{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RJQZEY2KG3ANVSWM22F7NCMVKR","short_pith_number":"pith:RJQZEY2K","canonical_record":{"source":{"id":"2211.04772","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-09T09:58:22Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"3771f025ef899c2b70834b04e31c59d834aa2fcc5d97a71ce18bcf5e05621783","abstract_canon_sha256":"800cd912b2b8ca29e71b8a0ee2f7b530e4bce18a977eb1fe13f314f33dda568a"},"schema_version":"1.0"},"canonical_sha256":"8a6192634a36c0dacaccd68bf68995545711dad974397e7e31d76d30d732e5cf","source":{"kind":"arxiv","id":"2211.04772","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04772","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04772v3","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04772","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"RJQZEY2KG3AN","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"RJQZEY2KG3ANVSWM","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"RJQZEY2K","created_at":"2026-07-05T06:23:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RJQZEY2KG3ANVSWM22F7NCMVKR","target":"record","payload":{"canonical_record":{"source":{"id":"2211.04772","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-09T09:58:22Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"3771f025ef899c2b70834b04e31c59d834aa2fcc5d97a71ce18bcf5e05621783","abstract_canon_sha256":"800cd912b2b8ca29e71b8a0ee2f7b530e4bce18a977eb1fe13f314f33dda568a"},"schema_version":"1.0"},"canonical_sha256":"8a6192634a36c0dacaccd68bf68995545711dad974397e7e31d76d30d732e5cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:56.765483Z","signature_b64":"11sXOGVjtQsCwvh/+jgLGHnQUcn4y5IAe3Rm9ZBcV51GgDlDinVFNtwqhSMFu6BsylCrLQyJCrRMsvk2LnjgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a6192634a36c0dacaccd68bf68995545711dad974397e7e31d76d30d732e5cf","last_reissued_at":"2026-07-05T06:23:56.764967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:56.764967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.04772","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":"2026-07-05T06:23:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nHCh5WV3x6Ge+jm6JLJGeMUQPDyi0yvLL1Wfxzr1pQKLKrUknpn190rM4u07VRWcEl0eXEf1JKAqxSK97B84BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:02:43.031919Z"},"content_sha256":"054f6e047d2d63c39881fdbb181f5442c36cf7c65ce3f0029e0fa7d4e64cd3e6","schema_version":"1.0","event_id":"sha256:054f6e047d2d63c39881fdbb181f5442c36cf7c65ce3f0029e0fa7d4e64cd3e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RJQZEY2KG3ANVSWM22F7NCMVKR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Schmid, Gerhard Widmer, Khaled Koutini","submitted_at":"2022-11-09T09:58:22Z","abstract_excerpt":"Audio Spectrogram Transformer models rule the field of Audio Tagging, outrunning previously dominating Convolutional Neural Networks (CNNs). Their superiority is based on the ability to scale up and exploit large-scale datasets such as AudioSet. However, Transformers are demanding in terms of model size and computational requirements compared to CNNs. We propose a training procedure for efficient CNNs based on offline Knowledge Distillation (KD) from high-performing yet complex transformers. The proposed training schema and the efficient CNN design based on MobileNetV3 results in models outper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04772","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/2211.04772/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":"2026-07-05T06:23:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l/lOmDuA1tDrwajBiqA5dMupfMeQm++YxpQVS9esWdi17j+LDTYYMFX531Kk7q10ZmsH/50+6Zvdim3l9o8lCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:02:43.032418Z"},"content_sha256":"a9d703a84176086609b36fc11cfa6949e5d4e0eb8c9ebbc71934ea8353de457b","schema_version":"1.0","event_id":"sha256:a9d703a84176086609b36fc11cfa6949e5d4e0eb8c9ebbc71934ea8353de457b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJQZEY2KG3ANVSWM22F7NCMVKR/bundle.json","state_url":"https://pith.science/pith/RJQZEY2KG3ANVSWM22F7NCMVKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJQZEY2KG3ANVSWM22F7NCMVKR/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":"2026-08-05T08:02:43Z","links":{"resolver":"https://pith.science/pith/RJQZEY2KG3ANVSWM22F7NCMVKR","bundle":"https://pith.science/pith/RJQZEY2KG3ANVSWM22F7NCMVKR/bundle.json","state":"https://pith.science/pith/RJQZEY2KG3ANVSWM22F7NCMVKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJQZEY2KG3ANVSWM22F7NCMVKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RJQZEY2KG3ANVSWM22F7NCMVKR","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":"800cd912b2b8ca29e71b8a0ee2f7b530e4bce18a977eb1fe13f314f33dda568a","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-09T09:58:22Z","title_canon_sha256":"3771f025ef899c2b70834b04e31c59d834aa2fcc5d97a71ce18bcf5e05621783"},"schema_version":"1.0","source":{"id":"2211.04772","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04772","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04772v3","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04772","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"RJQZEY2KG3AN","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"RJQZEY2KG3ANVSWM","created_at":"2026-07-05T06:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"RJQZEY2K","created_at":"2026-07-05T06:23:56Z"}],"graph_snapshots":[{"event_id":"sha256:a9d703a84176086609b36fc11cfa6949e5d4e0eb8c9ebbc71934ea8353de457b","target":"graph","created_at":"2026-07-05T06:23:56Z","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/2211.04772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio Spectrogram Transformer models rule the field of Audio Tagging, outrunning previously dominating Convolutional Neural Networks (CNNs). Their superiority is based on the ability to scale up and exploit large-scale datasets such as AudioSet. However, Transformers are demanding in terms of model size and computational requirements compared to CNNs. We propose a training procedure for efficient CNNs based on offline Knowledge Distillation (KD) from high-performing yet complex transformers. The proposed training schema and the efficient CNN design based on MobileNetV3 results in models outper","authors_text":"Florian Schmid, Gerhard Widmer, Khaled Koutini","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-09T09:58:22Z","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04772","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":"sha256:054f6e047d2d63c39881fdbb181f5442c36cf7c65ce3f0029e0fa7d4e64cd3e6","target":"record","created_at":"2026-07-05T06:23:56Z","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":"800cd912b2b8ca29e71b8a0ee2f7b530e4bce18a977eb1fe13f314f33dda568a","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-09T09:58:22Z","title_canon_sha256":"3771f025ef899c2b70834b04e31c59d834aa2fcc5d97a71ce18bcf5e05621783"},"schema_version":"1.0","source":{"id":"2211.04772","kind":"arxiv","version":3}},"canonical_sha256":"8a6192634a36c0dacaccd68bf68995545711dad974397e7e31d76d30d732e5cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a6192634a36c0dacaccd68bf68995545711dad974397e7e31d76d30d732e5cf","first_computed_at":"2026-07-05T06:23:56.764967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:56.764967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"11sXOGVjtQsCwvh/+jgLGHnQUcn4y5IAe3Rm9ZBcV51GgDlDinVFNtwqhSMFu6BsylCrLQyJCrRMsvk2LnjgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:56.765483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.04772","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:054f6e047d2d63c39881fdbb181f5442c36cf7c65ce3f0029e0fa7d4e64cd3e6","sha256:a9d703a84176086609b36fc11cfa6949e5d4e0eb8c9ebbc71934ea8353de457b"],"state_sha256":"20d4dbd89a4895dcb08d71f42ad8bf2b89d764b0b98f8aab1a5c2cf628a31e40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mme3BS7TslXnVdp2YVPf5HDykc0JzaBsQT6EfMjxQSEG3dA2EV0YzZLLIy3ImMGr4/N9QpqZscNkUHLelb1ZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:02:43.036375Z","bundle_sha256":"a34ddd90718b08f0a6623518635d05f554385376e742ccbfdfdc48f2ae05ed6e"}}