{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4DZXKYCDCZSYF7LYKLU27JYP4I","short_pith_number":"pith:4DZXKYCD","schema_version":"1.0","canonical_sha256":"e0f3756043166582fd7852e9afa70fe23c2c83d42f2906e0760394faa7950ea4","source":{"kind":"arxiv","id":"2505.22053","version":2},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.22053","created_at":"2026-07-05T11:48:26.376919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22053v2","created_at":"2026-07-05T11:48:26.376919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22053","created_at":"2026-07-05T11:48:26.376919+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DZXKYCDCZSY","created_at":"2026-07-05T11:48:26.376919+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DZXKYCDCZSYF7LY","created_at":"2026-07-05T11:48:26.376919+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DZXKYCD","created_at":"2026-07-05T11:48:26.376919+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/4DZXKYCDCZSYF7LYKLU27JYP4I","json":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I.json","graph_json":"https://pith.science/api/pith-number/4DZXKYCDCZSYF7LYKLU27JYP4I/graph.json","events_json":"https://pith.science/api/pith-number/4DZXKYCDCZSYF7LYKLU27JYP4I/events.json","paper":"https://pith.science/paper/4DZXKYCD"},"agent_actions":{"view_html":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I","download_json":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I.json","view_paper":"https://pith.science/paper/4DZXKYCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22053&json=true","fetch_graph":"https://pith.science/api/pith-number/4DZXKYCDCZSYF7LYKLU27JYP4I/graph.json","fetch_events":"https://pith.science/api/pith-number/4DZXKYCDCZSYF7LYKLU27JYP4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/action/storage_attestation","attest_author":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/action/author_attestation","sign_citation":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/action/citation_signature","submit_replication":"https://pith.science/pith/4DZXKYCDCZSYF7LYKLU27JYP4I/action/replication_record"}},"created_at":"2026-07-05T11:48:26.376919+00:00","updated_at":"2026-07-05T11:48:26.376919+00:00"}