{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6E7U4F6UGA42EIJOZ62WW6M537","short_pith_number":"pith:6E7U4F6U","canonical_record":{"source":{"id":"2311.00968","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-02T03:33:00Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"558eee76ac02f5c0ec99c4d2d601124222ac2fc70e5b5df05c780c15516e61af","abstract_canon_sha256":"76987cf83978fa3ed7fc2f6fdc6aac782dfc75c70ba04cb09c22623fe5d5b885"},"schema_version":"1.0"},"canonical_sha256":"f13f4e17d43039a2212ecfb56b799ddfd6234c427117df0d96c195a139030ed2","source":{"kind":"arxiv","id":"2311.00968","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00968","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00968v2","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00968","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"6E7U4F6UGA42","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"6E7U4F6UGA42EIJO","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"6E7U4F6U","created_at":"2026-07-05T08:25:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6E7U4F6UGA42EIJOZ62WW6M537","target":"record","payload":{"canonical_record":{"source":{"id":"2311.00968","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-02T03:33:00Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"558eee76ac02f5c0ec99c4d2d601124222ac2fc70e5b5df05c780c15516e61af","abstract_canon_sha256":"76987cf83978fa3ed7fc2f6fdc6aac782dfc75c70ba04cb09c22623fe5d5b885"},"schema_version":"1.0"},"canonical_sha256":"f13f4e17d43039a2212ecfb56b799ddfd6234c427117df0d96c195a139030ed2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:29.562567Z","signature_b64":"S/GgGDgdYZIo6EegRB8oGHazvJ6monm8xJeMLqYkDFt1iiV7ztqmVRknxWsAWx0yp5uSIn9/oBXiso0Qj4I7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f13f4e17d43039a2212ecfb56b799ddfd6234c427117df0d96c195a139030ed2","last_reissued_at":"2026-07-05T08:25:29.562083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:29.562083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.00968","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":"2026-07-05T08:25:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2W6v4l81PlM5PF5PeqCwF2vrF3onF4gRkA5nYH0CtYXh0YDSFIV93SK/fmMwpClGSZFq9bFq0qX/p9MS6tzDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:38:07.213230Z"},"content_sha256":"2558040dc40bcc97223c213472c8704b034ee3ef6f3ebb6df9322de8d61eebb7","schema_version":"1.0","event_id":"sha256:2558040dc40bcc97223c213472c8704b034ee3ef6f3ebb6df9322de8d61eebb7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6E7U4F6UGA42EIJOZ62WW6M537","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dorien Herremans, Jaeyong Kang, Soujanya Poria","submitted_at":"2023-11-02T03:33:00Z","abstract_excerpt":"Numerous studies in the field of music generation have demonstrated impressive performance, yet virtually no models are able to directly generate music to match accompanying videos. In this work, we develop a generative music AI framework, Video2Music, that can match a provided video. We first curated a unique collection of music videos. Then, we analysed the music videos to obtain semantic, scene offset, motion, and emotion features. These distinct features are then employed as guiding input to our music generation model. We transcribe the audio files into MIDI and chords, and extract feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00968","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/2311.00968/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":"2026-07-05T08:25:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JHR0WA3uvr3BCVPbmcGHMgb63WAO0x4c+8j9Z0x2o5lVJnR7pQGPZWFVM7zQvhSRirJQD4jHeTnqdCF9AmKvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:38:07.213734Z"},"content_sha256":"c66ca52f634e332082104be2578c002ab2cad51e31c23b48b1cb877bb270a5d0","schema_version":"1.0","event_id":"sha256:c66ca52f634e332082104be2578c002ab2cad51e31c23b48b1cb877bb270a5d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6E7U4F6UGA42EIJOZ62WW6M537/bundle.json","state_url":"https://pith.science/pith/6E7U4F6UGA42EIJOZ62WW6M537/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6E7U4F6UGA42EIJOZ62WW6M537/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":"2026-08-14T09:38:07Z","links":{"resolver":"https://pith.science/pith/6E7U4F6UGA42EIJOZ62WW6M537","bundle":"https://pith.science/pith/6E7U4F6UGA42EIJOZ62WW6M537/bundle.json","state":"https://pith.science/pith/6E7U4F6UGA42EIJOZ62WW6M537/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6E7U4F6UGA42EIJOZ62WW6M537/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6E7U4F6UGA42EIJOZ62WW6M537","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":"76987cf83978fa3ed7fc2f6fdc6aac782dfc75c70ba04cb09c22623fe5d5b885","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-02T03:33:00Z","title_canon_sha256":"558eee76ac02f5c0ec99c4d2d601124222ac2fc70e5b5df05c780c15516e61af"},"schema_version":"1.0","source":{"id":"2311.00968","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00968","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00968v2","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00968","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"6E7U4F6UGA42","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"6E7U4F6UGA42EIJO","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"6E7U4F6U","created_at":"2026-07-05T08:25:29Z"}],"graph_snapshots":[{"event_id":"sha256:c66ca52f634e332082104be2578c002ab2cad51e31c23b48b1cb877bb270a5d0","target":"graph","created_at":"2026-07-05T08:25:29Z","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/2311.00968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous studies in the field of music generation have demonstrated impressive performance, yet virtually no models are able to directly generate music to match accompanying videos. In this work, we develop a generative music AI framework, Video2Music, that can match a provided video. We first curated a unique collection of music videos. Then, we analysed the music videos to obtain semantic, scene offset, motion, and emotion features. These distinct features are then employed as guiding input to our music generation model. We transcribe the audio files into MIDI and chords, and extract feature","authors_text":"Dorien Herremans, Jaeyong Kang, Soujanya Poria","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-02T03:33:00Z","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00968","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":"sha256:2558040dc40bcc97223c213472c8704b034ee3ef6f3ebb6df9322de8d61eebb7","target":"record","created_at":"2026-07-05T08:25:29Z","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":"76987cf83978fa3ed7fc2f6fdc6aac782dfc75c70ba04cb09c22623fe5d5b885","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-02T03:33:00Z","title_canon_sha256":"558eee76ac02f5c0ec99c4d2d601124222ac2fc70e5b5df05c780c15516e61af"},"schema_version":"1.0","source":{"id":"2311.00968","kind":"arxiv","version":2}},"canonical_sha256":"f13f4e17d43039a2212ecfb56b799ddfd6234c427117df0d96c195a139030ed2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f13f4e17d43039a2212ecfb56b799ddfd6234c427117df0d96c195a139030ed2","first_computed_at":"2026-07-05T08:25:29.562083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:29.562083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S/GgGDgdYZIo6EegRB8oGHazvJ6monm8xJeMLqYkDFt1iiV7ztqmVRknxWsAWx0yp5uSIn9/oBXiso0Qj4I7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:29.562567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00968","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2558040dc40bcc97223c213472c8704b034ee3ef6f3ebb6df9322de8d61eebb7","sha256:c66ca52f634e332082104be2578c002ab2cad51e31c23b48b1cb877bb270a5d0"],"state_sha256":"8ca6205a2bfe6d401a78621f17ace5c5d0ecdcc799b39d2c3493da45d097f3ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iq5kmABkzTa3D7ypTmc7znTveItiAAncB1c2GS0ywJmK2oQoaZqDbU4A9/MBDDWopsf03wWHi5VAqeFJ15TKBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:38:07.217937Z","bundle_sha256":"17b8dbc4319e23f7184d75ece13bec3a1de9fa7cb628aeb78639988a0971c66a"}}