{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OYPEZI54IARYTKVTMQITICOHRF","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":"d9c27aaf0be84ee2780c78e51341ecb7e841b6b0700e1b1ff4cacb5e17164d7a","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-07T12:56:20Z","title_canon_sha256":"42003eac77c7417d7a0eda9742864bdbc369878525375eba4925a280a8ffe68a"},"schema_version":"1.0","source":{"id":"2507.04955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04955","created_at":"2026-07-05T11:33:07Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04955v1","created_at":"2026-07-05T11:33:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04955","created_at":"2026-07-05T11:33:07Z"},{"alias_kind":"pith_short_12","alias_value":"OYPEZI54IARY","created_at":"2026-07-05T11:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"OYPEZI54IARYTKVT","created_at":"2026-07-05T11:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"OYPEZI54","created_at":"2026-07-05T11:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:0d2c735f985cc37c1dc454828c1c57a0c2d9a41da779c60cdcc606db3fec1afd","target":"graph","created_at":"2026-07-05T11:33:07Z","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/2507.04955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Expotion (Facial Expression and Motion Control for Multimodal Music Generation), a generative model leveraging multimodal visual controls - specifically, human facial expressions and upper-body motion - as well as text prompts to produce expressive and temporally accurate music. We adopt parameter-efficient fine-tuning (PEFT) on the pretrained text-to-music generation model, enabling fine-grained adaptation to the multimodal controls using a small dataset. To ensure precise synchronization between video and music, we introduce a temporal smoothing strategy to align multiple modaliti","authors_text":"Fathinah Izzati, Gus Xia, Xinyue Li","cross_cats":["cs.AI","cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-07T12:56:20Z","title":"EXPOTION: Facial Expression and Motion Control for Multimodal Music Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04955","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":"sha256:7273c8fc73fb24e4a168e7740ac843be0814065c8737d7612f1eb23d43093ce3","target":"record","created_at":"2026-07-05T11:33:07Z","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":"d9c27aaf0be84ee2780c78e51341ecb7e841b6b0700e1b1ff4cacb5e17164d7a","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-07T12:56:20Z","title_canon_sha256":"42003eac77c7417d7a0eda9742864bdbc369878525375eba4925a280a8ffe68a"},"schema_version":"1.0","source":{"id":"2507.04955","kind":"arxiv","version":1}},"canonical_sha256":"761e4ca3bc402389aab364113409c7896525ceb179d8bfe93b7f74be26bb6bae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"761e4ca3bc402389aab364113409c7896525ceb179d8bfe93b7f74be26bb6bae","first_computed_at":"2026-07-05T11:33:07.035899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:07.035899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rqFc8xRI3zRlcoCDPyBNFg61j6bHP7b0g3M+h+xPCDuzQ1YwyaSFpx3c7igFAW9YqahdB8Dp5wdTobKMM0uACg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:07.036472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7273c8fc73fb24e4a168e7740ac843be0814065c8737d7612f1eb23d43093ce3","sha256:0d2c735f985cc37c1dc454828c1c57a0c2d9a41da779c60cdcc606db3fec1afd"],"state_sha256":"856bac2764d867e0ff7dea7c4661f4fe83dec5552c5a64aed6e7a73779200b83"}