{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:S6NA5HIQEBOCXYKBUM6FZPETQG","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":"1e2e2ed223f4679cf18bbb6fa32b59fd93f215bd365d2afe07dd2c988bb0cc5a","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-25T05:03:31Z","title_canon_sha256":"d3b92b2d89cfb8cdcbed2bc40aebeefd3d35a2a3b7c845859d1431447345bc47"},"schema_version":"1.0","source":{"id":"2203.13448","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13448","created_at":"2026-07-05T04:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13448v3","created_at":"2026-07-05T04:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13448","created_at":"2026-07-05T04:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"S6NA5HIQEBOC","created_at":"2026-07-05T04:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"S6NA5HIQEBOCXYKB","created_at":"2026-07-05T04:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"S6NA5HIQ","created_at":"2026-07-05T04:51:07Z"}],"graph_snapshots":[{"event_id":"sha256:87c04147b35a2b6872f8cd9b9b715367389e3c9fc16659d8ced27846f2002c87","target":"graph","created_at":"2026-07-05T04:51:07Z","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/2203.13448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"After its sweeping success in vision and language tasks, pure attention-based neural architectures (e.g. DeiT) are emerging to the top of audio tagging (AT) leaderboards, which seemingly obsoletes traditional convolutional neural networks (CNNs), feed-forward networks or recurrent networks. However, taking a closer look, there is great variability in published research, for instance, performances of models initialized with pretrained weights differ drastically from without pretraining, training time for a model varies from hours to weeks, and often, essences are hidden in seemingly trivial det","authors_text":"Florian Metze, Juncheng B Li, Po-Yao Huang, Shuhui Qu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-25T05:03:31Z","title":"AudioTagging Done Right: 2nd comparison of deep learning methods for environmental sound classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13448","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":"sha256:2641ed2cd6984fe9ca643c3aee6db78f4e8db3bbfa4393b09da1809fbf22e3a3","target":"record","created_at":"2026-07-05T04:51:07Z","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":"1e2e2ed223f4679cf18bbb6fa32b59fd93f215bd365d2afe07dd2c988bb0cc5a","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-25T05:03:31Z","title_canon_sha256":"d3b92b2d89cfb8cdcbed2bc40aebeefd3d35a2a3b7c845859d1431447345bc47"},"schema_version":"1.0","source":{"id":"2203.13448","kind":"arxiv","version":3}},"canonical_sha256":"979a0e9d10205c2be141a33c5cbc9381badcde14a04d3884494f79c803781993","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"979a0e9d10205c2be141a33c5cbc9381badcde14a04d3884494f79c803781993","first_computed_at":"2026-07-05T04:51:07.451637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:07.451637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3NxXmrbtq5t0IEeVEkwF/1LgoPTjCYKWp1PXKH5jZ+BqfYjxgj3EN6eiGMR1DokTyyl1246TrhY78LOwApYmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:07.452000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.13448","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2641ed2cd6984fe9ca643c3aee6db78f4e8db3bbfa4393b09da1809fbf22e3a3","sha256:87c04147b35a2b6872f8cd9b9b715367389e3c9fc16659d8ced27846f2002c87"],"state_sha256":"af6d920aa07b6acf17a55ac6f636c6b3406fd42fa883f5d29c8444db9f382ac3"}