{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7HA6ZKRFB4B2AKF73NLWUCATHH","short_pith_number":"pith:7HA6ZKRF","canonical_record":{"source":{"id":"2405.02801","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-05T03:15:52Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"5b0596c80f3701e0f9c2a3dd04254941cf055d71eb9699f9287f9d68f4ae6b0f","abstract_canon_sha256":"d15495d3ea9ed563d03e2c6efe3e0e728ea0b4997cc605dca020a94ae39d1db0"},"schema_version":"1.0"},"canonical_sha256":"f9c1ecaa250f03a028bfdb576a081339c86e839d01e5e5ec3b44721e0bbd21d8","source":{"kind":"arxiv","id":"2405.02801","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02801","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02801v3","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02801","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"7HA6ZKRFB4B2","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"7HA6ZKRFB4B2AKF7","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"7HA6ZKRF","created_at":"2026-07-05T09:39:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7HA6ZKRFB4B2AKF73NLWUCATHH","target":"record","payload":{"canonical_record":{"source":{"id":"2405.02801","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-05T03:15:52Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"5b0596c80f3701e0f9c2a3dd04254941cf055d71eb9699f9287f9d68f4ae6b0f","abstract_canon_sha256":"d15495d3ea9ed563d03e2c6efe3e0e728ea0b4997cc605dca020a94ae39d1db0"},"schema_version":"1.0"},"canonical_sha256":"f9c1ecaa250f03a028bfdb576a081339c86e839d01e5e5ec3b44721e0bbd21d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:54.557445Z","signature_b64":"klvkMI8CAdQ0RHSlh0hyzU2OnTlQpbqioO5HnnXg0W1khEI9uvd4sDOaDUEYKrRHakhPtYHuU67wWNFX6LU8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9c1ecaa250f03a028bfdb576a081339c86e839d01e5e5ec3b44721e0bbd21d8","last_reissued_at":"2026-07-05T09:39:54.556951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:54.556951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.02801","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":"2026-07-05T09:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W7mRg+UV9NbH1t4J3Dak7iTNE62lAPLEyfD8PzaG5FwNkY9XsDwEX+XmDGMB0GbN+LUbUQE+uhVa2w0YietNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:41:40.659647Z"},"content_sha256":"5c292cff177721ca5fc94d689d35573ec6e1b512f85eee1abe9148cd00ba3c5f","schema_version":"1.0","event_id":"sha256:5c292cff177721ca5fc94d689d35573ec6e1b512f85eee1abe9148cd00ba3c5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7HA6ZKRFB4B2AKF73NLWUCATHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mozart's Touch: A Lightweight Multi-modal Music Generation Framework Based on Pre-Trained Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiajun Li, Shuchang Liu, Tianze Xu, Xinrui Yao, Xuesong Chen","submitted_at":"2024-05-05T03:15:52Z","abstract_excerpt":"In recent years, AI-Generated Content (AIGC) has witnessed rapid advancements, facilitating the creation of music, images, and other artistic forms across a wide range of industries. However, current models for image- and video-to-music synthesis struggle to capture the nuanced emotions and atmosphere conveyed by visual content. To fill this gap, we propose Mozart's Touch, a multi-modal music generation framework capable of generating music aligned with cross-modal inputs such as images, videos, and text. The framework consists of three key components: Multi-modal Captioning Module, Large Lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02801","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/2405.02801/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":"2026-07-05T09:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"//bmQ4pZzRakmQ2F74DMEuFhLPoEvaIS94wNZlK5uuzsG+YdOHlTRk7gDzoYJeF2ApoMnLAf7znVevRcknUGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:41:40.660630Z"},"content_sha256":"4316efc216d0122d2e047e4e7062e9cbf88ce6237f446b9d9f3cc58dff055ecd","schema_version":"1.0","event_id":"sha256:4316efc216d0122d2e047e4e7062e9cbf88ce6237f446b9d9f3cc58dff055ecd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7HA6ZKRFB4B2AKF73NLWUCATHH/bundle.json","state_url":"https://pith.science/pith/7HA6ZKRFB4B2AKF73NLWUCATHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7HA6ZKRFB4B2AKF73NLWUCATHH/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":"2026-08-04T20:41:40Z","links":{"resolver":"https://pith.science/pith/7HA6ZKRFB4B2AKF73NLWUCATHH","bundle":"https://pith.science/pith/7HA6ZKRFB4B2AKF73NLWUCATHH/bundle.json","state":"https://pith.science/pith/7HA6ZKRFB4B2AKF73NLWUCATHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7HA6ZKRFB4B2AKF73NLWUCATHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7HA6ZKRFB4B2AKF73NLWUCATHH","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":"d15495d3ea9ed563d03e2c6efe3e0e728ea0b4997cc605dca020a94ae39d1db0","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-05T03:15:52Z","title_canon_sha256":"5b0596c80f3701e0f9c2a3dd04254941cf055d71eb9699f9287f9d68f4ae6b0f"},"schema_version":"1.0","source":{"id":"2405.02801","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02801","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02801v3","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02801","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"7HA6ZKRFB4B2","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"7HA6ZKRFB4B2AKF7","created_at":"2026-07-05T09:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"7HA6ZKRF","created_at":"2026-07-05T09:39:54Z"}],"graph_snapshots":[{"event_id":"sha256:4316efc216d0122d2e047e4e7062e9cbf88ce6237f446b9d9f3cc58dff055ecd","target":"graph","created_at":"2026-07-05T09:39:54Z","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/2405.02801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, AI-Generated Content (AIGC) has witnessed rapid advancements, facilitating the creation of music, images, and other artistic forms across a wide range of industries. However, current models for image- and video-to-music synthesis struggle to capture the nuanced emotions and atmosphere conveyed by visual content. To fill this gap, we propose Mozart's Touch, a multi-modal music generation framework capable of generating music aligned with cross-modal inputs such as images, videos, and text. The framework consists of three key components: Multi-modal Captioning Module, Large Lang","authors_text":"Jiajun Li, Shuchang Liu, Tianze Xu, Xinrui Yao, Xuesong Chen","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-05T03:15:52Z","title":"Mozart's Touch: A Lightweight Multi-modal Music Generation Framework Based on Pre-Trained Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02801","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":"sha256:5c292cff177721ca5fc94d689d35573ec6e1b512f85eee1abe9148cd00ba3c5f","target":"record","created_at":"2026-07-05T09:39:54Z","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":"d15495d3ea9ed563d03e2c6efe3e0e728ea0b4997cc605dca020a94ae39d1db0","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-05T03:15:52Z","title_canon_sha256":"5b0596c80f3701e0f9c2a3dd04254941cf055d71eb9699f9287f9d68f4ae6b0f"},"schema_version":"1.0","source":{"id":"2405.02801","kind":"arxiv","version":3}},"canonical_sha256":"f9c1ecaa250f03a028bfdb576a081339c86e839d01e5e5ec3b44721e0bbd21d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9c1ecaa250f03a028bfdb576a081339c86e839d01e5e5ec3b44721e0bbd21d8","first_computed_at":"2026-07-05T09:39:54.556951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:54.556951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"klvkMI8CAdQ0RHSlh0hyzU2OnTlQpbqioO5HnnXg0W1khEI9uvd4sDOaDUEYKrRHakhPtYHuU67wWNFX6LU8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:54.557445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02801","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c292cff177721ca5fc94d689d35573ec6e1b512f85eee1abe9148cd00ba3c5f","sha256:4316efc216d0122d2e047e4e7062e9cbf88ce6237f446b9d9f3cc58dff055ecd"],"state_sha256":"6d1020d97fa193a12104aaf907eb6e67449667c64db75086b481ba4adf15ae8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9le+Oslyx8q73Ty6v741Jwi0VBEi3/hLZ09AHnzeP9J4+NxuM1AB5eegK0vkaXPkcsWacuTypDeKB+SWvrJeBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:41:40.667511Z","bundle_sha256":"fdac5ebf2c06ae615eb261b90501d7de3a6ad5cadbcc809ead613721b581c30d"}}