{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UMFKTNZTLFWUREPRT6TQXWSOZT","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":"2b4b7795a47e7fa658aaba5829c96d404691d5ce7cce175803fa0ef7b792c5ee","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T17:59:40Z","title_canon_sha256":"9ce94ec5dd521de0c93a5a80de2650e063ef221485df1654582f86cefdee8b29"},"schema_version":"1.0","source":{"id":"2603.11042","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.11042","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"arxiv_version","alias_value":"2603.11042v2","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11042","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"pith_short_12","alias_value":"UMFKTNZTLFWU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UMFKTNZTLFWUREPR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UMFKTNZT","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:62eab2ebe1d1384d71b9cef9ddbaa0484dd600fbd22e0168fd836ece2d51c3bd","target":"graph","created_at":"2026-05-17T23:39:15Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our results validate that temporal alignment through within-modality features is not only effective for video-to-music generation but also leads to better performance than paired cross-modal supervision."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that event curves computed from intra-modal similarity using pretrained encoders provide comparable representations across modalities that enable direct substitution at inference without cross-modal training."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"V2M-Zero achieves state-of-the-art video-to-music generation with improved temporal synchronization and semantic alignment by substituting video event curves into a fine-tuned text-to-music model without any paired training data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Event curves from intra-modal similarities enable zero-pair training for time-aligned video-to-music generation."}],"snapshot_sha256":"631dd9d8567114de0a7cf6dfb1396539d5e207347054698406d1cccea66d4aad"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Generating music that temporally aligns with video events is challenging for existing text-to-music models, which lack fine-grained temporal control. We introduce V2M-ZERO, a video-to-music generation approach that generates time-aligned music with disentangled time synchronization and semantic control (e.g., genre, mood) from video while requiring zero video-music pairs at training time. Our method is motivated by a key observation: temporal synchronization requires matching when and how much change occurs, not what changes. While musical and visual events differ semantically, they exhibit sh","authors_text":"Aniruddha Mahapatra, Gedas Bertasius, Jonah Casebeer, Long Mai, Nicholas J. Bryan, Yan-Bo Lin","cross_cats":["cs.AI","cs.LG","cs.MM","cs.SD"],"headline":"Event curves from intra-modal similarities enable zero-pair training for time-aligned video-to-music generation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T17:59:40Z","title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation"},"references":{"count":111,"internal_anchors":0,"resolved_work":111,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"MusicLM: Generating music from text.arXiv Preprint, 2023","work_id":"2215fdec-d5ee-48e4-9cb0-ca5e6104f20b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"V-JEPA 2: Self-supervised video models enable understanding, prediction and planning.arXiv Preprint, 2025","work_id":"9319b4a4-f8e2-4c38-a4ca-731350281b54","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Yatong Bai, Jonah Casebeer, Somayeh Sojoudi, and Nicholas J. Bryan. DRAGON: Distributional rewards optimize diffusion generative models.TMLR,","work_id":"68f8c904-2857-4323-8f15-d5591a0652a2","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"AudioLM: a language modeling approach to audio generation","work_id":"b3eb82aa-6361-4788-98e1-566428a7f6aa","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Re-bottleneck: Latent re-structuring for neural audio autoencoders","work_id":"3ad4f3bd-241d-4346-b0a6-56a238439438","year":2025}],"snapshot_sha256":"3625d217df5d9c16ea8df15d8d698ffbe34cbf6447666061623d45de0a656f6b"},"source":{"id":"2603.11042","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T13:15:18.525988Z","id":"a84a8d18-b87e-4bbe-8251-34e5a67ac0a1","model_set":{"reader":"grok-4.3"},"one_line_summary":"V2M-Zero achieves state-of-the-art video-to-music generation with improved temporal synchronization and semantic alignment by substituting video event curves into a fine-tuned text-to-music model without any paired training data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Event curves from intra-modal similarities enable zero-pair training for time-aligned video-to-music generation.","strongest_claim":"Our results validate that temporal alignment through within-modality features is not only effective for video-to-music generation but also leads to better performance than paired cross-modal supervision.","weakest_assumption":"The assumption that event curves computed from intra-modal similarity using pretrained encoders provide comparable representations across modalities that enable direct substitution at inference without cross-modal training."}},"verdict_id":"a84a8d18-b87e-4bbe-8251-34e5a67ac0a1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5e9865fdec6084378ea3742e08a244b8a5ab003f964324e61c375a12d84b905c","target":"record","created_at":"2026-05-17T23:39:15Z","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":"2b4b7795a47e7fa658aaba5829c96d404691d5ce7cce175803fa0ef7b792c5ee","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T17:59:40Z","title_canon_sha256":"9ce94ec5dd521de0c93a5a80de2650e063ef221485df1654582f86cefdee8b29"},"schema_version":"1.0","source":{"id":"2603.11042","kind":"arxiv","version":2}},"canonical_sha256":"a30aa9b733596d4891f19fa70bda4ecce5224aa17e49642a73193ec5af8092b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a30aa9b733596d4891f19fa70bda4ecce5224aa17e49642a73193ec5af8092b3","first_computed_at":"2026-05-17T23:39:15.821418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:15.821418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R/96yWsYnAIAqGCHlWWZmA9SyX3fbAlCW4n0JrqPff5TwtUeNPogVzxovCMeYHxDr6RF+9nCY4GlLCTe0OeJDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:15.822193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.11042","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e9865fdec6084378ea3742e08a244b8a5ab003f964324e61c375a12d84b905c","sha256:62eab2ebe1d1384d71b9cef9ddbaa0484dd600fbd22e0168fd836ece2d51c3bd"],"state_sha256":"4ef2da646d78b84708157711d8a9238bf930398578826857cf2508b057c971dc"}