{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I3NAHG6FXK36FGJYIU5EXU66TJ","short_pith_number":"pith:I3NAHG6F","canonical_record":{"source":{"id":"2509.00029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-20T13:54:53Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"d201e4e62c84dd7fec59e21fd6b722fa6b679c81b3c76e7e3f36cbaaf678d02c","abstract_canon_sha256":"5a21915a742a463b108e4c935fd44dce07803cecfc69f5844ce0e97fdb946db3"},"schema_version":"1.0"},"canonical_sha256":"46da039bc5bab7e29938453a4bd3de9a56e7641342737688cfc14f18614fe909","source":{"kind":"arxiv","id":"2509.00029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00029","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00029v1","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00029","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"pith_short_12","alias_value":"I3NAHG6FXK36","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"pith_short_16","alias_value":"I3NAHG6FXK36FGJY","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"pith_short_8","alias_value":"I3NAHG6F","created_at":"2026-07-05T12:02:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I3NAHG6FXK36FGJYIU5EXU66TJ","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-20T13:54:53Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"d201e4e62c84dd7fec59e21fd6b722fa6b679c81b3c76e7e3f36cbaaf678d02c","abstract_canon_sha256":"5a21915a742a463b108e4c935fd44dce07803cecfc69f5844ce0e97fdb946db3"},"schema_version":"1.0"},"canonical_sha256":"46da039bc5bab7e29938453a4bd3de9a56e7641342737688cfc14f18614fe909","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:08.196916Z","signature_b64":"ByeqB4IAulLN6cFTfncr/7qbibgfaeeOW+zeZ7boiX3+aGaTdeyYWrjUb0R4c9e/ABX6hq5aMCIsT26kz3C+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46da039bc5bab7e29938453a4bd3de9a56e7641342737688cfc14f18614fe909","last_reissued_at":"2026-07-05T12:02:08.196496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:08.196496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00029","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":"2026-07-05T12:02:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSmedePQWKnHZCbzH13Enr8wgZcKfPhz2ZNiVtbMaWc8vdo8fce+zgqlp8Wd5DncXAfJEfAl0zgohcVXVJC4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:41:12.767447Z"},"content_sha256":"9a86e70dfb84e14e612dada1fef6fbe42f442afb538119b941c35035ebb86a65","schema_version":"1.0","event_id":"sha256:9a86e70dfb84e14e612dada1fef6fbe42f442afb538119b941c35035ebb86a65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I3NAHG6FXK36FGJYIU5EXU66TJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Sound to Sight: Towards AI-authored Music Videos","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Agnes Mercedes Kloft, Glenn McGarry, Justyna Starostka, Kun Li, Leo Vitasovic, Martin Cunneen, Sami S. Brandt, Stella Gra{\\ss}hof, Ville V. Lehtola","submitted_at":"2025-08-20T13:54:53Z","abstract_excerpt":"Conventional music visualisation systems rely on handcrafted ad hoc transformations of shapes and colours that offer only limited expressiveness. We propose two novel pipelines for automatically generating music videos from any user-specified, vocal or instrumental song using off-the-shelf deep learning models. Inspired by the manual workflows of music video producers, we experiment on how well latent feature-based techniques can analyse audio to detect musical qualities, such as emotional cues and instrumental patterns, and distil them into textual scene descriptions using a language model. N"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00029","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/2509.00029/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":"2026-07-05T12:02:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"85jaimQD5O1lRVp6VPV2MZChso8Aai1IMx5UpieerofVpHCbNTUsead45W5of2GQl0ox8V07ZSAy6oh7BTbACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:41:12.768104Z"},"content_sha256":"676738a8937db7c5a28eb309137458010ecdd3f16879dcfc7d7d1afac2f0b545","schema_version":"1.0","event_id":"sha256:676738a8937db7c5a28eb309137458010ecdd3f16879dcfc7d7d1afac2f0b545"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3NAHG6FXK36FGJYIU5EXU66TJ/bundle.json","state_url":"https://pith.science/pith/I3NAHG6FXK36FGJYIU5EXU66TJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3NAHG6FXK36FGJYIU5EXU66TJ/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":"2026-08-10T19:41:12Z","links":{"resolver":"https://pith.science/pith/I3NAHG6FXK36FGJYIU5EXU66TJ","bundle":"https://pith.science/pith/I3NAHG6FXK36FGJYIU5EXU66TJ/bundle.json","state":"https://pith.science/pith/I3NAHG6FXK36FGJYIU5EXU66TJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3NAHG6FXK36FGJYIU5EXU66TJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I3NAHG6FXK36FGJYIU5EXU66TJ","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":"5a21915a742a463b108e4c935fd44dce07803cecfc69f5844ce0e97fdb946db3","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-20T13:54:53Z","title_canon_sha256":"d201e4e62c84dd7fec59e21fd6b722fa6b679c81b3c76e7e3f36cbaaf678d02c"},"schema_version":"1.0","source":{"id":"2509.00029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00029","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00029v1","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00029","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"pith_short_12","alias_value":"I3NAHG6FXK36","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"pith_short_16","alias_value":"I3NAHG6FXK36FGJY","created_at":"2026-07-05T12:02:08Z"},{"alias_kind":"pith_short_8","alias_value":"I3NAHG6F","created_at":"2026-07-05T12:02:08Z"}],"graph_snapshots":[{"event_id":"sha256:676738a8937db7c5a28eb309137458010ecdd3f16879dcfc7d7d1afac2f0b545","target":"graph","created_at":"2026-07-05T12:02:08Z","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/2509.00029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional music visualisation systems rely on handcrafted ad hoc transformations of shapes and colours that offer only limited expressiveness. We propose two novel pipelines for automatically generating music videos from any user-specified, vocal or instrumental song using off-the-shelf deep learning models. Inspired by the manual workflows of music video producers, we experiment on how well latent feature-based techniques can analyse audio to detect musical qualities, such as emotional cues and instrumental patterns, and distil them into textual scene descriptions using a language model. N","authors_text":"Agnes Mercedes Kloft, Glenn McGarry, Justyna Starostka, Kun Li, Leo Vitasovic, Martin Cunneen, Sami S. Brandt, Stella Gra{\\ss}hof, Ville V. Lehtola","cross_cats":["cs.AI","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-20T13:54:53Z","title":"From Sound to Sight: Towards AI-authored Music Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00029","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":"sha256:9a86e70dfb84e14e612dada1fef6fbe42f442afb538119b941c35035ebb86a65","target":"record","created_at":"2026-07-05T12:02:08Z","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":"5a21915a742a463b108e4c935fd44dce07803cecfc69f5844ce0e97fdb946db3","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-20T13:54:53Z","title_canon_sha256":"d201e4e62c84dd7fec59e21fd6b722fa6b679c81b3c76e7e3f36cbaaf678d02c"},"schema_version":"1.0","source":{"id":"2509.00029","kind":"arxiv","version":1}},"canonical_sha256":"46da039bc5bab7e29938453a4bd3de9a56e7641342737688cfc14f18614fe909","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46da039bc5bab7e29938453a4bd3de9a56e7641342737688cfc14f18614fe909","first_computed_at":"2026-07-05T12:02:08.196496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:08.196496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ByeqB4IAulLN6cFTfncr/7qbibgfaeeOW+zeZ7boiX3+aGaTdeyYWrjUb0R4c9e/ABX6hq5aMCIsT26kz3C+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:08.196916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a86e70dfb84e14e612dada1fef6fbe42f442afb538119b941c35035ebb86a65","sha256:676738a8937db7c5a28eb309137458010ecdd3f16879dcfc7d7d1afac2f0b545"],"state_sha256":"6752d470cb2e6689d8e46f92b85c22599166dbaf3dfdbbd593b5953c4a6b363a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1G8JEAJA6vKJb71Lp/UNbmsDHp34lRAcxgz5HIOkl4B0KPPWt+QUywap2ObyOxbtnEbjNZxq02RIW+XtAUXJDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:41:12.772521Z","bundle_sha256":"9328b67ddf12daef408255ed4ce74eddf5f7390734daba7f2af3306c79a10f4f"}}