{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TEHJRWNN5J26KP26GEDINFVUME","short_pith_number":"pith:TEHJRWNN","schema_version":"1.0","canonical_sha256":"990e98d9adea75e53f5e31068696b46107c026803aa7dc8af5f6bd81f0a1bb0a","source":{"kind":"arxiv","id":"1907.05982","version":1},"attestation_state":"computed","paper":{"title":"Learning Complex Basis Functions for Invariant Representations of Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Arzt, Monika D\\\"orfler, Stefan Lattner","submitted_at":"2019-07-13T00:23:26Z","abstract_excerpt":"Learning features from data has shown to be more successful than using hand-crafted features for many machine learning tasks. In music information retrieval (MIR), features learned from windowed spectrograms are highly variant to transformations like transposition or time-shift. Such variances are undesirable when they are irrelevant for the respective MIR task. We propose an architecture called Complex Autoencoder (CAE) which learns features invariant to orthogonal transformations. Mapping signals onto complex basis functions learned by the CAE results in a transformation-invariant \"magnitude"},"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":"1907.05982","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-07-13T00:23:26Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"56de52b7798ff376fc3a5b0ff00bc9484b624d1782136e9cce7e06654e94ae34","abstract_canon_sha256":"f8214da31f28cf4cfa6acad8a1f95ba00ba61b5f635a988f5de173399de64098"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:42.788337Z","signature_b64":"wgXRvVrt4WgbFw+3UxFHscI0BdZe9R/BsuVKDLezFSrrNsJMeFdgzGEuBjUWzZRI6L7wy3qyl/4Mz/ugXN57DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"990e98d9adea75e53f5e31068696b46107c026803aa7dc8af5f6bd81f0a1bb0a","last_reissued_at":"2026-05-17T23:40:42.787834Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:42.787834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Complex Basis Functions for Invariant Representations of Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Arzt, Monika D\\\"orfler, Stefan Lattner","submitted_at":"2019-07-13T00:23:26Z","abstract_excerpt":"Learning features from data has shown to be more successful than using hand-crafted features for many machine learning tasks. In music information retrieval (MIR), features learned from windowed spectrograms are highly variant to transformations like transposition or time-shift. Such variances are undesirable when they are irrelevant for the respective MIR task. We propose an architecture called Complex Autoencoder (CAE) which learns features invariant to orthogonal transformations. Mapping signals onto complex basis functions learned by the CAE results in a transformation-invariant \"magnitude"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05982","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":""},"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":"1907.05982","created_at":"2026-05-17T23:40:42.787905+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05982v1","created_at":"2026-05-17T23:40:42.787905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05982","created_at":"2026-05-17T23:40:42.787905+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEHJRWNN5J26","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEHJRWNN5J26KP26","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEHJRWNN","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05982","citing_title":"Learning Complex Basis Functions for Invariant Representations of Audio","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEHJRWNN5J26KP26GEDINFVUME","json":"https://pith.science/pith/TEHJRWNN5J26KP26GEDINFVUME.json","graph_json":"https://pith.science/api/pith-number/TEHJRWNN5J26KP26GEDINFVUME/graph.json","events_json":"https://pith.science/api/pith-number/TEHJRWNN5J26KP26GEDINFVUME/events.json","paper":"https://pith.science/paper/TEHJRWNN"},"agent_actions":{"view_html":"https://pith.science/pith/TEHJRWNN5J26KP26GEDINFVUME","download_json":"https://pith.science/pith/TEHJRWNN5J26KP26GEDINFVUME.json","view_paper":"https://pith.science/paper/TEHJRWNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05982&json=true","fetch_graph":"https://pith.science/api/pith-number/TEHJRWNN5J26KP26GEDINFVUME/graph.json","fetch_events":"https://pith.science/api/pith-number/TEHJRWNN5J26KP26GEDINFVUME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEHJRWNN5J26KP26GEDINFVUME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEHJRWNN5J26KP26GEDINFVUME/action/storage_attestation","attest_author":"https://pith.science/pith/TEHJRWNN5J26KP26GEDINFVUME/action/author_attestation","sign_citation":"https://pith.science/pith/TEHJRWNN5J26KP26GEDINFVUME/action/citation_signature","submit_replication":"https://pith.science/pith/TEHJRWNN5J26KP26GEDINFVUME/action/replication_record"}},"created_at":"2026-05-17T23:40:42.787905+00:00","updated_at":"2026-05-17T23:40:42.787905+00:00"}