{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PNCBFF7WKCHG75F65L63NDVB3S","short_pith_number":"pith:PNCBFF7W","canonical_record":{"source":{"id":"2310.15648","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-24T09:08:20Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"cda665018a322d53dbc1ae9c6af8d82b5d35c2776e232848da209e0bffbe1020","abstract_canon_sha256":"544ce8d2fbefe59825af4e52f5c6f2c8866f75e32db74718be5d45be0d63efb7"},"schema_version":"1.0"},"canonical_sha256":"7b441297f6508e6ff4beeafdb68ea1dcaacb0b80cc8269b6aee6056699edb5d1","source":{"kind":"arxiv","id":"2310.15648","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15648","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15648v1","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15648","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"PNCBFF7WKCHG","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"PNCBFF7WKCHG75F6","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"PNCBFF7W","created_at":"2026-07-05T07:04:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PNCBFF7WKCHG75F65L63NDVB3S","target":"record","payload":{"canonical_record":{"source":{"id":"2310.15648","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-24T09:08:20Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"cda665018a322d53dbc1ae9c6af8d82b5d35c2776e232848da209e0bffbe1020","abstract_canon_sha256":"544ce8d2fbefe59825af4e52f5c6f2c8866f75e32db74718be5d45be0d63efb7"},"schema_version":"1.0"},"canonical_sha256":"7b441297f6508e6ff4beeafdb68ea1dcaacb0b80cc8269b6aee6056699edb5d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:28.992516Z","signature_b64":"at4sJO2Q3iYHZOL1AIKJOUkDCHXyxE3+XDIpCjGvC/KWwSTvLzGOOgcFUf3+h8ig1jecSGJAHeW/+iv/UAJtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b441297f6508e6ff4beeafdb68ea1dcaacb0b80cc8269b6aee6056699edb5d1","last_reissued_at":"2026-07-05T07:04:28.992117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:28.992117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.15648","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":"2026-07-05T07:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jvEkLK2hw/q4VUq3bUumiToQh7ZQsC8jPEs01EZxDX1pNrHTckrGzkL39HRklYNYYJG/+XB+5X8LcTcn4r8tBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:15:05.907192Z"},"content_sha256":"b653c66a6450fbe5b8b6887e1ecf1aff9e5ad14f86a6e2d5a6967c81809a04ad","schema_version":"1.0","event_id":"sha256:b653c66a6450fbe5b8b6887e1ecf1aff9e5ad14f86a6e2d5a6967c81809a04ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PNCBFF7WKCHG75F65L63NDVB3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","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":"2023-10-24T09:08:20Z","abstract_excerpt":"The introduction of large-scale audio datasets, such as AudioSet, paved the way for Transformers to conquer the audio domain and replace CNNs as the state-of-the-art neural network architecture for many tasks. Audio Spectrogram Transformers are excellent at exploiting large datasets, creating powerful pre-trained models that surpass CNNs when fine-tuned on downstream tasks. However, current popular Audio Spectrogram Transformers are demanding in terms of computational complexity compared to CNNs. Recently, we have shown that, by employing Transformer-to-CNN Knowledge Distillation, efficient CN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15648","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/2310.15648/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":"2026-07-05T07:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0WV7QFCWcTk8bP+pj/yB6B465QKtHyReOECrKtmaJ7fz7blEBrcfjQ1wUD6b0q9xTgMIoz4A/GNdz7jcgVNGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:15:05.907759Z"},"content_sha256":"32bd87be9acf4c002ef339b1f574e6bf797d295db95b67a42300233179419d4c","schema_version":"1.0","event_id":"sha256:32bd87be9acf4c002ef339b1f574e6bf797d295db95b67a42300233179419d4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNCBFF7WKCHG75F65L63NDVB3S/bundle.json","state_url":"https://pith.science/pith/PNCBFF7WKCHG75F65L63NDVB3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNCBFF7WKCHG75F65L63NDVB3S/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":"2026-08-16T16:15:05Z","links":{"resolver":"https://pith.science/pith/PNCBFF7WKCHG75F65L63NDVB3S","bundle":"https://pith.science/pith/PNCBFF7WKCHG75F65L63NDVB3S/bundle.json","state":"https://pith.science/pith/PNCBFF7WKCHG75F65L63NDVB3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNCBFF7WKCHG75F65L63NDVB3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PNCBFF7WKCHG75F65L63NDVB3S","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":"544ce8d2fbefe59825af4e52f5c6f2c8866f75e32db74718be5d45be0d63efb7","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-24T09:08:20Z","title_canon_sha256":"cda665018a322d53dbc1ae9c6af8d82b5d35c2776e232848da209e0bffbe1020"},"schema_version":"1.0","source":{"id":"2310.15648","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15648","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15648v1","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15648","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"PNCBFF7WKCHG","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"PNCBFF7WKCHG75F6","created_at":"2026-07-05T07:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"PNCBFF7W","created_at":"2026-07-05T07:04:28Z"}],"graph_snapshots":[{"event_id":"sha256:32bd87be9acf4c002ef339b1f574e6bf797d295db95b67a42300233179419d4c","target":"graph","created_at":"2026-07-05T07:04:28Z","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/2310.15648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The introduction of large-scale audio datasets, such as AudioSet, paved the way for Transformers to conquer the audio domain and replace CNNs as the state-of-the-art neural network architecture for many tasks. Audio Spectrogram Transformers are excellent at exploiting large datasets, creating powerful pre-trained models that surpass CNNs when fine-tuned on downstream tasks. However, current popular Audio Spectrogram Transformers are demanding in terms of computational complexity compared to CNNs. Recently, we have shown that, by employing Transformer-to-CNN Knowledge Distillation, efficient CN","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":"2023-10-24T09:08:20Z","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15648","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:b653c66a6450fbe5b8b6887e1ecf1aff9e5ad14f86a6e2d5a6967c81809a04ad","target":"record","created_at":"2026-07-05T07:04:28Z","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":"544ce8d2fbefe59825af4e52f5c6f2c8866f75e32db74718be5d45be0d63efb7","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-24T09:08:20Z","title_canon_sha256":"cda665018a322d53dbc1ae9c6af8d82b5d35c2776e232848da209e0bffbe1020"},"schema_version":"1.0","source":{"id":"2310.15648","kind":"arxiv","version":1}},"canonical_sha256":"7b441297f6508e6ff4beeafdb68ea1dcaacb0b80cc8269b6aee6056699edb5d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b441297f6508e6ff4beeafdb68ea1dcaacb0b80cc8269b6aee6056699edb5d1","first_computed_at":"2026-07-05T07:04:28.992117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:28.992117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"at4sJO2Q3iYHZOL1AIKJOUkDCHXyxE3+XDIpCjGvC/KWwSTvLzGOOgcFUf3+h8ig1jecSGJAHeW/+iv/UAJtAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:28.992516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15648","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b653c66a6450fbe5b8b6887e1ecf1aff9e5ad14f86a6e2d5a6967c81809a04ad","sha256:32bd87be9acf4c002ef339b1f574e6bf797d295db95b67a42300233179419d4c"],"state_sha256":"9fec143fdaea9705f6c787e7ca4b2355a676fc67d227381429b1c727316bfdde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0jR4cWQi71gf6FQHURpxQYMcL3eri34oM/hanf9fSdkegtkKmUfLjeKd1h26MtRMJnWGD8WwabJBaOrBtWDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T16:15:05.913226Z","bundle_sha256":"813663fb5396e70c69ef1973b95d59e03ec9146f30fba53126dcd316a0b23bb5"}}