{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SI6BHRWCSM4LYYYZZHV3O6VUFU","short_pith_number":"pith:SI6BHRWC","canonical_record":{"source":{"id":"2407.10328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-14T20:51:08Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"63547c59c6ab66d2276dee2f9843936342493b62c140e58be9c1a55d8001c8af","abstract_canon_sha256":"f2260b24c9275d5cb3310c1d513a687f255d3f06c55e40283ab006c345cf2c0c"},"schema_version":"1.0"},"canonical_sha256":"923c13c6c29338bc6319c9ebb77ab42d015891b758887e76dbd47e9209f71f52","source":{"kind":"arxiv","id":"2407.10328","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10328","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10328v1","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10328","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"SI6BHRWCSM4L","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"SI6BHRWCSM4LYYYZ","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"SI6BHRWC","created_at":"2026-07-05T08:43:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SI6BHRWCSM4LYYYZZHV3O6VUFU","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-14T20:51:08Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"63547c59c6ab66d2276dee2f9843936342493b62c140e58be9c1a55d8001c8af","abstract_canon_sha256":"f2260b24c9275d5cb3310c1d513a687f255d3f06c55e40283ab006c345cf2c0c"},"schema_version":"1.0"},"canonical_sha256":"923c13c6c29338bc6319c9ebb77ab42d015891b758887e76dbd47e9209f71f52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:58.542912Z","signature_b64":"jJXpzpiyX8TmzJ4aedA+HxhBXlIw8P+Be04ccf82SerH5vslp1ISKci5nliM/eWqMRkGEmx7VXARVrm8VpZVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"923c13c6c29338bc6319c9ebb77ab42d015891b758887e76dbd47e9209f71f52","last_reissued_at":"2026-07-05T08:43:58.542490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:58.542490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10328","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":"2026-07-05T08:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqiYYJE+z1gynDIuiSrFabsSLPbrF6uO9Yf7PxGaVNH4RMzLrYNmz9e5+ynXYJXPti+bL04IZDRBbnEl3BfhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:09:15.542928Z"},"content_sha256":"a71a656d56f481ef9d611da44959da43804305a8f909d36361b62b2372bae1f4","schema_version":"1.0","event_id":"sha256:a71a656d56f481ef9d611da44959da43804305a8f909d36361b62b2372bae1f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SI6BHRWCSM4LYYYZZHV3O6VUFU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Interpretation Gap in Text-to-Music Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Yixiao Zhang, Yongyi Zang","submitted_at":"2024-07-14T20:51:08Z","abstract_excerpt":"Large-scale text-to-music generation models have significantly enhanced music creation capabilities, offering unprecedented creative freedom. However, their ability to collaborate effectively with human musicians remains limited. In this paper, we propose a framework to describe the musical interaction process, which includes expression, interpretation, and execution of controls. Following this framework, we argue that the primary gap between existing text-to-music models and musicians lies in the interpretation stage, where models lack the ability to interpret controls from musicians. We also"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10328","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/2407.10328/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":"2026-07-05T08:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n7nIB29IUjnPxLhpZe2hX9xmiOttUIsNVSE2bcRgTeeVuJls2khzw8DLW70xktaWEnczWddYDXm+cK+K9AVMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:09:15.543508Z"},"content_sha256":"0e85e0cb9b84aa7d2c78cc1ec3c4058806289eb638561e7ae98f54dc0192709a","schema_version":"1.0","event_id":"sha256:0e85e0cb9b84aa7d2c78cc1ec3c4058806289eb638561e7ae98f54dc0192709a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SI6BHRWCSM4LYYYZZHV3O6VUFU/bundle.json","state_url":"https://pith.science/pith/SI6BHRWCSM4LYYYZZHV3O6VUFU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SI6BHRWCSM4LYYYZZHV3O6VUFU/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":"2026-08-22T03:09:15Z","links":{"resolver":"https://pith.science/pith/SI6BHRWCSM4LYYYZZHV3O6VUFU","bundle":"https://pith.science/pith/SI6BHRWCSM4LYYYZZHV3O6VUFU/bundle.json","state":"https://pith.science/pith/SI6BHRWCSM4LYYYZZHV3O6VUFU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SI6BHRWCSM4LYYYZZHV3O6VUFU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SI6BHRWCSM4LYYYZZHV3O6VUFU","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":"f2260b24c9275d5cb3310c1d513a687f255d3f06c55e40283ab006c345cf2c0c","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-14T20:51:08Z","title_canon_sha256":"63547c59c6ab66d2276dee2f9843936342493b62c140e58be9c1a55d8001c8af"},"schema_version":"1.0","source":{"id":"2407.10328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10328","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10328v1","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10328","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"SI6BHRWCSM4L","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"SI6BHRWCSM4LYYYZ","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"SI6BHRWC","created_at":"2026-07-05T08:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:0e85e0cb9b84aa7d2c78cc1ec3c4058806289eb638561e7ae98f54dc0192709a","target":"graph","created_at":"2026-07-05T08:43:58Z","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/2407.10328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale text-to-music generation models have significantly enhanced music creation capabilities, offering unprecedented creative freedom. However, their ability to collaborate effectively with human musicians remains limited. In this paper, we propose a framework to describe the musical interaction process, which includes expression, interpretation, and execution of controls. Following this framework, we argue that the primary gap between existing text-to-music models and musicians lies in the interpretation stage, where models lack the ability to interpret controls from musicians. We also","authors_text":"Yixiao Zhang, Yongyi Zang","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-14T20:51:08Z","title":"The Interpretation Gap in Text-to-Music Generation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10328","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:a71a656d56f481ef9d611da44959da43804305a8f909d36361b62b2372bae1f4","target":"record","created_at":"2026-07-05T08:43:58Z","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":"f2260b24c9275d5cb3310c1d513a687f255d3f06c55e40283ab006c345cf2c0c","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-14T20:51:08Z","title_canon_sha256":"63547c59c6ab66d2276dee2f9843936342493b62c140e58be9c1a55d8001c8af"},"schema_version":"1.0","source":{"id":"2407.10328","kind":"arxiv","version":1}},"canonical_sha256":"923c13c6c29338bc6319c9ebb77ab42d015891b758887e76dbd47e9209f71f52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"923c13c6c29338bc6319c9ebb77ab42d015891b758887e76dbd47e9209f71f52","first_computed_at":"2026-07-05T08:43:58.542490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:58.542490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jJXpzpiyX8TmzJ4aedA+HxhBXlIw8P+Be04ccf82SerH5vslp1ISKci5nliM/eWqMRkGEmx7VXARVrm8VpZVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:58.542912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a71a656d56f481ef9d611da44959da43804305a8f909d36361b62b2372bae1f4","sha256:0e85e0cb9b84aa7d2c78cc1ec3c4058806289eb638561e7ae98f54dc0192709a"],"state_sha256":"d5f8b26567ced88d03193163707f3a86a27dfbb70d10fb26bebc60202b0d5a15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BA3XZfJs791mIdSqnHKABOn52rnhlHrwap//b6DbOcPPwC0BnSPYN/B8JjXQap6TfbcSqooq++0Tz/48G2EdBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T03:09:15.548187Z","bundle_sha256":"94da2cc794ef6f3b47ea2def0a6ea712293261415a47e00f1878a69969ed4a05"}}