{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LQV3Y4CBCCVRCJA3FJ5JBYZLHA","short_pith_number":"pith:LQV3Y4CB","schema_version":"1.0","canonical_sha256":"5c2bbc704110ab11241b2a7a90e32b381991369699d09ab01bffb47acf76747a","source":{"kind":"arxiv","id":"2506.21440","version":1},"attestation_state":"computed","paper":{"title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Axel Barrau, Laurent Massouli\\'e, Maxime Leiber, Sylvain Meignen, Yosra Marnissi","submitted_at":"2025-06-26T16:24:27Z","abstract_excerpt":"The short-time Fourier transform (STFT) is widely used for analyzing non-stationary signals. However, its performance is highly sensitive to its parameters, and manual or heuristic tuning often yields suboptimal results. To overcome this limitation, we propose a unified differentiable formulation of the STFT that enables gradient-based optimization of its parameters. This approach addresses the limitations of traditional STFT parameter tuning methods, which often rely on computationally intensive discrete searches. It enables fine-tuning of the time-frequency representation (TFR) based on any "},"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":"2506.21440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-26T16:24:27Z","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"d7d369d13b44c486406baae383b0201c16c06a518c09cedd9fa490588c5674a2","abstract_canon_sha256":"cdcd91585e12f68c24e10bc701cc7693a221eb77e46d731d3873e60010381697"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:45.922762Z","signature_b64":"Kq12z/KZ+MjRKCu0BL5lWKRMWwpzNpjKZfKIEilUPKFUoFCpj9bfem5zd5GDU1DDZOGWg7ygI49HHDqdBS1kDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c2bbc704110ab11241b2a7a90e32b381991369699d09ab01bffb47acf76747a","last_reissued_at":"2026-07-05T11:27:45.922238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:45.922238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Axel Barrau, Laurent Massouli\\'e, Maxime Leiber, Sylvain Meignen, Yosra Marnissi","submitted_at":"2025-06-26T16:24:27Z","abstract_excerpt":"The short-time Fourier transform (STFT) is widely used for analyzing non-stationary signals. However, its performance is highly sensitive to its parameters, and manual or heuristic tuning often yields suboptimal results. To overcome this limitation, we propose a unified differentiable formulation of the STFT that enables gradient-based optimization of its parameters. This approach addresses the limitations of traditional STFT parameter tuning methods, which often rely on computationally intensive discrete searches. It enables fine-tuning of the time-frequency representation (TFR) based on any "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21440","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/2506.21440/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.21440","created_at":"2026-07-05T11:27:45.922301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21440v1","created_at":"2026-07-05T11:27:45.922301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21440","created_at":"2026-07-05T11:27:45.922301+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQV3Y4CBCCVR","created_at":"2026-07-05T11:27:45.922301+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQV3Y4CBCCVRCJA3","created_at":"2026-07-05T11:27:45.922301+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQV3Y4CB","created_at":"2026-07-05T11:27:45.922301+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/LQV3Y4CBCCVRCJA3FJ5JBYZLHA","json":"https://pith.science/pith/LQV3Y4CBCCVRCJA3FJ5JBYZLHA.json","graph_json":"https://pith.science/api/pith-number/LQV3Y4CBCCVRCJA3FJ5JBYZLHA/graph.json","events_json":"https://pith.science/api/pith-number/LQV3Y4CBCCVRCJA3FJ5JBYZLHA/events.json","paper":"https://pith.science/paper/LQV3Y4CB"},"agent_actions":{"view_html":"https://pith.science/pith/LQV3Y4CBCCVRCJA3FJ5JBYZLHA","download_json":"https://pith.science/pith/LQV3Y4CBCCVRCJA3FJ5JBYZLHA.json","view_paper":"https://pith.science/paper/LQV3Y4CB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21440&json=true","fetch_graph":"https://pith.science/api/pith-number/LQV3Y4CBCCVRCJA3FJ5JBYZLHA/graph.json","fetch_events":"https://pith.science/api/pith-number/LQV3Y4CBCCVRCJA3FJ5JBYZLHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQV3Y4CBCCVRCJA3FJ5JBYZLHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQV3Y4CBCCVRCJA3FJ5JBYZLHA/action/storage_attestation","attest_author":"https://pith.science/pith/LQV3Y4CBCCVRCJA3FJ5JBYZLHA/action/author_attestation","sign_citation":"https://pith.science/pith/LQV3Y4CBCCVRCJA3FJ5JBYZLHA/action/citation_signature","submit_replication":"https://pith.science/pith/LQV3Y4CBCCVRCJA3FJ5JBYZLHA/action/replication_record"}},"created_at":"2026-07-05T11:27:45.922301+00:00","updated_at":"2026-07-05T11:27:45.922301+00:00"}