{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7COGR35D74Z6IIUSHGKW3EQ3C5","short_pith_number":"pith:7COGR35D","canonical_record":{"source":{"id":"2112.11436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-29T11:02:24Z","cross_cats_sorted":[],"title_canon_sha256":"046d077b9a6f031ce039c62a3c3ffab87022b94c48fd34cbd95745bdd5c0f49f","abstract_canon_sha256":"d44b1914c44a66a702e682023c2e353fe5fefb812494640a674da453b6b90f47"},"schema_version":"1.0"},"canonical_sha256":"f89c68efa3ff33e4229239956d921b1757c9183e9a1576ee96f8bcd9cc2c2a76","source":{"kind":"arxiv","id":"2112.11436","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11436","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11436v1","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11436","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"pith_short_12","alias_value":"7COGR35D74Z6","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"pith_short_16","alias_value":"7COGR35D74Z6IIUS","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"pith_short_8","alias_value":"7COGR35D","created_at":"2026-07-05T03:42:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7COGR35D74Z6IIUSHGKW3EQ3C5","target":"record","payload":{"canonical_record":{"source":{"id":"2112.11436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-29T11:02:24Z","cross_cats_sorted":[],"title_canon_sha256":"046d077b9a6f031ce039c62a3c3ffab87022b94c48fd34cbd95745bdd5c0f49f","abstract_canon_sha256":"d44b1914c44a66a702e682023c2e353fe5fefb812494640a674da453b6b90f47"},"schema_version":"1.0"},"canonical_sha256":"f89c68efa3ff33e4229239956d921b1757c9183e9a1576ee96f8bcd9cc2c2a76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:57.994945Z","signature_b64":"gU/CbxO2YZz/ZTXlKptJPf1MCJ904EQkjeQqHVl0GGBJ5BOwYNYTTLuYlNBUhKgcF0CZsNJehEeInwqRwv6XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f89c68efa3ff33e4229239956d921b1757c9183e9a1576ee96f8bcd9cc2c2a76","last_reissued_at":"2026-07-05T03:42:57.994496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:57.994496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.11436","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":"2026-07-05T03:42:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GShHS6T1p8jA2R8nEeAtsJLsfFUMzOyLHLQ2ECgBlMWaLUN0DgnHma0zXV4v1U/dbv5v948OBVJYN411Hd8DDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T08:28:58.596346Z"},"content_sha256":"dedca5aafab2d32a633e8e27780cb6605e179692272a21bfc291003957e98f3d","schema_version":"1.0","event_id":"sha256:dedca5aafab2d32a633e8e27780cb6605e179692272a21bfc291003957e98f3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7COGR35D74Z6IIUSHGKW3EQ3C5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lyric document embeddings for music tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baris Dundar, Bruno Di Giorgi, Matthias Mauch, Matt Mcvicar","submitted_at":"2021-11-29T11:02:24Z","abstract_excerpt":"We present an empirical study on embedding the lyrics of a song into a fixed-dimensional feature for the purpose of music tagging. Five methods of computing token-level and four methods of computing document-level representations are trained on an industrial-scale dataset of tens of millions of songs. We compare simple averaging of pretrained embeddings to modern recurrent and attention-based neural architectures. Evaluating on a wide range of tagging tasks such as genre classification, explicit content identification and era detection, we find that averaging word embeddings outperform more co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11436","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/2112.11436/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":"2026-07-05T03:42:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tMIwDbrFjbxcw5AIWB7OWc1B/9V3tNC9KJ190LIcchIK9hFmBkracAr/AuYevuVICfvUPjRz1Ii/1dOBo45TDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T08:28:58.597200Z"},"content_sha256":"abaa7152265893dfb9ed7fcb438c8b26c380bc4454876fff5d39ca8b171fee5c","schema_version":"1.0","event_id":"sha256:abaa7152265893dfb9ed7fcb438c8b26c380bc4454876fff5d39ca8b171fee5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7COGR35D74Z6IIUSHGKW3EQ3C5/bundle.json","state_url":"https://pith.science/pith/7COGR35D74Z6IIUSHGKW3EQ3C5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7COGR35D74Z6IIUSHGKW3EQ3C5/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":"2026-08-23T08:28:58Z","links":{"resolver":"https://pith.science/pith/7COGR35D74Z6IIUSHGKW3EQ3C5","bundle":"https://pith.science/pith/7COGR35D74Z6IIUSHGKW3EQ3C5/bundle.json","state":"https://pith.science/pith/7COGR35D74Z6IIUSHGKW3EQ3C5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7COGR35D74Z6IIUSHGKW3EQ3C5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7COGR35D74Z6IIUSHGKW3EQ3C5","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":"d44b1914c44a66a702e682023c2e353fe5fefb812494640a674da453b6b90f47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-29T11:02:24Z","title_canon_sha256":"046d077b9a6f031ce039c62a3c3ffab87022b94c48fd34cbd95745bdd5c0f49f"},"schema_version":"1.0","source":{"id":"2112.11436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11436","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11436v1","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11436","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"pith_short_12","alias_value":"7COGR35D74Z6","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"pith_short_16","alias_value":"7COGR35D74Z6IIUS","created_at":"2026-07-05T03:42:57Z"},{"alias_kind":"pith_short_8","alias_value":"7COGR35D","created_at":"2026-07-05T03:42:57Z"}],"graph_snapshots":[{"event_id":"sha256:abaa7152265893dfb9ed7fcb438c8b26c380bc4454876fff5d39ca8b171fee5c","target":"graph","created_at":"2026-07-05T03:42:57Z","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/2112.11436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an empirical study on embedding the lyrics of a song into a fixed-dimensional feature for the purpose of music tagging. Five methods of computing token-level and four methods of computing document-level representations are trained on an industrial-scale dataset of tens of millions of songs. We compare simple averaging of pretrained embeddings to modern recurrent and attention-based neural architectures. Evaluating on a wide range of tagging tasks such as genre classification, explicit content identification and era detection, we find that averaging word embeddings outperform more co","authors_text":"Baris Dundar, Bruno Di Giorgi, Matthias Mauch, Matt Mcvicar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-29T11:02:24Z","title":"Lyric document embeddings for music tagging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11436","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:dedca5aafab2d32a633e8e27780cb6605e179692272a21bfc291003957e98f3d","target":"record","created_at":"2026-07-05T03:42:57Z","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":"d44b1914c44a66a702e682023c2e353fe5fefb812494640a674da453b6b90f47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-29T11:02:24Z","title_canon_sha256":"046d077b9a6f031ce039c62a3c3ffab87022b94c48fd34cbd95745bdd5c0f49f"},"schema_version":"1.0","source":{"id":"2112.11436","kind":"arxiv","version":1}},"canonical_sha256":"f89c68efa3ff33e4229239956d921b1757c9183e9a1576ee96f8bcd9cc2c2a76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f89c68efa3ff33e4229239956d921b1757c9183e9a1576ee96f8bcd9cc2c2a76","first_computed_at":"2026-07-05T03:42:57.994496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:42:57.994496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gU/CbxO2YZz/ZTXlKptJPf1MCJ904EQkjeQqHVl0GGBJ5BOwYNYTTLuYlNBUhKgcF0CZsNJehEeInwqRwv6XAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:42:57.994945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.11436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dedca5aafab2d32a633e8e27780cb6605e179692272a21bfc291003957e98f3d","sha256:abaa7152265893dfb9ed7fcb438c8b26c380bc4454876fff5d39ca8b171fee5c"],"state_sha256":"acd6b6695507e4caaf39b8cc07daa80b48a0bae8486a1f32d46130824d03b351"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0DGn3d6ZCgwDvZKfmNeWv3cG9CXrAUzXCdOkXRPcvH7NumR2qU/M3YTtYvsvjbfIv9RFHVzuQ1pIoYxmu4yAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T08:28:58.603426Z","bundle_sha256":"e998aa2f720fa1d4100d37d73c34f0f2e8a788b78fe9fbdb748a25dd6758b04a"}}