{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RL47IKWS7J56WK2RYQJ6B26I7T","short_pith_number":"pith:RL47IKWS","schema_version":"1.0","canonical_sha256":"8af9f42ad2fa7beb2b51c413e0ebc8fcf99d7646c5e2e1d8d82980c4ed573411","source":{"kind":"arxiv","id":"2508.21243","version":1},"attestation_state":"computed","paper":{"title":"Full-Frequency Temporal Patching and Structured Masking for Enhanced Audio Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Aditya Makineni, Baocheng Geng, Qing Tian","submitted_at":"2025-08-28T22:13:20Z","abstract_excerpt":"Transformers and State-Space Models (SSMs) have advanced audio classification by modeling spectrograms as sequences of patches. However, existing models such as the Audio Spectrogram Transformer (AST) and Audio Mamba (AuM) adopt square patching from computer vision, which disrupts continuous frequency patterns and produces an excessive number of patches, slowing training, and increasing computation. We propose Full-Frequency Temporal Patching (FFTP), a patching strategy that better matches the time-frequency asymmetry of spectrograms by spanning full frequency bands with localized temporal con"},"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":"2508.21243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-28T22:13:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1bdf13ea6fab12d9a11312cfaf974048927beef1e237d2588dd69c0431d123a6","abstract_canon_sha256":"22a90ade97f0d3e5b6c8aef73df30419eaf01965a3b866549abef789c50ab237"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:30.788424Z","signature_b64":"c7I4hWJf4YhYVrA7Njj2dIJ5pVjb5UKd2xzMH6Qs6SsmykQaUEHOYxbjwzZ35xYkhQ7gheRqXSNPHBzODMGyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8af9f42ad2fa7beb2b51c413e0ebc8fcf99d7646c5e2e1d8d82980c4ed573411","last_reissued_at":"2026-07-05T12:01:30.787870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:30.787870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Full-Frequency Temporal Patching and Structured Masking for Enhanced Audio Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Aditya Makineni, Baocheng Geng, Qing Tian","submitted_at":"2025-08-28T22:13:20Z","abstract_excerpt":"Transformers and State-Space Models (SSMs) have advanced audio classification by modeling spectrograms as sequences of patches. However, existing models such as the Audio Spectrogram Transformer (AST) and Audio Mamba (AuM) adopt square patching from computer vision, which disrupts continuous frequency patterns and produces an excessive number of patches, slowing training, and increasing computation. We propose Full-Frequency Temporal Patching (FFTP), a patching strategy that better matches the time-frequency asymmetry of spectrograms by spanning full frequency bands with localized temporal con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21243","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/2508.21243/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":"2508.21243","created_at":"2026-07-05T12:01:30.787930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21243v1","created_at":"2026-07-05T12:01:30.787930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21243","created_at":"2026-07-05T12:01:30.787930+00:00"},{"alias_kind":"pith_short_12","alias_value":"RL47IKWS7J56","created_at":"2026-07-05T12:01:30.787930+00:00"},{"alias_kind":"pith_short_16","alias_value":"RL47IKWS7J56WK2R","created_at":"2026-07-05T12:01:30.787930+00:00"},{"alias_kind":"pith_short_8","alias_value":"RL47IKWS","created_at":"2026-07-05T12:01:30.787930+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/RL47IKWS7J56WK2RYQJ6B26I7T","json":"https://pith.science/pith/RL47IKWS7J56WK2RYQJ6B26I7T.json","graph_json":"https://pith.science/api/pith-number/RL47IKWS7J56WK2RYQJ6B26I7T/graph.json","events_json":"https://pith.science/api/pith-number/RL47IKWS7J56WK2RYQJ6B26I7T/events.json","paper":"https://pith.science/paper/RL47IKWS"},"agent_actions":{"view_html":"https://pith.science/pith/RL47IKWS7J56WK2RYQJ6B26I7T","download_json":"https://pith.science/pith/RL47IKWS7J56WK2RYQJ6B26I7T.json","view_paper":"https://pith.science/paper/RL47IKWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21243&json=true","fetch_graph":"https://pith.science/api/pith-number/RL47IKWS7J56WK2RYQJ6B26I7T/graph.json","fetch_events":"https://pith.science/api/pith-number/RL47IKWS7J56WK2RYQJ6B26I7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RL47IKWS7J56WK2RYQJ6B26I7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RL47IKWS7J56WK2RYQJ6B26I7T/action/storage_attestation","attest_author":"https://pith.science/pith/RL47IKWS7J56WK2RYQJ6B26I7T/action/author_attestation","sign_citation":"https://pith.science/pith/RL47IKWS7J56WK2RYQJ6B26I7T/action/citation_signature","submit_replication":"https://pith.science/pith/RL47IKWS7J56WK2RYQJ6B26I7T/action/replication_record"}},"created_at":"2026-07-05T12:01:30.787930+00:00","updated_at":"2026-07-05T12:01:30.787930+00:00"}