{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6JRHYYSINQSSUXFS22FRJKHEAK","short_pith_number":"pith:6JRHYYSI","canonical_record":{"source":{"id":"2203.16691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-30T22:06:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"9e60d6c8939d09b7a3e0d9138f9b44b05a9c244a69a21ff539cfc736ae10457d","abstract_canon_sha256":"669e97200382936fb0803c2b656b7fa7f1940d084d88703d033c41f479362c89"},"schema_version":"1.0"},"canonical_sha256":"f2627c62486c252a5cb2d68b14a8e402a10a7599f8c8463af501fed61689b550","source":{"kind":"arxiv","id":"2203.16691","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16691","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16691v1","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16691","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"6JRHYYSINQSS","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"6JRHYYSINQSSUXFS","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"6JRHYYSI","created_at":"2026-07-05T04:10:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6JRHYYSINQSSUXFS22FRJKHEAK","target":"record","payload":{"canonical_record":{"source":{"id":"2203.16691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-30T22:06:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"9e60d6c8939d09b7a3e0d9138f9b44b05a9c244a69a21ff539cfc736ae10457d","abstract_canon_sha256":"669e97200382936fb0803c2b656b7fa7f1940d084d88703d033c41f479362c89"},"schema_version":"1.0"},"canonical_sha256":"f2627c62486c252a5cb2d68b14a8e402a10a7599f8c8463af501fed61689b550","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:15.018782Z","signature_b64":"/entHVZosKk75LF+WCzFTIRcUGirayPFMYay1gWyyVe8VAIRmVxbeF7mE8Id39Rf2wuF3TpSWw/OJ9D+We1hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2627c62486c252a5cb2d68b14a8e402a10a7599f8c8463af501fed61689b550","last_reissued_at":"2026-07-05T04:10:15.018377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:15.018377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.16691","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":"2026-07-05T04:10:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bqQiP9S4w2gek8UsKZRl/NR2HQwF95XOKRYWR3EExpyAccrwWjcLDfc8A4FBtjVu/eHeyBsu3oP27b/xIGC2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:56:11.895945Z"},"content_sha256":"95aa5e096b92cb835b4f33a8d6022872e256ad3c15b01f1722420c679f2fe5e1","schema_version":"1.0","event_id":"sha256:95aa5e096b92cb835b4f33a8d6022872e256ad3c15b01f1722420c679f2fe5e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6JRHYYSINQSSUXFS22FRJKHEAK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alan Baade, David Harwath, Puyuan Peng","submitted_at":"2022-03-30T22:06:13Z","abstract_excerpt":"In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the SSAST uses a very high masking ratio (75%) during pretraining, meaning that the vast majority of self-attention compute is performed on mask tokens. We address this by integrating the encoder-decoder architecture from Masked Autoencoders are Scalable Vision Learners (MAE) into the SSAST, where a deep encoder operates on only unmasked input, and a shallow decoder operates on enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16691","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/2203.16691/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":"2026-07-05T04:10:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MY9ou1QNleFb87EjjsQDq6NjrExL3imkj28xBdzCdtxBq6ycfQpH/1/XKUekDksHdMtTzQUWUe/3yw2+gQwLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:56:11.896576Z"},"content_sha256":"2a82b29c3bfef21a730d37e858fc928c25e85209cae911fe003d0048ba36bb5e","schema_version":"1.0","event_id":"sha256:2a82b29c3bfef21a730d37e858fc928c25e85209cae911fe003d0048ba36bb5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JRHYYSINQSSUXFS22FRJKHEAK/bundle.json","state_url":"https://pith.science/pith/6JRHYYSINQSSUXFS22FRJKHEAK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JRHYYSINQSSUXFS22FRJKHEAK/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":"2026-07-07T03:56:11Z","links":{"resolver":"https://pith.science/pith/6JRHYYSINQSSUXFS22FRJKHEAK","bundle":"https://pith.science/pith/6JRHYYSINQSSUXFS22FRJKHEAK/bundle.json","state":"https://pith.science/pith/6JRHYYSINQSSUXFS22FRJKHEAK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JRHYYSINQSSUXFS22FRJKHEAK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6JRHYYSINQSSUXFS22FRJKHEAK","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":"669e97200382936fb0803c2b656b7fa7f1940d084d88703d033c41f479362c89","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-30T22:06:13Z","title_canon_sha256":"9e60d6c8939d09b7a3e0d9138f9b44b05a9c244a69a21ff539cfc736ae10457d"},"schema_version":"1.0","source":{"id":"2203.16691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16691","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16691v1","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16691","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"6JRHYYSINQSS","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"6JRHYYSINQSSUXFS","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"6JRHYYSI","created_at":"2026-07-05T04:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:2a82b29c3bfef21a730d37e858fc928c25e85209cae911fe003d0048ba36bb5e","target":"graph","created_at":"2026-07-05T04:10:15Z","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/2203.16691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the SSAST uses a very high masking ratio (75%) during pretraining, meaning that the vast majority of self-attention compute is performed on mask tokens. We address this by integrating the encoder-decoder architecture from Masked Autoencoders are Scalable Vision Learners (MAE) into the SSAST, where a deep encoder operates on only unmasked input, and a shallow decoder operates on enc","authors_text":"Alan Baade, David Harwath, Puyuan Peng","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-30T22:06:13Z","title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16691","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":"sha256:95aa5e096b92cb835b4f33a8d6022872e256ad3c15b01f1722420c679f2fe5e1","target":"record","created_at":"2026-07-05T04:10:15Z","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":"669e97200382936fb0803c2b656b7fa7f1940d084d88703d033c41f479362c89","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-30T22:06:13Z","title_canon_sha256":"9e60d6c8939d09b7a3e0d9138f9b44b05a9c244a69a21ff539cfc736ae10457d"},"schema_version":"1.0","source":{"id":"2203.16691","kind":"arxiv","version":1}},"canonical_sha256":"f2627c62486c252a5cb2d68b14a8e402a10a7599f8c8463af501fed61689b550","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2627c62486c252a5cb2d68b14a8e402a10a7599f8c8463af501fed61689b550","first_computed_at":"2026-07-05T04:10:15.018377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:15.018377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/entHVZosKk75LF+WCzFTIRcUGirayPFMYay1gWyyVe8VAIRmVxbeF7mE8Id39Rf2wuF3TpSWw/OJ9D+We1hCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:15.018782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95aa5e096b92cb835b4f33a8d6022872e256ad3c15b01f1722420c679f2fe5e1","sha256:2a82b29c3bfef21a730d37e858fc928c25e85209cae911fe003d0048ba36bb5e"],"state_sha256":"dc4651580257c628e7aeebdfa0b072561f1b5ca6f5a535d894a621534b0223a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YlMcgDrxh8xKfThKrddEBkaLH5RPMu1FeoziRXtza4pfOjtFSR1Iqy7+r183mHXFQwwqA7HwImFTUNhRbjVtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:56:11.899331Z","bundle_sha256":"1823497bc23a461b7e4256c06ff56fd0946d14740dd4c3d96b1dc43e64339607"}}