{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EANOUWYXV637CL3VOVNXZE4GVM","short_pith_number":"pith:EANOUWYX","canonical_record":{"source":{"id":"2409.11498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-17T19:00:21Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"981fb9b30be03632baa2fd08affb7bf88344bdeefef3269718811f9b7b3b7e06","abstract_canon_sha256":"5230915165b508ccd598ed07fc5103f80806742deaf96b148f3ea2c9b00f4c0e"},"schema_version":"1.0"},"canonical_sha256":"201aea5b17afb7f12f75755b7c9386ab1c4a400a9b862e2d2ea9f38be0ef9a1e","source":{"kind":"arxiv","id":"2409.11498","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11498","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11498v1","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11498","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"EANOUWYXV637","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"EANOUWYXV637CL3V","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"EANOUWYX","created_at":"2026-07-05T09:08:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EANOUWYXV637CL3VOVNXZE4GVM","target":"record","payload":{"canonical_record":{"source":{"id":"2409.11498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-17T19:00:21Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"981fb9b30be03632baa2fd08affb7bf88344bdeefef3269718811f9b7b3b7e06","abstract_canon_sha256":"5230915165b508ccd598ed07fc5103f80806742deaf96b148f3ea2c9b00f4c0e"},"schema_version":"1.0"},"canonical_sha256":"201aea5b17afb7f12f75755b7c9386ab1c4a400a9b862e2d2ea9f38be0ef9a1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:32.468602Z","signature_b64":"KwE28htFKnBsk3Si/nJZwr/5zGqFBGNk5YpA2A0WY/1sDIw0alu5yfMC24EeREKyJw8Qot4XSqxA9Sb+BtDLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"201aea5b17afb7f12f75755b7c9386ab1c4a400a9b862e2d2ea9f38be0ef9a1e","last_reissued_at":"2026-07-05T09:08:32.468099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:32.468099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.11498","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":"2026-07-05T09:08:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4AmrdFRjjKHVrViw/LxfdQd52QXs+326ZUnovNhPQ7onaGatdfq9OE28qcr/luioWd4Y6HaPsPWhFBW2g1rNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:59:41.633488Z"},"content_sha256":"4f382e6591cbf5ae7416e4e4538350d5a26b42ffa95e2f973b913dc6366fc841","schema_version":"1.0","event_id":"sha256:4f382e6591cbf5ae7416e4e4538350d5a26b42ffa95e2f973b913dc6366fc841"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EANOUWYXV637CL3VOVNXZE4GVM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ilaria Manco, Justin Salamon, Oriol Nieto","submitted_at":"2024-09-17T19:00:21Z","abstract_excerpt":"Audio-text contrastive models have become a powerful approach in music representation learning. Despite their empirical success, however, little is known about the influence of key design choices on the quality of music-text representations learnt through this framework. In this work, we expose these design choices within the constraints of limited data and computation budgets, and establish a more solid understanding of their impact grounded in empirical observations along three axes: the choice of base encoders, the level of curation in training data, and the use of text augmentation. We fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11498","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/2409.11498/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":"2026-07-05T09:08:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oESw+Bkgnz5YcQAmOJ33Z6SfyJyh8XlDgASXhE+xEycl4HcACt/VmXV0I/ZDX7esuGDR0kSdnyOGo4J7Ly56CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:59:41.634011Z"},"content_sha256":"0ee2fe779f7d883c9656cb73d8f884288a23dad712b857e3c5f9dd11f2c4388d","schema_version":"1.0","event_id":"sha256:0ee2fe779f7d883c9656cb73d8f884288a23dad712b857e3c5f9dd11f2c4388d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EANOUWYXV637CL3VOVNXZE4GVM/bundle.json","state_url":"https://pith.science/pith/EANOUWYXV637CL3VOVNXZE4GVM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EANOUWYXV637CL3VOVNXZE4GVM/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":"2026-08-01T09:59:41Z","links":{"resolver":"https://pith.science/pith/EANOUWYXV637CL3VOVNXZE4GVM","bundle":"https://pith.science/pith/EANOUWYXV637CL3VOVNXZE4GVM/bundle.json","state":"https://pith.science/pith/EANOUWYXV637CL3VOVNXZE4GVM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EANOUWYXV637CL3VOVNXZE4GVM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EANOUWYXV637CL3VOVNXZE4GVM","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":"5230915165b508ccd598ed07fc5103f80806742deaf96b148f3ea2c9b00f4c0e","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-17T19:00:21Z","title_canon_sha256":"981fb9b30be03632baa2fd08affb7bf88344bdeefef3269718811f9b7b3b7e06"},"schema_version":"1.0","source":{"id":"2409.11498","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11498","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11498v1","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11498","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"EANOUWYXV637","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"EANOUWYXV637CL3V","created_at":"2026-07-05T09:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"EANOUWYX","created_at":"2026-07-05T09:08:32Z"}],"graph_snapshots":[{"event_id":"sha256:0ee2fe779f7d883c9656cb73d8f884288a23dad712b857e3c5f9dd11f2c4388d","target":"graph","created_at":"2026-07-05T09:08:32Z","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/2409.11498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-text contrastive models have become a powerful approach in music representation learning. Despite their empirical success, however, little is known about the influence of key design choices on the quality of music-text representations learnt through this framework. In this work, we expose these design choices within the constraints of limited data and computation budgets, and establish a more solid understanding of their impact grounded in empirical observations along three axes: the choice of base encoders, the level of curation in training data, and the use of text augmentation. We fin","authors_text":"Ilaria Manco, Justin Salamon, Oriol Nieto","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-17T19:00:21Z","title":"Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11498","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":"sha256:4f382e6591cbf5ae7416e4e4538350d5a26b42ffa95e2f973b913dc6366fc841","target":"record","created_at":"2026-07-05T09:08:32Z","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":"5230915165b508ccd598ed07fc5103f80806742deaf96b148f3ea2c9b00f4c0e","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-17T19:00:21Z","title_canon_sha256":"981fb9b30be03632baa2fd08affb7bf88344bdeefef3269718811f9b7b3b7e06"},"schema_version":"1.0","source":{"id":"2409.11498","kind":"arxiv","version":1}},"canonical_sha256":"201aea5b17afb7f12f75755b7c9386ab1c4a400a9b862e2d2ea9f38be0ef9a1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"201aea5b17afb7f12f75755b7c9386ab1c4a400a9b862e2d2ea9f38be0ef9a1e","first_computed_at":"2026-07-05T09:08:32.468099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:32.468099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KwE28htFKnBsk3Si/nJZwr/5zGqFBGNk5YpA2A0WY/1sDIw0alu5yfMC24EeREKyJw8Qot4XSqxA9Sb+BtDLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:32.468602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11498","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f382e6591cbf5ae7416e4e4538350d5a26b42ffa95e2f973b913dc6366fc841","sha256:0ee2fe779f7d883c9656cb73d8f884288a23dad712b857e3c5f9dd11f2c4388d"],"state_sha256":"69607aaed0c6f980989ebf1da7db1d0d4f0e31a75c287435b43cc7a0b3726bc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EIKIZ3feYQxyfDHqZL81tiwWFtzV3SPVt/VoxvhJZF58PnqwE6LXachGVEEUeD7ayr7AEmfjaWNMSTpiWkD0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T09:59:41.637347Z","bundle_sha256":"0cbbdccf489e55befec2d4189e5dd1e6c36cc744c048881b6e763a490ba8a19c"}}