{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XMN4YCUBROLMGUERYZRNXPAXKS","short_pith_number":"pith:XMN4YCUB","canonical_record":{"source":{"id":"2306.10785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-19T08:58:26Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"c4ee0750416e67fbb412503563ec8c1837329b2207a265abe04d388334ed48a4","abstract_canon_sha256":"54b0c72db088972b16ffb932d7259183b1c618630476eb1341a7594f1ed024a2"},"schema_version":"1.0"},"canonical_sha256":"bb1bcc0a818b96c35091c662dbbc1754b6ef7c8060bbbdcec58fb4bb2e11f09e","source":{"kind":"arxiv","id":"2306.10785","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10785","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10785v1","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10785","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"XMN4YCUBROLM","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"XMN4YCUBROLMGUER","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"XMN4YCUB","created_at":"2026-07-05T06:22:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XMN4YCUBROLMGUERYZRNXPAXKS","target":"record","payload":{"canonical_record":{"source":{"id":"2306.10785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-19T08:58:26Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"c4ee0750416e67fbb412503563ec8c1837329b2207a265abe04d388334ed48a4","abstract_canon_sha256":"54b0c72db088972b16ffb932d7259183b1c618630476eb1341a7594f1ed024a2"},"schema_version":"1.0"},"canonical_sha256":"bb1bcc0a818b96c35091c662dbbc1754b6ef7c8060bbbdcec58fb4bb2e11f09e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:11.733799Z","signature_b64":"5HspEoVP3SsvrAc0zqQqFn2ig9YpNlNMsrFevaX5EhYwXd6sYt9jCINYPQU1A/r/EZ5uUvVRdOeGDqB+gusTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb1bcc0a818b96c35091c662dbbc1754b6ef7c8060bbbdcec58fb4bb2e11f09e","last_reissued_at":"2026-07-05T06:22:11.733291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:11.733291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.10785","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":"2026-07-05T06:22:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"brsRNOSoqjCnyl381Uzf6YxGMJdzznmYHteuUXWrLygph6ji2MuUzNzzM7q9t9stfbiveHfAINSdwgoT1W8VDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:15:17.293323Z"},"content_sha256":"59d4137f876867f9f92ccb7c606c85b085ced984aed2b733b1b2510c3ed3b15d","schema_version":"1.0","event_id":"sha256:59d4137f876867f9f92ccb7c606c85b085ced984aed2b733b1b2510c3ed3b15d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XMN4YCUBROLMGUERYZRNXPAXKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multitrack Music Transcription with a Time-Frequency Perceiver","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ju-Chiang Wang, Wei-Tsung Lu, Yun-Ning Hung","submitted_at":"2023-06-19T08:58:26Z","abstract_excerpt":"Multitrack music transcription aims to transcribe a music audio input into the musical notes of multiple instruments simultaneously. It is a very challenging task that typically requires a more complex model to achieve satisfactory result. In addition, prior works mostly focus on transcriptions of regular instruments, however, neglecting vocals, which are usually the most important signal source if present in a piece of music. In this paper, we propose a novel deep neural network architecture, Perceiver TF, to model the time-frequency representation of audio input for multitrack transcription."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10785","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/2306.10785/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":"2026-07-05T06:22:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ym3b4KTqb3Ehn7oWE1E+H4n5JXaxLkpGBLo5HrK4knz//QfKSQ5wIBZZQeIbaAPeRYMXzTSY3bfBJ+sTHnE5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:15:17.294425Z"},"content_sha256":"309030e81d267e1b29d61de8df99c82094d1426ca64e6b3201cc90fbaa01aece","schema_version":"1.0","event_id":"sha256:309030e81d267e1b29d61de8df99c82094d1426ca64e6b3201cc90fbaa01aece"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS/bundle.json","state_url":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMN4YCUBROLMGUERYZRNXPAXKS/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":"2026-08-05T15:15:17Z","links":{"resolver":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS","bundle":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS/bundle.json","state":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMN4YCUBROLMGUERYZRNXPAXKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XMN4YCUBROLMGUERYZRNXPAXKS","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":"54b0c72db088972b16ffb932d7259183b1c618630476eb1341a7594f1ed024a2","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-19T08:58:26Z","title_canon_sha256":"c4ee0750416e67fbb412503563ec8c1837329b2207a265abe04d388334ed48a4"},"schema_version":"1.0","source":{"id":"2306.10785","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10785","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10785v1","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10785","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"XMN4YCUBROLM","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"XMN4YCUBROLMGUER","created_at":"2026-07-05T06:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"XMN4YCUB","created_at":"2026-07-05T06:22:11Z"}],"graph_snapshots":[{"event_id":"sha256:309030e81d267e1b29d61de8df99c82094d1426ca64e6b3201cc90fbaa01aece","target":"graph","created_at":"2026-07-05T06:22:11Z","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/2306.10785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multitrack music transcription aims to transcribe a music audio input into the musical notes of multiple instruments simultaneously. It is a very challenging task that typically requires a more complex model to achieve satisfactory result. In addition, prior works mostly focus on transcriptions of regular instruments, however, neglecting vocals, which are usually the most important signal source if present in a piece of music. In this paper, we propose a novel deep neural network architecture, Perceiver TF, to model the time-frequency representation of audio input for multitrack transcription.","authors_text":"Ju-Chiang Wang, Wei-Tsung Lu, Yun-Ning Hung","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-19T08:58:26Z","title":"Multitrack Music Transcription with a Time-Frequency Perceiver"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10785","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":"sha256:59d4137f876867f9f92ccb7c606c85b085ced984aed2b733b1b2510c3ed3b15d","target":"record","created_at":"2026-07-05T06:22:11Z","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":"54b0c72db088972b16ffb932d7259183b1c618630476eb1341a7594f1ed024a2","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-19T08:58:26Z","title_canon_sha256":"c4ee0750416e67fbb412503563ec8c1837329b2207a265abe04d388334ed48a4"},"schema_version":"1.0","source":{"id":"2306.10785","kind":"arxiv","version":1}},"canonical_sha256":"bb1bcc0a818b96c35091c662dbbc1754b6ef7c8060bbbdcec58fb4bb2e11f09e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb1bcc0a818b96c35091c662dbbc1754b6ef7c8060bbbdcec58fb4bb2e11f09e","first_computed_at":"2026-07-05T06:22:11.733291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:22:11.733291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5HspEoVP3SsvrAc0zqQqFn2ig9YpNlNMsrFevaX5EhYwXd6sYt9jCINYPQU1A/r/EZ5uUvVRdOeGDqB+gusTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:22:11.733799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10785","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59d4137f876867f9f92ccb7c606c85b085ced984aed2b733b1b2510c3ed3b15d","sha256:309030e81d267e1b29d61de8df99c82094d1426ca64e6b3201cc90fbaa01aece"],"state_sha256":"012d8f7859bec4189bde61710ac21ea4ed3ee172f4b89810c227fe1219d108f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"saz13r49I2nQpJHiSJ3/zzMzFPmBsCzmuc+rkFJ7nSOVcPUn4jRKaszXb4HrC3jw/WZUzM+oHyrATvuEyQIZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:15:17.299744Z","bundle_sha256":"8282ff17a529b02c0e8fffd0d75c6be3db5dc172e00c401ba28290125885e6c6"}}