{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CZDID7XJV7B4LMJWEHUHAFHQQQ","short_pith_number":"pith:CZDID7XJ","canonical_record":{"source":{"id":"1711.08976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-24T14:21:46Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3d123fe9862ed1a058ccf95dea5326120c76ba615e6eeada0ca369ac11cb5393","abstract_canon_sha256":"e2d15670443b3358793376d1213441efdc9be1325bc3c8a38aa7796da8920268"},"schema_version":"1.0"},"canonical_sha256":"164681fee9afc3c5b13621e87014f0841ba6eda4d5c15f11ba7bb558f8a97d08","source":{"kind":"arxiv","id":"1711.08976","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08976","created_at":"2026-05-18T00:29:17Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08976v2","created_at":"2026-05-18T00:29:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08976","created_at":"2026-05-18T00:29:17Z"},{"alias_kind":"pith_short_12","alias_value":"CZDID7XJV7B4","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CZDID7XJV7B4LMJW","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CZDID7XJ","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CZDID7XJV7B4LMJWEHUHAFHQQQ","target":"record","payload":{"canonical_record":{"source":{"id":"1711.08976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-24T14:21:46Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3d123fe9862ed1a058ccf95dea5326120c76ba615e6eeada0ca369ac11cb5393","abstract_canon_sha256":"e2d15670443b3358793376d1213441efdc9be1325bc3c8a38aa7796da8920268"},"schema_version":"1.0"},"canonical_sha256":"164681fee9afc3c5b13621e87014f0841ba6eda4d5c15f11ba7bb558f8a97d08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:17.953695Z","signature_b64":"qGbBtjIhCvD488acglbINKJxo5CsTTSLYiIAHmZ5a2Nfz4XACdE7IyyfxqBZnXaLcqRWZETLubf4G7edBUZdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"164681fee9afc3c5b13621e87014f0841ba6eda4d5c15f11ba7bb558f8a97d08","last_reissued_at":"2026-05-18T00:29:17.953030Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:17.953030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.08976","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:29:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jCwzeZ8r13fmUW/8o7oSOyHvWkgO1Y58gqjW2IzJrczlySCOaO/iQqt07KSzqIvHmva7jhh3hOUTASe7Um1ECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:10:48.670598Z"},"content_sha256":"abdcd1f850666b22b925f4e0db7a6dc220af9b31709c19abb04a09c4dbb00b6b","schema_version":"1.0","event_id":"sha256:abdcd1f850666b22b925f4e0db7a6dc220af9b31709c19abb04a09c4dbb00b6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CZDID7XJV7B4LMJWEHUHAFHQQQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Cross-Modal Correlation Learning for Audio and Lyrics in Music Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.IR","authors_text":"Francisco Raposo, Lei Chen, Suhua Tang, Yi Yu","submitted_at":"2017-11-24T14:21:46Z","abstract_excerpt":"Little research focuses on cross-modal correlation learning where temporal structures of different data modalities such as audio and lyrics are taken into account. Stemming from the characteristic of temporal structures of music in nature, we are motivated to learn the deep sequential correlation between audio and lyrics. In this work, we propose a deep cross-modal correlation learning architecture involving two-branch deep neural networks for audio modality and text modality (lyrics). Different modality data are converted to the same canonical space where inter modal canonical correlation ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08976","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:29:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ptRNgzBbrLbx/RNVtjmsVux+5crUsWqvsIoozAD+uQEzjJR9ytpOtdiG48IThwWB2phZ06rNhohkBzIoouFEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:10:48.670943Z"},"content_sha256":"6981c5c017ad4a6d85bafea64a6d846417866fd9373aa60d2f52dfe8576caa43","schema_version":"1.0","event_id":"sha256:6981c5c017ad4a6d85bafea64a6d846417866fd9373aa60d2f52dfe8576caa43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZDID7XJV7B4LMJWEHUHAFHQQQ/bundle.json","state_url":"https://pith.science/pith/CZDID7XJV7B4LMJWEHUHAFHQQQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZDID7XJV7B4LMJWEHUHAFHQQQ/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":"2026-06-02T11:10:48Z","links":{"resolver":"https://pith.science/pith/CZDID7XJV7B4LMJWEHUHAFHQQQ","bundle":"https://pith.science/pith/CZDID7XJV7B4LMJWEHUHAFHQQQ/bundle.json","state":"https://pith.science/pith/CZDID7XJV7B4LMJWEHUHAFHQQQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZDID7XJV7B4LMJWEHUHAFHQQQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CZDID7XJV7B4LMJWEHUHAFHQQQ","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":"e2d15670443b3358793376d1213441efdc9be1325bc3c8a38aa7796da8920268","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-24T14:21:46Z","title_canon_sha256":"3d123fe9862ed1a058ccf95dea5326120c76ba615e6eeada0ca369ac11cb5393"},"schema_version":"1.0","source":{"id":"1711.08976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08976","created_at":"2026-05-18T00:29:17Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08976v2","created_at":"2026-05-18T00:29:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08976","created_at":"2026-05-18T00:29:17Z"},{"alias_kind":"pith_short_12","alias_value":"CZDID7XJV7B4","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CZDID7XJV7B4LMJW","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CZDID7XJ","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:6981c5c017ad4a6d85bafea64a6d846417866fd9373aa60d2f52dfe8576caa43","target":"graph","created_at":"2026-05-18T00:29:17Z","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"},"paper":{"abstract_excerpt":"Little research focuses on cross-modal correlation learning where temporal structures of different data modalities such as audio and lyrics are taken into account. Stemming from the characteristic of temporal structures of music in nature, we are motivated to learn the deep sequential correlation between audio and lyrics. In this work, we propose a deep cross-modal correlation learning architecture involving two-branch deep neural networks for audio modality and text modality (lyrics). Different modality data are converted to the same canonical space where inter modal canonical correlation ana","authors_text":"Francisco Raposo, Lei Chen, Suhua Tang, Yi Yu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-24T14:21:46Z","title":"Deep Cross-Modal Correlation Learning for Audio and Lyrics in Music Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08976","kind":"arxiv","version":2},"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:abdcd1f850666b22b925f4e0db7a6dc220af9b31709c19abb04a09c4dbb00b6b","target":"record","created_at":"2026-05-18T00:29:17Z","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":"e2d15670443b3358793376d1213441efdc9be1325bc3c8a38aa7796da8920268","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-11-24T14:21:46Z","title_canon_sha256":"3d123fe9862ed1a058ccf95dea5326120c76ba615e6eeada0ca369ac11cb5393"},"schema_version":"1.0","source":{"id":"1711.08976","kind":"arxiv","version":2}},"canonical_sha256":"164681fee9afc3c5b13621e87014f0841ba6eda4d5c15f11ba7bb558f8a97d08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"164681fee9afc3c5b13621e87014f0841ba6eda4d5c15f11ba7bb558f8a97d08","first_computed_at":"2026-05-18T00:29:17.953030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:17.953030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qGbBtjIhCvD488acglbINKJxo5CsTTSLYiIAHmZ5a2Nfz4XACdE7IyyfxqBZnXaLcqRWZETLubf4G7edBUZdBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:17.953695Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.08976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abdcd1f850666b22b925f4e0db7a6dc220af9b31709c19abb04a09c4dbb00b6b","sha256:6981c5c017ad4a6d85bafea64a6d846417866fd9373aa60d2f52dfe8576caa43"],"state_sha256":"8ee5eec98917566911b35b07b7a66462338cb282c933be00637b6b3200b1500f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZcnREOYrLA1nSmfpxFMd0lt598cVeNyu6RpZ/b+zmt8R1g1sODSA/Gibrf7bZtACQY6BxOXV4RslTM0hbH1sDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T11:10:48.672991Z","bundle_sha256":"a56bf4682943e531cf455e21b74e1d6b3839dd288925935561fec2f3adb22ac4"}}