{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:73KG5W6SI2XDGSYQQBIMO4MCAE","short_pith_number":"pith:73KG5W6S","schema_version":"1.0","canonical_sha256":"fed46edbd246ae334b108050c7718201326739b5461e636394fdf9906132ffd0","source":{"kind":"arxiv","id":"1711.04022","version":2},"attestation_state":"computed","paper":{"title":"Deep Within-Class Covariance Analysis for Robust Audio Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Gerhard Widmer, Hamid Eghbal-zadeh, Matthias Dorfer","submitted_at":"2017-11-10T21:39:12Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) can learn effective features, though have been shown to suffer from a performance drop when the distribution of the data changes from training to test data. In this paper we analyze the internal representations of CNNs and observe that the representations of unseen data in each class, spread more (with higher variance) in the embedding space of the CNN compared to representations of the training data. More importantly, this difference is more extreme if the unseen data comes from a shifted distribution. Based on this observation, we objectively evaluate the"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1711.04022","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-10T21:39:12Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"875549456b76454c946e0649d9656156a786da0bb36dd5f9e9ad2a727a845cd6","abstract_canon_sha256":"fed0b5aae1a096cef59d53c8e0e0da4f59ddf8ce6f1dc4f46b173ea5b0c04dea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:33.116761Z","signature_b64":"VjU7LcNoWZqATNtBbf5myvtoVnId3srLGVhJ1lmzMr+yEBPnZd0PiONRJCVsK/iDnkWzErbn6AThcxNViqxnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fed46edbd246ae334b108050c7718201326739b5461e636394fdf9906132ffd0","last_reissued_at":"2026-05-17T23:59:33.116228Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:33.116228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Within-Class Covariance Analysis for Robust Audio Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Gerhard Widmer, Hamid Eghbal-zadeh, Matthias Dorfer","submitted_at":"2017-11-10T21:39:12Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) can learn effective features, though have been shown to suffer from a performance drop when the distribution of the data changes from training to test data. In this paper we analyze the internal representations of CNNs and observe that the representations of unseen data in each class, spread more (with higher variance) in the embedding space of the CNN compared to representations of the training data. More importantly, this difference is more extreme if the unseen data comes from a shifted distribution. Based on this observation, we objectively evaluate the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04022","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1711.04022","created_at":"2026-05-17T23:59:33.116326+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04022v2","created_at":"2026-05-17T23:59:33.116326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04022","created_at":"2026-05-17T23:59:33.116326+00:00"},{"alias_kind":"pith_short_12","alias_value":"73KG5W6SI2XD","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"73KG5W6SI2XDGSYQ","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"73KG5W6S","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73KG5W6SI2XDGSYQQBIMO4MCAE","json":"https://pith.science/pith/73KG5W6SI2XDGSYQQBIMO4MCAE.json","graph_json":"https://pith.science/api/pith-number/73KG5W6SI2XDGSYQQBIMO4MCAE/graph.json","events_json":"https://pith.science/api/pith-number/73KG5W6SI2XDGSYQQBIMO4MCAE/events.json","paper":"https://pith.science/paper/73KG5W6S"},"agent_actions":{"view_html":"https://pith.science/pith/73KG5W6SI2XDGSYQQBIMO4MCAE","download_json":"https://pith.science/pith/73KG5W6SI2XDGSYQQBIMO4MCAE.json","view_paper":"https://pith.science/paper/73KG5W6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04022&json=true","fetch_graph":"https://pith.science/api/pith-number/73KG5W6SI2XDGSYQQBIMO4MCAE/graph.json","fetch_events":"https://pith.science/api/pith-number/73KG5W6SI2XDGSYQQBIMO4MCAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73KG5W6SI2XDGSYQQBIMO4MCAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73KG5W6SI2XDGSYQQBIMO4MCAE/action/storage_attestation","attest_author":"https://pith.science/pith/73KG5W6SI2XDGSYQQBIMO4MCAE/action/author_attestation","sign_citation":"https://pith.science/pith/73KG5W6SI2XDGSYQQBIMO4MCAE/action/citation_signature","submit_replication":"https://pith.science/pith/73KG5W6SI2XDGSYQQBIMO4MCAE/action/replication_record"}},"created_at":"2026-05-17T23:59:33.116326+00:00","updated_at":"2026-05-17T23:59:33.116326+00:00"}