{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:PY4GW77WHJS4TFYIW4EVYS7WD5","short_pith_number":"pith:PY4GW77W","canonical_record":{"source":{"id":"2207.06405","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T17:59:55Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"3af8f0d30ec36869ef9501cbc54b560916f866ded8d1554f7661b87ad9cebd6a","abstract_canon_sha256":"7ee002bca1e15d7b5b6de1c179b9a51c64ce49ee6117b7408b4e421d55fbef06"},"schema_version":"1.0"},"canonical_sha256":"7e386b7ff63a65c99708b7095c4bf61f72b3ed9e9739806a7677b6eecd351e14","source":{"kind":"arxiv","id":"2207.06405","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06405","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06405v3","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06405","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"pith_short_12","alias_value":"PY4GW77WHJS4","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"PY4GW77WHJS4TFYI","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"PY4GW77W","created_at":"2026-07-05T05:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:PY4GW77WHJS4TFYIW4EVYS7WD5","target":"record","payload":{"canonical_record":{"source":{"id":"2207.06405","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T17:59:55Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"3af8f0d30ec36869ef9501cbc54b560916f866ded8d1554f7661b87ad9cebd6a","abstract_canon_sha256":"7ee002bca1e15d7b5b6de1c179b9a51c64ce49ee6117b7408b4e421d55fbef06"},"schema_version":"1.0"},"canonical_sha256":"7e386b7ff63a65c99708b7095c4bf61f72b3ed9e9739806a7677b6eecd351e14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:31.325438Z","signature_b64":"z1eCCoBL5r02iPaEsotBSdDldvrFAmliUiEOatInkggXIsYMc6k2+HXwkPMgJKbnn0LXSL30NjDzH9ZhVryJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e386b7ff63a65c99708b7095c4bf61f72b3ed9e9739806a7677b6eecd351e14","last_reissued_at":"2026-07-05T05:32:31.324944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:31.324944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.06405","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:32:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTH2Gi7MZLQkssdbpcWu5UHATiPzAjysahvBo8DPYv6FgM1t1w3cp8WnNoG+JA2+AfjwlFpjkHz3nEuioq9AAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T16:41:38.957836Z"},"content_sha256":"5c1c6d1e056daa02c15de428a2811998a5c883782619f7c9b0ccf46e6d359970","schema_version":"1.0","event_id":"sha256:5c1c6d1e056daa02c15de428a2811998a5c883782619f7c9b0ccf46e6d359970"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:PY4GW77WHJS4TFYIW4EVYS7WD5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masked Autoencoders that Listen","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexei Baevski, Christoph Feichtenhofer, Florian Metze, Hu Xu, Juncheng Li, Michael Auli, Po-Yao Huang, Wojciech Galuba","submitted_at":"2022-07-13T17:59:55Z","abstract_excerpt":"This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE first encodes audio spectrogram patches with a high masking ratio, feeding only the non-masked tokens through encoder layers. The decoder then re-orders and decodes the encoded context padded with mask tokens, in order to reconstruct the input spectrogram. We find it beneficial to incorporate local window attention in the decoder, as audio spectrograms are highly correlated in lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06405","kind":"arxiv","version":3},"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/2207.06405/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":"2026-07-05T05:32:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vbY84HViUC5/4yRpheL5TDMLdmWenO2a9kwMIMPV1nXCYEQSs92KnU4dRxynWaJZmPr36Pk7msIaRW+8i6T6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T16:41:38.958233Z"},"content_sha256":"55bb935f361dcad41b00dc276e9c856863436de0691644eebfc7a14b48875f51","schema_version":"1.0","event_id":"sha256:55bb935f361dcad41b00dc276e9c856863436de0691644eebfc7a14b48875f51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PY4GW77WHJS4TFYIW4EVYS7WD5/bundle.json","state_url":"https://pith.science/pith/PY4GW77WHJS4TFYIW4EVYS7WD5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PY4GW77WHJS4TFYIW4EVYS7WD5/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":"2026-07-10T16:41:38Z","links":{"resolver":"https://pith.science/pith/PY4GW77WHJS4TFYIW4EVYS7WD5","bundle":"https://pith.science/pith/PY4GW77WHJS4TFYIW4EVYS7WD5/bundle.json","state":"https://pith.science/pith/PY4GW77WHJS4TFYIW4EVYS7WD5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PY4GW77WHJS4TFYIW4EVYS7WD5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PY4GW77WHJS4TFYIW4EVYS7WD5","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":"7ee002bca1e15d7b5b6de1c179b9a51c64ce49ee6117b7408b4e421d55fbef06","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T17:59:55Z","title_canon_sha256":"3af8f0d30ec36869ef9501cbc54b560916f866ded8d1554f7661b87ad9cebd6a"},"schema_version":"1.0","source":{"id":"2207.06405","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06405","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06405v3","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06405","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"pith_short_12","alias_value":"PY4GW77WHJS4","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"PY4GW77WHJS4TFYI","created_at":"2026-07-05T05:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"PY4GW77W","created_at":"2026-07-05T05:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:55bb935f361dcad41b00dc276e9c856863436de0691644eebfc7a14b48875f51","target":"graph","created_at":"2026-07-05T05:32:31Z","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/2207.06405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE first encodes audio spectrogram patches with a high masking ratio, feeding only the non-masked tokens through encoder layers. The decoder then re-orders and decodes the encoded context padded with mask tokens, in order to reconstruct the input spectrogram. We find it beneficial to incorporate local window attention in the decoder, as audio spectrograms are highly correlated in lo","authors_text":"Alexei Baevski, Christoph Feichtenhofer, Florian Metze, Hu Xu, Juncheng Li, Michael Auli, Po-Yao Huang, Wojciech Galuba","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T17:59:55Z","title":"Masked Autoencoders that Listen"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06405","kind":"arxiv","version":3},"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":"sha256:5c1c6d1e056daa02c15de428a2811998a5c883782619f7c9b0ccf46e6d359970","target":"record","created_at":"2026-07-05T05:32:31Z","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":"7ee002bca1e15d7b5b6de1c179b9a51c64ce49ee6117b7408b4e421d55fbef06","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T17:59:55Z","title_canon_sha256":"3af8f0d30ec36869ef9501cbc54b560916f866ded8d1554f7661b87ad9cebd6a"},"schema_version":"1.0","source":{"id":"2207.06405","kind":"arxiv","version":3}},"canonical_sha256":"7e386b7ff63a65c99708b7095c4bf61f72b3ed9e9739806a7677b6eecd351e14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e386b7ff63a65c99708b7095c4bf61f72b3ed9e9739806a7677b6eecd351e14","first_computed_at":"2026-07-05T05:32:31.324944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:32:31.324944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z1eCCoBL5r02iPaEsotBSdDldvrFAmliUiEOatInkggXIsYMc6k2+HXwkPMgJKbnn0LXSL30NjDzH9ZhVryJDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:32:31.325438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.06405","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c1c6d1e056daa02c15de428a2811998a5c883782619f7c9b0ccf46e6d359970","sha256:55bb935f361dcad41b00dc276e9c856863436de0691644eebfc7a14b48875f51"],"state_sha256":"26fd8a98e147b4aac4c3f1ba2ee9f5d8ad26f9a17954ff213c1eef08c714df77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MtO8JnjVSMzGM3mYZjFhubJgIp8YW8j09w9zlrdI/MMUOvz9Zi1ehlaKwDX7qUKyw9RAC8iqLRk0tPn8AaPmCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T16:41:38.960550Z","bundle_sha256":"29de8ee26ae9938455da83d3d26f2133ea7a1c32cc7f45a39f084a318d4b2f76"}}