{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZUA73UCXZDFA645FECOTBR7S42","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":"fb0da88fb464a5a592dabb34250b2033d4b9a8100a2a5c50d28a2b0a0ea29cb0","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-18T09:30:58Z","title_canon_sha256":"9896facb0267b59fee07fe29ad7bd37ba794e9bbf7e6c5dae80acb929e88045a"},"schema_version":"1.0","source":{"id":"2110.09127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09127","created_at":"2026-07-05T03:25:18Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09127v1","created_at":"2026-07-05T03:25:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09127","created_at":"2026-07-05T03:25:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZUA73UCXZDFA","created_at":"2026-07-05T03:25:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZUA73UCXZDFA645F","created_at":"2026-07-05T03:25:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZUA73UCX","created_at":"2026-07-05T03:25:18Z"}],"graph_snapshots":[{"event_id":"sha256:68ddaeb927a600acaa0de22d69376ddea1ea6ae1310b977fd4c4c213cbb2707d","target":"graph","created_at":"2026-07-05T03:25:18Z","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/2110.09127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers have drawn attention in the MIR field for their remarkable performance shown in natural language processing and computer vision. However, prior works in the audio processing domain mostly use Transformer as a temporal feature aggregator that acts similar to RNNs. In this paper, we propose SpecTNT, a Transformer-based architecture to model both spectral and temporal sequences of an input time-frequency representation. Specifically, we introduce a novel variant of the Transformer-in-Transformer (TNT) architecture. In each SpecTNT block, a spectral Transformer extracts frequency-rela","authors_text":"Ju-Chiang Wang, Keunwoo Choi, Minz Won, Wei-Tsung Lu, Xuchen Song","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-18T09:30:58Z","title":"SpecTNT: a Time-Frequency Transformer for Music Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09127","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:b7f5a6b029c56b8e44f3ec9f9386222089c1a8b006529bf8413a18ebdc4ee1d0","target":"record","created_at":"2026-07-05T03:25:18Z","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":"fb0da88fb464a5a592dabb34250b2033d4b9a8100a2a5c50d28a2b0a0ea29cb0","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-18T09:30:58Z","title_canon_sha256":"9896facb0267b59fee07fe29ad7bd37ba794e9bbf7e6c5dae80acb929e88045a"},"schema_version":"1.0","source":{"id":"2110.09127","kind":"arxiv","version":1}},"canonical_sha256":"cd01fdd057c8ca0f73a5209d30c7f2e6a2b8ab2e9eefc70faac4909c32fcefb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd01fdd057c8ca0f73a5209d30c7f2e6a2b8ab2e9eefc70faac4909c32fcefb1","first_computed_at":"2026-07-05T03:25:18.205496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:18.205496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kq9dr32gCidHilwBcQlUXFEh7VJKS4C133+Pa1dYqz1xBCUEiDGb0EnX6A+nZi/aEIotjmoPYkAZqIsKlX31Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:18.205993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.09127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7f5a6b029c56b8e44f3ec9f9386222089c1a8b006529bf8413a18ebdc4ee1d0","sha256:68ddaeb927a600acaa0de22d69376ddea1ea6ae1310b977fd4c4c213cbb2707d"],"state_sha256":"20c7dca159da733a31d8fea481c30b47c4aefc05a1eb089b7686170b9cb032fa"}