{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WTSPQ62OIYNGEQU2LGXDPONA34","short_pith_number":"pith:WTSPQ62O","canonical_record":{"source":{"id":"2204.12260","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-26T12:32:10Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"74f53abbe63d0670aad02fec12a6e76d2c4af2221849a21c662562501ba83d2c","abstract_canon_sha256":"4bb66264465aa6f8f65d2e805161f1a7087d88f844b85818c0eafde58c678907"},"schema_version":"1.0"},"canonical_sha256":"b4e4f87b4e461a62429a59ae37b9a0df2b72e8fe80b9ba6f435c1928066f75bf","source":{"kind":"arxiv","id":"2204.12260","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12260","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12260v1","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12260","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"WTSPQ62OIYNG","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"WTSPQ62OIYNGEQU2","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"WTSPQ62O","created_at":"2026-07-05T05:49:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WTSPQ62OIYNGEQU2LGXDPONA34","target":"record","payload":{"canonical_record":{"source":{"id":"2204.12260","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-26T12:32:10Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"74f53abbe63d0670aad02fec12a6e76d2c4af2221849a21c662562501ba83d2c","abstract_canon_sha256":"4bb66264465aa6f8f65d2e805161f1a7087d88f844b85818c0eafde58c678907"},"schema_version":"1.0"},"canonical_sha256":"b4e4f87b4e461a62429a59ae37b9a0df2b72e8fe80b9ba6f435c1928066f75bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:13.252961Z","signature_b64":"JKK1hQnSWgZJL/XOWz7TUCxX2TD+tiOFTmN0a4trNvQvToJxx6Fj/+7F4Jw+bNqR8CozGglPjr3G14zyAP7lCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4e4f87b4e461a62429a59ae37b9a0df2b72e8fe80b9ba6f435c1928066f75bf","last_reissued_at":"2026-07-05T05:49:13.252528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:13.252528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.12260","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":"2026-07-05T05:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzhCVOy2PITTXcrmg7QSWle8BgTa5NmD7boPzBpLRc76qbdo8aV0Jj8LvfjMkqjkC5SoWrp6EGzajAvxnL1LBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:15:09.968468Z"},"content_sha256":"c1c61698df1457cee68fef6464ad470f77d53abdb99dea51de0b7ce677d4d56e","schema_version":"1.0","event_id":"sha256:c1c61698df1457cee68fef6464ad470f77d53abdb99dea51de0b7ce677d4d56e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WTSPQ62OIYNGEQU2LGXDPONA34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daiki Takeuchi, Daisuke Niizumi, Kunio Kashino, Noboru Harada, Yasunori Ohishi","submitted_at":"2022-04-26T12:32:10Z","abstract_excerpt":"Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example, typical audio contrastive learning uses temporal relationships among input sounds to create training signals, whereas some methods use a difference among input views created by data augmentations. However, these training signals do not provide information derived from the intact input sound, which we think is suboptimal for learning representation that describes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12260","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/2204.12260/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":"2026-07-05T05:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DOZU2pDn3OXeYguwRlxrgc6H/EWYH/NwRBQHW8+Nb0molmWgtU71phdL+3E/s8ib6C/J6szknm3NBckbWFTVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:15:09.968975Z"},"content_sha256":"5560d36a950644cc55770c25bbd09225343d15e83668ce5738ca25e46b0c0fdd","schema_version":"1.0","event_id":"sha256:5560d36a950644cc55770c25bbd09225343d15e83668ce5738ca25e46b0c0fdd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTSPQ62OIYNGEQU2LGXDPONA34/bundle.json","state_url":"https://pith.science/pith/WTSPQ62OIYNGEQU2LGXDPONA34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTSPQ62OIYNGEQU2LGXDPONA34/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":"2026-08-07T12:15:09Z","links":{"resolver":"https://pith.science/pith/WTSPQ62OIYNGEQU2LGXDPONA34","bundle":"https://pith.science/pith/WTSPQ62OIYNGEQU2LGXDPONA34/bundle.json","state":"https://pith.science/pith/WTSPQ62OIYNGEQU2LGXDPONA34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTSPQ62OIYNGEQU2LGXDPONA34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WTSPQ62OIYNGEQU2LGXDPONA34","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":"4bb66264465aa6f8f65d2e805161f1a7087d88f844b85818c0eafde58c678907","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-26T12:32:10Z","title_canon_sha256":"74f53abbe63d0670aad02fec12a6e76d2c4af2221849a21c662562501ba83d2c"},"schema_version":"1.0","source":{"id":"2204.12260","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12260","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12260v1","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12260","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"WTSPQ62OIYNG","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"WTSPQ62OIYNGEQU2","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"WTSPQ62O","created_at":"2026-07-05T05:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:5560d36a950644cc55770c25bbd09225343d15e83668ce5738ca25e46b0c0fdd","target":"graph","created_at":"2026-07-05T05:49:13Z","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/2204.12260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example, typical audio contrastive learning uses temporal relationships among input sounds to create training signals, whereas some methods use a difference among input views created by data augmentations. However, these training signals do not provide information derived from the intact input sound, which we think is suboptimal for learning representation that describes ","authors_text":"Daiki Takeuchi, Daisuke Niizumi, Kunio Kashino, Noboru Harada, Yasunori Ohishi","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-26T12:32:10Z","title":"Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12260","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:c1c61698df1457cee68fef6464ad470f77d53abdb99dea51de0b7ce677d4d56e","target":"record","created_at":"2026-07-05T05:49:13Z","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":"4bb66264465aa6f8f65d2e805161f1a7087d88f844b85818c0eafde58c678907","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-26T12:32:10Z","title_canon_sha256":"74f53abbe63d0670aad02fec12a6e76d2c4af2221849a21c662562501ba83d2c"},"schema_version":"1.0","source":{"id":"2204.12260","kind":"arxiv","version":1}},"canonical_sha256":"b4e4f87b4e461a62429a59ae37b9a0df2b72e8fe80b9ba6f435c1928066f75bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4e4f87b4e461a62429a59ae37b9a0df2b72e8fe80b9ba6f435c1928066f75bf","first_computed_at":"2026-07-05T05:49:13.252528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:13.252528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JKK1hQnSWgZJL/XOWz7TUCxX2TD+tiOFTmN0a4trNvQvToJxx6Fj/+7F4Jw+bNqR8CozGglPjr3G14zyAP7lCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:13.252961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.12260","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1c61698df1457cee68fef6464ad470f77d53abdb99dea51de0b7ce677d4d56e","sha256:5560d36a950644cc55770c25bbd09225343d15e83668ce5738ca25e46b0c0fdd"],"state_sha256":"bc379c7981735654332ad1c16d7f478f3b06feaeb350cc7a658fe46a9b209b06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CixrTNT82IaMRa8WB4lu8sZ9yew5VIPSxQE6eHZnfyfJI1gEzx5+alo2LgYbxM978QkFDytvINYv3sF9yN/tDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:15:09.973294Z","bundle_sha256":"81af743f76ea52ba22063eff91bfff92a9472f98e7bacf9d54b2bdaa7aaa909c"}}