{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OYPEZI54IARYTKVTMQITICOHRF","short_pith_number":"pith:OYPEZI54","canonical_record":{"source":{"id":"2507.04955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-07T12:56:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"42003eac77c7417d7a0eda9742864bdbc369878525375eba4925a280a8ffe68a","abstract_canon_sha256":"d9c27aaf0be84ee2780c78e51341ecb7e841b6b0700e1b1ff4cacb5e17164d7a"},"schema_version":"1.0"},"canonical_sha256":"761e4ca3bc402389aab364113409c7896525ceb179d8bfe93b7f74be26bb6bae","source":{"kind":"arxiv","id":"2507.04955","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OYPEZI54IARYTKVTMQITICOHRF","target":"record","payload":{"canonical_record":{"source":{"id":"2507.04955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-07T12:56:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"42003eac77c7417d7a0eda9742864bdbc369878525375eba4925a280a8ffe68a","abstract_canon_sha256":"d9c27aaf0be84ee2780c78e51341ecb7e841b6b0700e1b1ff4cacb5e17164d7a"},"schema_version":"1.0"},"canonical_sha256":"761e4ca3bc402389aab364113409c7896525ceb179d8bfe93b7f74be26bb6bae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:07.036472Z","signature_b64":"rqFc8xRI3zRlcoCDPyBNFg61j6bHP7b0g3M+h+xPCDuzQ1YwyaSFpx3c7igFAW9YqahdB8Dp5wdTobKMM0uACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"761e4ca3bc402389aab364113409c7896525ceb179d8bfe93b7f74be26bb6bae","last_reissued_at":"2026-07-05T11:33:07.035899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:07.035899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.04955","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":"2026-07-05T11:33:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NYFdh9DSORTVUM+eMBg7LCGyQ+/eAzUSSa1SZs1CjTW8uj+PSs2VS9BN0aNY83/eZf79LxMaWMRFCU+XspGxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:58:06.516179Z"},"content_sha256":"7273c8fc73fb24e4a168e7740ac843be0814065c8737d7612f1eb23d43093ce3","schema_version":"1.0","event_id":"sha256:7273c8fc73fb24e4a168e7740ac843be0814065c8737d7612f1eb23d43093ce3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OYPEZI54IARYTKVTMQITICOHRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EXPOTION: Facial Expression and Motion Control for Multimodal Music Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fathinah Izzati, Gus Xia, Xinyue Li","submitted_at":"2025-07-07T12:56:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04955","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/2507.04955/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":"2026-07-05T11:33:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9N9FAWEXZ2ZG3wOmFThbe83cp7ZbKCkIj3fzsFpFuL4V/PSNbaRe1St4xMhpdWRQy7sTI50av86eoD7gE8IhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:58:06.516888Z"},"content_sha256":"0d2c735f985cc37c1dc454828c1c57a0c2d9a41da779c60cdcc606db3fec1afd","schema_version":"1.0","event_id":"sha256:0d2c735f985cc37c1dc454828c1c57a0c2d9a41da779c60cdcc606db3fec1afd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OYPEZI54IARYTKVTMQITICOHRF/bundle.json","state_url":"https://pith.science/pith/OYPEZI54IARYTKVTMQITICOHRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OYPEZI54IARYTKVTMQITICOHRF/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":"2026-08-08T18:58:06Z","links":{"resolver":"https://pith.science/pith/OYPEZI54IARYTKVTMQITICOHRF","bundle":"https://pith.science/pith/OYPEZI54IARYTKVTMQITICOHRF/bundle.json","state":"https://pith.science/pith/OYPEZI54IARYTKVTMQITICOHRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OYPEZI54IARYTKVTMQITICOHRF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f9lDvrj2KwAdmWioJtKx2TgUddMWb97Es6dTRglb/OLtpUknILISf/vki0jX2Fpkh7QjWra1yxZrFQhONgsTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:58:06.523543Z","bundle_sha256":"c9860988d7e1932e07964361eb2660a732f391a15c9b8f6d393b40fe10bac521"}}