{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DBFV7CW4MEQE5RM5OV2OHLU63T","short_pith_number":"pith:DBFV7CW4","canonical_record":{"source":{"id":"2406.04321","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:58:11Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD"],"title_canon_sha256":"c7e5c5cd481001991d99294c4825f3e96c49b6ae2a0db239e90fd0829fafe150","abstract_canon_sha256":"f0aec36806b55cf124d99eef998677b13a888f349b792f2f7aa2213932d05715"},"schema_version":"1.0"},"canonical_sha256":"184b5f8adc61204ec59d7574e3ae9edcce0d5a5d2d61db5c3411321ef272ca8d","source":{"kind":"arxiv","id":"2406.04321","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04321","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04321v3","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04321","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"pith_short_12","alias_value":"DBFV7CW4MEQE","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"pith_short_16","alias_value":"DBFV7CW4MEQE5RM5","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"pith_short_8","alias_value":"DBFV7CW4","created_at":"2026-07-05T10:59:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DBFV7CW4MEQE5RM5OV2OHLU63T","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04321","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:58:11Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD"],"title_canon_sha256":"c7e5c5cd481001991d99294c4825f3e96c49b6ae2a0db239e90fd0829fafe150","abstract_canon_sha256":"f0aec36806b55cf124d99eef998677b13a888f349b792f2f7aa2213932d05715"},"schema_version":"1.0"},"canonical_sha256":"184b5f8adc61204ec59d7574e3ae9edcce0d5a5d2d61db5c3411321ef272ca8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:46.975047Z","signature_b64":"2CLWaizZrPVVJHYaX+vq54DQA/puN2jWPk3BC/tmACrHnRfIj0l5s7ehj1SeUaVfAxIHU78vmy/K9UVYkmy/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"184b5f8adc61204ec59d7574e3ae9edcce0d5a5d2d61db5c3411321ef272ca8d","last_reissued_at":"2026-07-05T10:59:46.974593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:46.974593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04321","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:59:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LqqUe9gufQEUq8G99xk6S3omhFXIZllm9yPL69NN/BF8Xh5iMGjaVIrRDh67VlnwXGQRicSNCCC+tDiOLhBMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:20:10.278771Z"},"content_sha256":"bf614bde6995b50eb28f6c0f32dc6c2dabd8ae0e0a693455bbfd808d69a718c6","schema_version":"1.0","event_id":"sha256:bf614bde6995b50eb28f6c0f32dc6c2dabd8ae0e0a693455bbfd808d69a718c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DBFV7CW4MEQE5RM5OV2OHLU63T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Jiahao Pan, Qifeng Chen, Qifeng Liu, Ruibin Yuan, Wei Xue, Xu Tan, Yike Guo, Zeyue Tian, Zhaoyang Liu","submitted_at":"2024-06-06T17:58:11Z","abstract_excerpt":"In this work, we systematically study music generation conditioned solely on the video. First, we present a large-scale dataset comprising 360K video-music pairs, including various genres such as movie trailers, advertisements, and documentaries. Furthermore, we propose VidMuse, a simple framework for generating music aligned with video inputs. VidMuse stands out by producing high-fidelity music that is both acoustically and semantically aligned with the video. By incorporating local and global visual cues, VidMuse enables the creation of musically coherent audio tracks that consistently match"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04321","kind":"arxiv","version":3},"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/2406.04321/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":"2026-07-05T10:59:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m9QUUxyJ/Z3h1NI7r3xwBNmuE2NWOVssv9aWzUZ5/erpO37GoYPG+vG4BKhL3sM8V+/IObeh9jVRvzGajQlvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:20:10.279363Z"},"content_sha256":"879557cb5d47b21902e8ea0d1bb77e926e0146d69e777edacebb6a2f7ea3702f","schema_version":"1.0","event_id":"sha256:879557cb5d47b21902e8ea0d1bb77e926e0146d69e777edacebb6a2f7ea3702f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBFV7CW4MEQE5RM5OV2OHLU63T/bundle.json","state_url":"https://pith.science/pith/DBFV7CW4MEQE5RM5OV2OHLU63T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBFV7CW4MEQE5RM5OV2OHLU63T/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":"2026-08-08T16:20:10Z","links":{"resolver":"https://pith.science/pith/DBFV7CW4MEQE5RM5OV2OHLU63T","bundle":"https://pith.science/pith/DBFV7CW4MEQE5RM5OV2OHLU63T/bundle.json","state":"https://pith.science/pith/DBFV7CW4MEQE5RM5OV2OHLU63T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBFV7CW4MEQE5RM5OV2OHLU63T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DBFV7CW4MEQE5RM5OV2OHLU63T","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":"f0aec36806b55cf124d99eef998677b13a888f349b792f2f7aa2213932d05715","cross_cats_sorted":["cs.LG","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:58:11Z","title_canon_sha256":"c7e5c5cd481001991d99294c4825f3e96c49b6ae2a0db239e90fd0829fafe150"},"schema_version":"1.0","source":{"id":"2406.04321","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04321","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04321v3","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04321","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"pith_short_12","alias_value":"DBFV7CW4MEQE","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"pith_short_16","alias_value":"DBFV7CW4MEQE5RM5","created_at":"2026-07-05T10:59:46Z"},{"alias_kind":"pith_short_8","alias_value":"DBFV7CW4","created_at":"2026-07-05T10:59:46Z"}],"graph_snapshots":[{"event_id":"sha256:879557cb5d47b21902e8ea0d1bb77e926e0146d69e777edacebb6a2f7ea3702f","target":"graph","created_at":"2026-07-05T10:59:46Z","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/2406.04321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we systematically study music generation conditioned solely on the video. First, we present a large-scale dataset comprising 360K video-music pairs, including various genres such as movie trailers, advertisements, and documentaries. Furthermore, we propose VidMuse, a simple framework for generating music aligned with video inputs. VidMuse stands out by producing high-fidelity music that is both acoustically and semantically aligned with the video. By incorporating local and global visual cues, VidMuse enables the creation of musically coherent audio tracks that consistently match","authors_text":"Jiahao Pan, Qifeng Chen, Qifeng Liu, Ruibin Yuan, Wei Xue, Xu Tan, Yike Guo, Zeyue Tian, Zhaoyang Liu","cross_cats":["cs.LG","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:58:11Z","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04321","kind":"arxiv","version":3},"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:bf614bde6995b50eb28f6c0f32dc6c2dabd8ae0e0a693455bbfd808d69a718c6","target":"record","created_at":"2026-07-05T10:59:46Z","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":"f0aec36806b55cf124d99eef998677b13a888f349b792f2f7aa2213932d05715","cross_cats_sorted":["cs.LG","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:58:11Z","title_canon_sha256":"c7e5c5cd481001991d99294c4825f3e96c49b6ae2a0db239e90fd0829fafe150"},"schema_version":"1.0","source":{"id":"2406.04321","kind":"arxiv","version":3}},"canonical_sha256":"184b5f8adc61204ec59d7574e3ae9edcce0d5a5d2d61db5c3411321ef272ca8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"184b5f8adc61204ec59d7574e3ae9edcce0d5a5d2d61db5c3411321ef272ca8d","first_computed_at":"2026-07-05T10:59:46.974593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:46.974593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2CLWaizZrPVVJHYaX+vq54DQA/puN2jWPk3BC/tmACrHnRfIj0l5s7ehj1SeUaVfAxIHU78vmy/K9UVYkmy/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:46.975047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04321","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf614bde6995b50eb28f6c0f32dc6c2dabd8ae0e0a693455bbfd808d69a718c6","sha256:879557cb5d47b21902e8ea0d1bb77e926e0146d69e777edacebb6a2f7ea3702f"],"state_sha256":"39b625a076a560390eda2dbed7f9b369a12f446a822a4808e8f40d6302f83dd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yUeQFIe6pAg2v1eZbcxlDUdmuPQGoW8VVX/Ps/KE5J2yghurFCXCjAmGz+CdVHCttcJfUU/WFbXCmneKjxlsAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:20:10.284311Z","bundle_sha256":"e414f5f3b1a69c3b8fca54b8e0c33659f3e2b3f82597b1ac0a10403f65827ccf"}}