{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KLE5Y7OZZCJEVBCF63GG3JDGS7","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":"47aae3c8acf4eb43c492d287f268b19a1437bbddc7a4f9b07a5db867bc4c7efe","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-05-29T16:01:39Z","title_canon_sha256":"af3dca45ab6ed0f0bd4f925a1ca291dd09051289fd31878a0c56dfe0bc02f327"},"schema_version":"1.0","source":{"id":"2205.14701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14701","created_at":"2026-07-05T04:27:20Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14701v1","created_at":"2026-07-05T04:27:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14701","created_at":"2026-07-05T04:27:20Z"},{"alias_kind":"pith_short_12","alias_value":"KLE5Y7OZZCJE","created_at":"2026-07-05T04:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"KLE5Y7OZZCJEVBCF","created_at":"2026-07-05T04:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"KLE5Y7OZ","created_at":"2026-07-05T04:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:61c329ba47977488637ad4a245d7c1a7ba216bb88c3f922b543b76d99befb51a","target":"graph","created_at":"2026-07-05T04:27:20Z","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/2205.14701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer is a successful deep neural network (DNN) architecture that has shown its versatility not only in natural language processing but also in music information retrieval (MIR). In this paper, we present a novel Transformer-based approach to tackle beat and downbeat tracking. This approach employs SpecTNT (Spectral-Temporal Transformer in Transformer), a variant of Transformer that models both spectral and temporal dimensions of a time-frequency input of music audio. A SpecTNT model uses a stack of blocks, where each consists of two levels of Transformer encoders. The lower-level (or sp","authors_text":"Ju-Chiang Wang, Minz Won, Wei-Tsung Lu, Xuchen Song, Yun-Ning Hung","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-05-29T16:01:39Z","title":"Modeling Beats and Downbeats with a Time-Frequency Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14701","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":"sha256:59ca0dc35f2655af1c7979ce0e7204ccb9b1229086d86c97658b87570286031c","target":"record","created_at":"2026-07-05T04:27:20Z","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":"47aae3c8acf4eb43c492d287f268b19a1437bbddc7a4f9b07a5db867bc4c7efe","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-05-29T16:01:39Z","title_canon_sha256":"af3dca45ab6ed0f0bd4f925a1ca291dd09051289fd31878a0c56dfe0bc02f327"},"schema_version":"1.0","source":{"id":"2205.14701","kind":"arxiv","version":1}},"canonical_sha256":"52c9dc7dd9c8924a8445f6cc6da46697d01b9834c49e8b76d78231944f65bd9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52c9dc7dd9c8924a8445f6cc6da46697d01b9834c49e8b76d78231944f65bd9b","first_computed_at":"2026-07-05T04:27:20.551885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:20.551885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hyIaQNO/oAFUm9rzCuqiF/n5H0jg7esNZ99JyhqnNXNPhzMkIqPGq3evkGFta7zHH5QhMQmfp8l5ffG27GF+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:20.552289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59ca0dc35f2655af1c7979ce0e7204ccb9b1229086d86c97658b87570286031c","sha256:61c329ba47977488637ad4a245d7c1a7ba216bb88c3f922b543b76d99befb51a"],"state_sha256":"6ce5107738da70bee8a5d7d729b96bdf2c8ba458800088ffa766aac803309652"}