{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VCU36OMEDDC7OGMMGMUJRB7XY3","short_pith_number":"pith:VCU36OME","canonical_record":{"source":{"id":"2212.10901","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-12-21T10:20:54Z","cross_cats_sorted":["cs.CL","cs.IR","cs.MM","eess.AS"],"title_canon_sha256":"aba137dd6c06299db3973170e63b7ad964f281c47eb16ae3d73d451a5335c2d9","abstract_canon_sha256":"61292cf3a1627948c93ba04a1a5f4138e57ffaa689790cb6fbdd4da4436c88c7"},"schema_version":"1.0"},"canonical_sha256":"a8a9bf398418c5f7198c33289887f7c6e38520955b911a24be74b2598af6be79","source":{"kind":"arxiv","id":"2212.10901","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10901","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10901v3","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10901","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"VCU36OMEDDC7","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"VCU36OMEDDC7OGMM","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"VCU36OME","created_at":"2026-07-05T07:03:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VCU36OMEDDC7OGMMGMUJRB7XY3","target":"record","payload":{"canonical_record":{"source":{"id":"2212.10901","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-12-21T10:20:54Z","cross_cats_sorted":["cs.CL","cs.IR","cs.MM","eess.AS"],"title_canon_sha256":"aba137dd6c06299db3973170e63b7ad964f281c47eb16ae3d73d451a5335c2d9","abstract_canon_sha256":"61292cf3a1627948c93ba04a1a5f4138e57ffaa689790cb6fbdd4da4436c88c7"},"schema_version":"1.0"},"canonical_sha256":"a8a9bf398418c5f7198c33289887f7c6e38520955b911a24be74b2598af6be79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:19.971757Z","signature_b64":"U+4uqZ38Wj7TR7LCK5g+WxKWCiTa0ph7w+65JlpmJPGtM4E5TWNipyoHeaJJnC6ygbsPfjZ5XCb4MdRQTAFABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8a9bf398418c5f7198c33289887f7c6e38520955b911a24be74b2598af6be79","last_reissued_at":"2026-07-05T07:03:19.971274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:19.971274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.10901","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":"2026-07-05T07:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WmcXCR43TShVIXzvXA0QJWooMEBmx51buM+B9V4+pdLSNbs+/ezbT8Y8cIPvjLiY17UHN25LDUn7XBzIgQHjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:46:06.791751Z"},"content_sha256":"4d690a0968c0ef8259799da8b9248b5591e6ae900d315cc7c4240cb977f83928","schema_version":"1.0","event_id":"sha256:4d690a0968c0ef8259799da8b9248b5591e6ae900d315cc7c4240cb977f83928"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VCU36OMEDDC7OGMMGMUJRB7XY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ALCAP: Alignment-Augmented Music Captioner","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Changyou Chen, Kristina Lerman, Wei-Tsung Lu, Weituo Hao, Xuchen Song, Zihao He","submitted_at":"2022-12-21T10:20:54Z","abstract_excerpt":"Music captioning has gained significant attention in the wake of the rising prominence of streaming media platforms. Traditional approaches often prioritize either the audio or lyrics aspect of the music, inadvertently ignoring the intricate interplay between the two. However, a comprehensive understanding of music necessitates the integration of both these elements. In this study, we delve into this overlooked realm by introducing a method to systematically learn multimodal alignment between audio and lyrics through contrastive learning. This not only recognizes and emphasizes the synergy bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10901","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/2212.10901/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":"2026-07-05T07:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cIM6xpmy3XbHwPoIj7WqTRNeEbBVTMeMNXqY1FJ6vAoe3QHU6KVjrjmYB07UtUyZtiDQQIuxJdVCN0cNxcfQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:46:06.792141Z"},"content_sha256":"2b597adefd06bff8a181d5001dd618a1574bd4f7095ebb7738d9ab5f6a75c1b2","schema_version":"1.0","event_id":"sha256:2b597adefd06bff8a181d5001dd618a1574bd4f7095ebb7738d9ab5f6a75c1b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VCU36OMEDDC7OGMMGMUJRB7XY3/bundle.json","state_url":"https://pith.science/pith/VCU36OMEDDC7OGMMGMUJRB7XY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VCU36OMEDDC7OGMMGMUJRB7XY3/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":"2026-07-09T06:46:06Z","links":{"resolver":"https://pith.science/pith/VCU36OMEDDC7OGMMGMUJRB7XY3","bundle":"https://pith.science/pith/VCU36OMEDDC7OGMMGMUJRB7XY3/bundle.json","state":"https://pith.science/pith/VCU36OMEDDC7OGMMGMUJRB7XY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VCU36OMEDDC7OGMMGMUJRB7XY3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VCU36OMEDDC7OGMMGMUJRB7XY3","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":"61292cf3a1627948c93ba04a1a5f4138e57ffaa689790cb6fbdd4da4436c88c7","cross_cats_sorted":["cs.CL","cs.IR","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-12-21T10:20:54Z","title_canon_sha256":"aba137dd6c06299db3973170e63b7ad964f281c47eb16ae3d73d451a5335c2d9"},"schema_version":"1.0","source":{"id":"2212.10901","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10901","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10901v3","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10901","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"VCU36OMEDDC7","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"VCU36OMEDDC7OGMM","created_at":"2026-07-05T07:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"VCU36OME","created_at":"2026-07-05T07:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:2b597adefd06bff8a181d5001dd618a1574bd4f7095ebb7738d9ab5f6a75c1b2","target":"graph","created_at":"2026-07-05T07:03:19Z","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/2212.10901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Music captioning has gained significant attention in the wake of the rising prominence of streaming media platforms. Traditional approaches often prioritize either the audio or lyrics aspect of the music, inadvertently ignoring the intricate interplay between the two. However, a comprehensive understanding of music necessitates the integration of both these elements. In this study, we delve into this overlooked realm by introducing a method to systematically learn multimodal alignment between audio and lyrics through contrastive learning. This not only recognizes and emphasizes the synergy bet","authors_text":"Changyou Chen, Kristina Lerman, Wei-Tsung Lu, Weituo Hao, Xuchen Song, Zihao He","cross_cats":["cs.CL","cs.IR","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-12-21T10:20:54Z","title":"ALCAP: Alignment-Augmented Music Captioner"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10901","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":"sha256:4d690a0968c0ef8259799da8b9248b5591e6ae900d315cc7c4240cb977f83928","target":"record","created_at":"2026-07-05T07:03:19Z","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":"61292cf3a1627948c93ba04a1a5f4138e57ffaa689790cb6fbdd4da4436c88c7","cross_cats_sorted":["cs.CL","cs.IR","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-12-21T10:20:54Z","title_canon_sha256":"aba137dd6c06299db3973170e63b7ad964f281c47eb16ae3d73d451a5335c2d9"},"schema_version":"1.0","source":{"id":"2212.10901","kind":"arxiv","version":3}},"canonical_sha256":"a8a9bf398418c5f7198c33289887f7c6e38520955b911a24be74b2598af6be79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8a9bf398418c5f7198c33289887f7c6e38520955b911a24be74b2598af6be79","first_computed_at":"2026-07-05T07:03:19.971274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:19.971274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U+4uqZ38Wj7TR7LCK5g+WxKWCiTa0ph7w+65JlpmJPGtM4E5TWNipyoHeaJJnC6ygbsPfjZ5XCb4MdRQTAFABg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:19.971757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10901","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d690a0968c0ef8259799da8b9248b5591e6ae900d315cc7c4240cb977f83928","sha256:2b597adefd06bff8a181d5001dd618a1574bd4f7095ebb7738d9ab5f6a75c1b2"],"state_sha256":"d099b9db80325a149ef9ec8befac5ae10aad921d56f7e272c5c396d2bf6b033e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RxsvxR0jsD3E0sYUVRVmXb8gutkHv1hmdUHGHq+YtEMYXkK1NzOtYp127S5BW2scxNDw7UTddaZeSoWiODrIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:46:06.795146Z","bundle_sha256":"c99de58aa6124aaad7918d048359d0838796fa40003f4b682b80998179f5aece"}}