{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZF6CI7IQZXVL6E4XVTPSR4UZSL","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":"dadd09e99ccf92a7ca64a5183322cd8d52d50ab45fd00fa947e10ad013082ebf","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-19T07:58:28Z","title_canon_sha256":"81caaad4506e26e6136bae6d7955bd89865c1ef5bf55193b356bddce4033c6bc"},"schema_version":"1.0","source":{"id":"2110.09784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09784","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09784v2","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09784","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZF6CI7IQZXVL","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZF6CI7IQZXVL6E4X","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZF6CI7IQ","created_at":"2026-07-05T03:56:04Z"}],"graph_snapshots":[{"event_id":"sha256:b694c2dc765a9a4a7f343d0addbbe953120fc2931c86c96230a5d9c5964a7c3b","target":"graph","created_at":"2026-07-05T03:56:04Z","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/2110.09784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending the success of Transformers, which were originally developed for language processing, to the vision domain. A recent study showed that a similar methodology can also be applied to the audio domain. Specifically, the Audio Spectrogram Transformer (AST) achieves state-of-the-art results on various audio classification benchmarks. However, pure Transformer mod","authors_text":"Cheng-I Jeff Lai, James Glass, Yu-An Chung, Yuan Gong","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-19T07:58:28Z","title":"SSAST: Self-Supervised Audio Spectrogram Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09784","kind":"arxiv","version":2},"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:de45de18eba2f07f29f65d88dd618fd0ce069599659844568fb4b436d22184ca","target":"record","created_at":"2026-07-05T03:56:04Z","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":"dadd09e99ccf92a7ca64a5183322cd8d52d50ab45fd00fa947e10ad013082ebf","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-19T07:58:28Z","title_canon_sha256":"81caaad4506e26e6136bae6d7955bd89865c1ef5bf55193b356bddce4033c6bc"},"schema_version":"1.0","source":{"id":"2110.09784","kind":"arxiv","version":2}},"canonical_sha256":"c97c247d10cdeabf1397acdf28f29992d1d298844e686142db4e0c9b8fc787be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c97c247d10cdeabf1397acdf28f29992d1d298844e686142db4e0c9b8fc787be","first_computed_at":"2026-07-05T03:56:04.081984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:04.081984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JNlOVLeYaBdC8YqE43x+MkBJ5otpod1SHDiCPTVjM0sw9qsZKzRw4xKxKo0w/lqTHMWH5EB5UqA4w6VVZjYtDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:04.082436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.09784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de45de18eba2f07f29f65d88dd618fd0ce069599659844568fb4b436d22184ca","sha256:b694c2dc765a9a4a7f343d0addbbe953120fc2931c86c96230a5d9c5964a7c3b"],"state_sha256":"da089f883abdeab84f096f109a49303eef30096f42c747a49841408853207ddc"}