{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5XCQ3HD46KMAFEDEFLLHWM6AZR","short_pith_number":"pith:5XCQ3HD4","canonical_record":{"source":{"id":"2501.09972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-17T06:30:11Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"15c9d56ca15ab7e6bfe472885859957e9544ab01e21c83b7b8c71663e9f7b915","abstract_canon_sha256":"6c9392abce6d56c671e331ea606cb30de129ec040e7bead34ce3b0397e381ba2"},"schema_version":"1.0"},"canonical_sha256":"edc50d9c7cf2980290642ad67b33c0cc41bed392e87b2355ebc526b2f529f6d6","source":{"kind":"arxiv","id":"2501.09972","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09972","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09972v1","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09972","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"5XCQ3HD46KMA","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"5XCQ3HD46KMAFEDE","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"5XCQ3HD4","created_at":"2026-07-05T10:50:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5XCQ3HD46KMAFEDEFLLHWM6AZR","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-17T06:30:11Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"15c9d56ca15ab7e6bfe472885859957e9544ab01e21c83b7b8c71663e9f7b915","abstract_canon_sha256":"6c9392abce6d56c671e331ea606cb30de129ec040e7bead34ce3b0397e381ba2"},"schema_version":"1.0"},"canonical_sha256":"edc50d9c7cf2980290642ad67b33c0cc41bed392e87b2355ebc526b2f529f6d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:46.673943Z","signature_b64":"BxL4ML/znaxWY7J+5ArnmPoF5Iq97GWLc7uSqEMcLtePcUYQiotoi8a01vltyqmAi6xGh1CQFnB9gpxMp2/VCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edc50d9c7cf2980290642ad67b33c0cc41bed392e87b2355ebc526b2f529f6d6","last_reissued_at":"2026-07-05T10:50:46.673444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:46.673444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09972","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":"2026-07-05T10:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KPyiS27RqjbZKD6HvfaQEoKbTCU8+q18hljmAAktLVkzlsAlaVkir5nOSXmWVWA1qRjgL22K2PpC65q022tQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:38:37.010229Z"},"content_sha256":"da4a08b6e8875999ba81f149ac829c75ac10c112dc8399f7aa2c88783118de2b","schema_version":"1.0","event_id":"sha256:da4a08b6e8875999ba81f149ac829c75ac10c112dc8399f7aa2c88783118de2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5XCQ3HD46KMAFEDEFLLHWM6AZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GVMGen: A General Video-to-Music Generation Model with Hierarchical Attentions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Heda Zuo, Junxian Wu, Lingyun Sun, Mingxu Zhou, Pei Chen, Shihong Ren, Weitao You, Yujia Lu","submitted_at":"2025-01-17T06:30:11Z","abstract_excerpt":"Composing music for video is essential yet challenging, leading to a growing interest in automating music generation for video applications. Existing approaches often struggle to achieve robust music-video correspondence and generative diversity, primarily due to inadequate feature alignment methods and insufficient datasets. In this study, we present General Video-to-Music Generation model (GVMGen), designed for generating high-related music to the video input. Our model employs hierarchical attentions to extract and align video features with music in both spatial and temporal dimensions, ens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09972","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/2501.09972/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":"2026-07-05T10:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RoIrJrWMRQ2vU58NcVqOaTjctMnENlu4Br/QS6Y6xUauilRe3NKAPTa45azPuOiEpAG/GiSRM+kZVYsui0kYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:38:37.010721Z"},"content_sha256":"0e71363ad54cdea93bf13a4bd8bc30851aadbc1f84b8050b63202d70dc639517","schema_version":"1.0","event_id":"sha256:0e71363ad54cdea93bf13a4bd8bc30851aadbc1f84b8050b63202d70dc639517"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XCQ3HD46KMAFEDEFLLHWM6AZR/bundle.json","state_url":"https://pith.science/pith/5XCQ3HD46KMAFEDEFLLHWM6AZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XCQ3HD46KMAFEDEFLLHWM6AZR/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":"2026-08-08T03:38:37Z","links":{"resolver":"https://pith.science/pith/5XCQ3HD46KMAFEDEFLLHWM6AZR","bundle":"https://pith.science/pith/5XCQ3HD46KMAFEDEFLLHWM6AZR/bundle.json","state":"https://pith.science/pith/5XCQ3HD46KMAFEDEFLLHWM6AZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XCQ3HD46KMAFEDEFLLHWM6AZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5XCQ3HD46KMAFEDEFLLHWM6AZR","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":"6c9392abce6d56c671e331ea606cb30de129ec040e7bead34ce3b0397e381ba2","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-17T06:30:11Z","title_canon_sha256":"15c9d56ca15ab7e6bfe472885859957e9544ab01e21c83b7b8c71663e9f7b915"},"schema_version":"1.0","source":{"id":"2501.09972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09972","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09972v1","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09972","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"5XCQ3HD46KMA","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"5XCQ3HD46KMAFEDE","created_at":"2026-07-05T10:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"5XCQ3HD4","created_at":"2026-07-05T10:50:46Z"}],"graph_snapshots":[{"event_id":"sha256:0e71363ad54cdea93bf13a4bd8bc30851aadbc1f84b8050b63202d70dc639517","target":"graph","created_at":"2026-07-05T10:50:46Z","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/2501.09972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Composing music for video is essential yet challenging, leading to a growing interest in automating music generation for video applications. Existing approaches often struggle to achieve robust music-video correspondence and generative diversity, primarily due to inadequate feature alignment methods and insufficient datasets. In this study, we present General Video-to-Music Generation model (GVMGen), designed for generating high-related music to the video input. Our model employs hierarchical attentions to extract and align video features with music in both spatial and temporal dimensions, ens","authors_text":"Heda Zuo, Junxian Wu, Lingyun Sun, Mingxu Zhou, Pei Chen, Shihong Ren, Weitao You, Yujia Lu","cross_cats":["cs.AI","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-17T06:30:11Z","title":"GVMGen: A General Video-to-Music Generation Model with Hierarchical Attentions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09972","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:da4a08b6e8875999ba81f149ac829c75ac10c112dc8399f7aa2c88783118de2b","target":"record","created_at":"2026-07-05T10:50:46Z","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":"6c9392abce6d56c671e331ea606cb30de129ec040e7bead34ce3b0397e381ba2","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-17T06:30:11Z","title_canon_sha256":"15c9d56ca15ab7e6bfe472885859957e9544ab01e21c83b7b8c71663e9f7b915"},"schema_version":"1.0","source":{"id":"2501.09972","kind":"arxiv","version":1}},"canonical_sha256":"edc50d9c7cf2980290642ad67b33c0cc41bed392e87b2355ebc526b2f529f6d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edc50d9c7cf2980290642ad67b33c0cc41bed392e87b2355ebc526b2f529f6d6","first_computed_at":"2026-07-05T10:50:46.673444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:46.673444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BxL4ML/znaxWY7J+5ArnmPoF5Iq97GWLc7uSqEMcLtePcUYQiotoi8a01vltyqmAi6xGh1CQFnB9gpxMp2/VCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:46.673943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da4a08b6e8875999ba81f149ac829c75ac10c112dc8399f7aa2c88783118de2b","sha256:0e71363ad54cdea93bf13a4bd8bc30851aadbc1f84b8050b63202d70dc639517"],"state_sha256":"a938a3e40352a871eb001f2b01099815a0b0884bc21bf23c3ee5e534f9882c1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lm7kXAw6qMmBZmtWURsos7hTJZZCEkGYZ7LRaDGDtljGEJHYbhCvtkVjjh/3nnJF/JHIclgTviI221ovIz9mBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:38:37.014369Z","bundle_sha256":"90de51dfaa8b767690b41e17d0973b0fa7ad61db7abd032f7255c88811e203e1"}}