{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LMPOKNXMAQYXJXVBOY5COQCVKF","short_pith_number":"pith:LMPOKNXM","canonical_record":{"source":{"id":"2208.11402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-24T09:48:22Z","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"3e2537c4712531ec5deecaa3d5eddedee4b8319774aab6f311ed0066596a0a10","abstract_canon_sha256":"a130b43c608c9fc8c5b01b0aa4ceb447354cf0e5217b33dd41ae5b9abff972a6"},"schema_version":"1.0"},"canonical_sha256":"5b1ee536ec043174dea1763a2740555158b27793e0de4c7aaa1a756c092afdd0","source":{"kind":"arxiv","id":"2208.11402","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.11402","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"2208.11402v1","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11402","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"LMPOKNXMAQYX","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"pith_short_16","alias_value":"LMPOKNXMAQYXJXVB","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"pith_short_8","alias_value":"LMPOKNXM","created_at":"2026-07-05T04:51:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LMPOKNXMAQYXJXVBOY5COQCVKF","target":"record","payload":{"canonical_record":{"source":{"id":"2208.11402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-24T09:48:22Z","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"3e2537c4712531ec5deecaa3d5eddedee4b8319774aab6f311ed0066596a0a10","abstract_canon_sha256":"a130b43c608c9fc8c5b01b0aa4ceb447354cf0e5217b33dd41ae5b9abff972a6"},"schema_version":"1.0"},"canonical_sha256":"5b1ee536ec043174dea1763a2740555158b27793e0de4c7aaa1a756c092afdd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:14.719044Z","signature_b64":"s1BhxLTl+2TiOe3MZwT12cks1BKqIAgPcg0qJuRsonB48heUSRnPxPruzZe5UdqLCyK0gXP1+t8V71zf33DRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b1ee536ec043174dea1763a2740555158b27793e0de4c7aaa1a756c092afdd0","last_reissued_at":"2026-07-05T04:51:14.718657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:14.718657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.11402","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":"2026-07-05T04:51:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GAKBz6722vZ7tFuUMvsdb6oBcvuvKJGCP6F12NfJdy0gnsHj3i5gZ+iRHl3A1VZZIZU/YvYoMPgYN2tAzVOaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:33:22.733200Z"},"content_sha256":"5516941729a8bc39ae0eb0630a331b22ebaf8c50988f8c80972dcfb60606f2a8","schema_version":"1.0","event_id":"sha256:5516941729a8bc39ae0eb0630a331b22ebaf8c50988f8c80972dcfb60606f2a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LMPOKNXMAQYXJXVBOY5COQCVKF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Gerhard Widmer, Paul Primus","submitted_at":"2022-08-24T09:48:22Z","abstract_excerpt":"Standard machine learning models for tagging and classifying acoustic signals cannot handle classes that were not seen during training. Zero-Shot (ZS) learning overcomes this restriction by predicting classes based on adaptable class descriptions. This study sets out to investigate the effectiveness of self-attention-based audio embedding architectures for ZS learning. To this end, we compare the very recent patchout spectrogram transformer with two classic convolutional architectures. We evaluate these three architectures on three tasks and on three different benchmark datasets: general-purpo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11402","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/2208.11402/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":"2026-07-05T04:51:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XV3C7eGRNbiRMN+DM5IFYIxP+qlofPFwWxVaRMvbUpa178HuSZE5c9W7rxMmdSVDbE+q2/6TIfVfnqRaTFssBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:33:22.733751Z"},"content_sha256":"10aa113df71ef67fabdd6a51cc7f7775525bb202496f19854e3ee3a29f831f87","schema_version":"1.0","event_id":"sha256:10aa113df71ef67fabdd6a51cc7f7775525bb202496f19854e3ee3a29f831f87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LMPOKNXMAQYXJXVBOY5COQCVKF/bundle.json","state_url":"https://pith.science/pith/LMPOKNXMAQYXJXVBOY5COQCVKF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LMPOKNXMAQYXJXVBOY5COQCVKF/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":"2026-08-05T16:33:22Z","links":{"resolver":"https://pith.science/pith/LMPOKNXMAQYXJXVBOY5COQCVKF","bundle":"https://pith.science/pith/LMPOKNXMAQYXJXVBOY5COQCVKF/bundle.json","state":"https://pith.science/pith/LMPOKNXMAQYXJXVBOY5COQCVKF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LMPOKNXMAQYXJXVBOY5COQCVKF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LMPOKNXMAQYXJXVBOY5COQCVKF","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":"a130b43c608c9fc8c5b01b0aa4ceb447354cf0e5217b33dd41ae5b9abff972a6","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-24T09:48:22Z","title_canon_sha256":"3e2537c4712531ec5deecaa3d5eddedee4b8319774aab6f311ed0066596a0a10"},"schema_version":"1.0","source":{"id":"2208.11402","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.11402","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"2208.11402v1","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11402","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"LMPOKNXMAQYX","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"pith_short_16","alias_value":"LMPOKNXMAQYXJXVB","created_at":"2026-07-05T04:51:14Z"},{"alias_kind":"pith_short_8","alias_value":"LMPOKNXM","created_at":"2026-07-05T04:51:14Z"}],"graph_snapshots":[{"event_id":"sha256:10aa113df71ef67fabdd6a51cc7f7775525bb202496f19854e3ee3a29f831f87","target":"graph","created_at":"2026-07-05T04:51:14Z","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/2208.11402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard machine learning models for tagging and classifying acoustic signals cannot handle classes that were not seen during training. Zero-Shot (ZS) learning overcomes this restriction by predicting classes based on adaptable class descriptions. This study sets out to investigate the effectiveness of self-attention-based audio embedding architectures for ZS learning. To this end, we compare the very recent patchout spectrogram transformer with two classic convolutional architectures. We evaluate these three architectures on three tasks and on three different benchmark datasets: general-purpo","authors_text":"Gerhard Widmer, Paul Primus","cross_cats":["cs.LG","eess.AS","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-24T09:48:22Z","title":"Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11402","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":"sha256:5516941729a8bc39ae0eb0630a331b22ebaf8c50988f8c80972dcfb60606f2a8","target":"record","created_at":"2026-07-05T04:51:14Z","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":"a130b43c608c9fc8c5b01b0aa4ceb447354cf0e5217b33dd41ae5b9abff972a6","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-24T09:48:22Z","title_canon_sha256":"3e2537c4712531ec5deecaa3d5eddedee4b8319774aab6f311ed0066596a0a10"},"schema_version":"1.0","source":{"id":"2208.11402","kind":"arxiv","version":1}},"canonical_sha256":"5b1ee536ec043174dea1763a2740555158b27793e0de4c7aaa1a756c092afdd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b1ee536ec043174dea1763a2740555158b27793e0de4c7aaa1a756c092afdd0","first_computed_at":"2026-07-05T04:51:14.718657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:14.718657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s1BhxLTl+2TiOe3MZwT12cks1BKqIAgPcg0qJuRsonB48heUSRnPxPruzZe5UdqLCyK0gXP1+t8V71zf33DRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:14.719044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.11402","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5516941729a8bc39ae0eb0630a331b22ebaf8c50988f8c80972dcfb60606f2a8","sha256:10aa113df71ef67fabdd6a51cc7f7775525bb202496f19854e3ee3a29f831f87"],"state_sha256":"76c6c1cc98025f31dfae3662585a52b48e9300324b3085c224de0a165eaa4a4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kffkEEWwEWiux1j3Br0AASo7HbZPg55quHO0leIIQddO6cUiUk3itp4/dE6pvB9FzbUwiC15BEQhrzKyhYooCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:33:22.736898Z","bundle_sha256":"d88e62218681cdd1bd660c35b92d66eae43f46b642cefbdef2d94228bc0f60dc"}}