","cross_cats_sorted":["cs.MA","cs.MM","eess.AS"],"title_canon_sha256":"bb2d19e082e8df8f56b390d412d4abf4d5ac4f4605b1591e5191abb603878384","abstract_canon_sha256":"cee09050b21d7d7d01a867d883f8b24c17f38c8843b452ba155ad39e80dfe1c5"},"schema_version":"1.0"},"canonical_sha256":"e0f3756043166582fd7852e9afa70fe23c2c83d42f2906e0760394faa7950ea4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:26.377383Z","signature_b64":"F8gKUyicZw6F5DHVay+HxDbZ322NEJNXlPfCKdmOMXumBCYPatF67WS+aCsfFkKK2+mAf2dFPycHnX8vvd5GBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0f3756043166582fd7852e9afa70fe23c2c83d42f2906e0760394faa7950ea4","last_reissued_at":"2026-07-05T11:48:26.376849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:26.376849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22053","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:48:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tAVQ+aOpaQu/8MOYUAFsq0LrmHS+/r1OEm4Ni1B3xtp7PJUapuQ+lWsnOCK7QEAzgpGOgJiZqTB39CfYjXQoDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:06:19.529920Z"},"content_sha256":"155dd98bce2b139de44510b6cf8d118801667650d48f72c5e090f539d24d8bbf","schema_version":"1.0","event_id":"sha256:155dd98bce2b139de44510b6cf8d118801667650d48f72c5e090f539d24d8bbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4DZXKYCDCZSYF7LYKLU27JYP4I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guangzhi Lei, Jinting Wang, Li Liu, Shan Yang, Yan Rong","submitted_at":"2025-05-28T07:23:53Z","abstract_excerpt":"Multimodality-to-Multiaudio (MM2MA) generation faces significant challenges in synthesizing diverse and contextually aligned audio types (e.g., sound effects, speech, music, and songs) from multimodal inputs (e.g., video, text, images), owing to the scarcity of high-quality paired datasets and the lack of robust multi-task learning frameworks. Recently, multi-agent system shows great potential in tackling the above issues. However, directly applying it to MM2MA task presents three critical challenges: (1) inadequate fine-grained understanding of multimodal inputs (especially for video), (2) th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22053","kind":"arxiv","version":2},"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/2505.22053/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":"2026-07-05T11:48:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZ/ko85VQK/gCS422WX4w+YHeTnmnDBmQJ3dg3SXMe5HIOxyOX/CHMBsMr8hynZvII9N/ArlbylGVFAXJkFUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:06:19.530309Z"},"content_sha256":"176fc98f649ad374159413f19521d8fa02512e3adfc2f857a047e4fa5134cf2e","schema_version":"1.0","event_id":"sha256:176fc98f649ad374159413f19521d8fa02512e3adfc2f857a047e4fa5134cf2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/bundle.json","state_url":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/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":"2026-07-08T16:06:19Z","links":{"resolver":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I","bundle":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/bundle.json","state":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4DZXKYCDCZSYF7LYKLU27JYP4I","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":"cee09050b21d7d7d01a867d883f8b24c17f38c8843b452ba155ad39e80dfe1c5","cross_cats_sorted":["cs.MA","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:23:53Z","title_canon_sha256":"bb2d19e082e8df8f56b390d412d4abf4d5ac4f4605b1591e5191abb603878384"},"schema_version":"1.0","source":{"id":"2505.22053","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22053","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22053v2","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22053","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"4DZXKYCDCZSY","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_16","alias_value":"4DZXKYCDCZSYF7LY","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_8","alias_value":"4DZXKYCD","created_at":"2026-07-05T11:48:26Z"}],"graph_snapshots":[{"event_id":"sha256:176fc98f649ad374159413f19521d8fa02512e3adfc2f857a047e4fa5134cf2e","target":"graph","created_at":"2026-07-05T11:48:26Z","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/2505.22053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodality-to-Multiaudio (MM2MA) generation faces significant challenges in synthesizing diverse and contextually aligned audio types (e.g., sound effects, speech, music, and songs) from multimodal inputs (e.g., video, text, images), owing to the scarcity of high-quality paired datasets and the lack of robust multi-task learning frameworks. Recently, multi-agent system shows great potential in tackling the above issues. However, directly applying it to MM2MA task presents three critical challenges: (1) inadequate fine-grained understanding of multimodal inputs (especially for video), (2) th","authors_text":"Guangzhi Lei, Jinting Wang, Li Liu, Shan Yang, Yan Rong","cross_cats":["cs.MA","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:23:53Z","title":"AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22053","kind":"arxiv","version":2},"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":"sha256:155dd98bce2b139de44510b6cf8d118801667650d48f72c5e090f539d24d8bbf","target":"record","created_at":"2026-07-05T11:48:26Z","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":"cee09050b21d7d7d01a867d883f8b24c17f38c8843b452ba155ad39e80dfe1c5","cross_cats_sorted":["cs.MA","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T07:23:53Z","title_canon_sha256":"bb2d19e082e8df8f56b390d412d4abf4d5ac4f4605b1591e5191abb603878384"},"schema_version":"1.0","source":{"id":"2505.22053","kind":"arxiv","version":2}},"canonical_sha256":"e0f3756043166582fd7852e9afa70fe23c2c83d42f2906e0760394faa7950ea4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0f3756043166582fd7852e9afa70fe23c2c83d42f2906e0760394faa7950ea4","first_computed_at":"2026-07-05T11:48:26.376849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:26.376849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F8gKUyicZw6F5DHVay+HxDbZ322NEJNXlPfCKdmOMXumBCYPatF67WS+aCsfFkKK2+mAf2dFPycHnX8vvd5GBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:26.377383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22053","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:155dd98bce2b139de44510b6cf8d118801667650d48f72c5e090f539d24d8bbf","sha256:176fc98f649ad374159413f19521d8fa02512e3adfc2f857a047e4fa5134cf2e"],"state_sha256":"4f2f2a719753c92ab257984210c3773e7401f841c2445e9cf339383e81da478b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uEP6m6n0Z7ATXVzNMpPJTwH/qnEn6vfsI2dv0sX5DJJcEkqMy0KsyaFCe7ReSeeKngzIn84YfUC/J0WWuYs1DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T16:06:19.532423Z","bundle_sha256":"1e6744540ad5683ec72d245e3ed98a5def76be7e974c35ecb5a4537beb0ac982"}}