{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5WMAHDIHTPTB2FTPP5NBIAY2WO","short_pith_number":"pith:5WMAHDIH","canonical_record":{"source":{"id":"2407.20445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-29T22:53:32Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"381d643146218100c3ce534298590e6076042301fbc06e739b13d59fe7f7b39b","abstract_canon_sha256":"aa2d84a5941ded15806a722b78989c1b7dfdd9b61cd4107d91d281777df63cf5"},"schema_version":"1.0"},"canonical_sha256":"ed98038d079be61d166f7f5a14031ab397e3ad4838eeca11a631d7b34095bfaa","source":{"kind":"arxiv","id":"2407.20445","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20445","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20445v1","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20445","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"5WMAHDIHTPTB","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"5WMAHDIHTPTB2FTP","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"5WMAHDIH","created_at":"2026-07-05T08:49:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5WMAHDIHTPTB2FTPP5NBIAY2WO","target":"record","payload":{"canonical_record":{"source":{"id":"2407.20445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-29T22:53:32Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"381d643146218100c3ce534298590e6076042301fbc06e739b13d59fe7f7b39b","abstract_canon_sha256":"aa2d84a5941ded15806a722b78989c1b7dfdd9b61cd4107d91d281777df63cf5"},"schema_version":"1.0"},"canonical_sha256":"ed98038d079be61d166f7f5a14031ab397e3ad4838eeca11a631d7b34095bfaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:58.015086Z","signature_b64":"QXrBtygDqXmQEDNJFygkOqXg9oXzs25SNGnRVsVOekMZm+U3aKeQCnIMCo5O6OpgRA1rY4519CZG1XUDEdAzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed98038d079be61d166f7f5a14031ab397e3ad4838eeca11a631d7b34095bfaa","last_reissued_at":"2026-07-05T08:49:58.014615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:58.014615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.20445","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":"2026-07-05T08:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"daUDk6RhjIZkOoV/naDZ339+kfuqqsPY4EfT/14FFAh7jWc0aPMe6M2VSKDM1u/kTUK3xP8NS0qUmMiFZ1KnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:03:54.214914Z"},"content_sha256":"6af2b314469918cd76e96b2535276af583bea9fb150eab50ed71bb29ac7a6a0f","schema_version":"1.0","event_id":"sha256:6af2b314469918cd76e96b2535276af583bea9fb150eab50ed71bb29ac7a6a0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5WMAHDIHTPTB2FTPP5NBIAY2WO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Futga: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Amit Namburi, Carol Chen, Hao-Wen Dong, Jiaheng Dai, Julian McAuley, Junda Wu, Zachary Novack, Zhouhang Xie","submitted_at":"2024-07-29T22:53:32Z","abstract_excerpt":"Existing music captioning methods are limited to generating concise global descriptions of short music clips, which fail to capture fine-grained musical characteristics and time-aware musical changes. To address these limitations, we propose FUTGA, a model equipped with fined-grained music understanding capabilities through learning from generative augmentation with temporal compositions. We leverage existing music caption datasets and large language models (LLMs) to synthesize fine-grained music captions with structural descriptions and time boundaries for full-length songs. Augmented by the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20445","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/2407.20445/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":"2026-07-05T08:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjeQkl1kFEPWMCNZnlViGOqNGVrPUM3wcPRN9teXuy3s9uGoiEm3FQKodczH3qqPhmM7FRdcULSEs0+Mc11SDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:03:54.215413Z"},"content_sha256":"100520cd7a6d67f077cce59494bb8f38b9c935216f1ffe31da772d0cec5d200e","schema_version":"1.0","event_id":"sha256:100520cd7a6d67f077cce59494bb8f38b9c935216f1ffe31da772d0cec5d200e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WMAHDIHTPTB2FTPP5NBIAY2WO/bundle.json","state_url":"https://pith.science/pith/5WMAHDIHTPTB2FTPP5NBIAY2WO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WMAHDIHTPTB2FTPP5NBIAY2WO/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":"2026-08-22T18:03:54Z","links":{"resolver":"https://pith.science/pith/5WMAHDIHTPTB2FTPP5NBIAY2WO","bundle":"https://pith.science/pith/5WMAHDIHTPTB2FTPP5NBIAY2WO/bundle.json","state":"https://pith.science/pith/5WMAHDIHTPTB2FTPP5NBIAY2WO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WMAHDIHTPTB2FTPP5NBIAY2WO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5WMAHDIHTPTB2FTPP5NBIAY2WO","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":"aa2d84a5941ded15806a722b78989c1b7dfdd9b61cd4107d91d281777df63cf5","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-29T22:53:32Z","title_canon_sha256":"381d643146218100c3ce534298590e6076042301fbc06e739b13d59fe7f7b39b"},"schema_version":"1.0","source":{"id":"2407.20445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20445","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20445v1","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20445","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"5WMAHDIHTPTB","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"5WMAHDIHTPTB2FTP","created_at":"2026-07-05T08:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"5WMAHDIH","created_at":"2026-07-05T08:49:58Z"}],"graph_snapshots":[{"event_id":"sha256:100520cd7a6d67f077cce59494bb8f38b9c935216f1ffe31da772d0cec5d200e","target":"graph","created_at":"2026-07-05T08:49:58Z","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/2407.20445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing music captioning methods are limited to generating concise global descriptions of short music clips, which fail to capture fine-grained musical characteristics and time-aware musical changes. To address these limitations, we propose FUTGA, a model equipped with fined-grained music understanding capabilities through learning from generative augmentation with temporal compositions. We leverage existing music caption datasets and large language models (LLMs) to synthesize fine-grained music captions with structural descriptions and time boundaries for full-length songs. Augmented by the ","authors_text":"Amit Namburi, Carol Chen, Hao-Wen Dong, Jiaheng Dai, Julian McAuley, Junda Wu, Zachary Novack, Zhouhang Xie","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-29T22:53:32Z","title":"Futga: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20445","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":"sha256:6af2b314469918cd76e96b2535276af583bea9fb150eab50ed71bb29ac7a6a0f","target":"record","created_at":"2026-07-05T08:49:58Z","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":"aa2d84a5941ded15806a722b78989c1b7dfdd9b61cd4107d91d281777df63cf5","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-29T22:53:32Z","title_canon_sha256":"381d643146218100c3ce534298590e6076042301fbc06e739b13d59fe7f7b39b"},"schema_version":"1.0","source":{"id":"2407.20445","kind":"arxiv","version":1}},"canonical_sha256":"ed98038d079be61d166f7f5a14031ab397e3ad4838eeca11a631d7b34095bfaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed98038d079be61d166f7f5a14031ab397e3ad4838eeca11a631d7b34095bfaa","first_computed_at":"2026-07-05T08:49:58.014615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:58.014615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QXrBtygDqXmQEDNJFygkOqXg9oXzs25SNGnRVsVOekMZm+U3aKeQCnIMCo5O6OpgRA1rY4519CZG1XUDEdAzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:58.015086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6af2b314469918cd76e96b2535276af583bea9fb150eab50ed71bb29ac7a6a0f","sha256:100520cd7a6d67f077cce59494bb8f38b9c935216f1ffe31da772d0cec5d200e"],"state_sha256":"813469f9cce5a48fc34cf82e14b5f828351db3cb999c0353bf6dc721f1ebfb0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"beTWwtbLBgJYlqomPwFW/6un6jsF0IKAsrEbaQVhUmf/w36vQXaiod03Kc8FM0Lq5Xt69MbNz4GrS8s/7OQjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T18:03:54.220075Z","bundle_sha256":"29d98d6c22c3cd7829a03e77d227d410f7bd719b8b96571bee1a43857b62d343"}}