{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:APOPZVK3ISYJC57GABQ6ZKG5S5","short_pith_number":"pith:APOPZVK3","schema_version":"1.0","canonical_sha256":"03dcfcd55b44b09177e60061eca8dd974796fa55a6f1e63906211f8096002355","source":{"kind":"arxiv","id":"2406.07676","version":1},"attestation_state":"computed","paper":{"title":"FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aalekhya Satya Narayani, Abhishek Dhiman, Karthik Gowda, Swarup Ranjan Behera","submitted_at":"2024-06-11T19:50:50Z","abstract_excerpt":"Audio classification models, particularly the Audio Spectrogram Transformer (AST), play a crucial role in efficient audio analysis. However, optimizing their efficiency without compromising accuracy remains a challenge. In this paper, we introduce FastAST, a framework that integrates Token Merging (ToMe) into the AST framework. FastAST enhances inference speed without requiring extensive retraining by merging similar tokens in audio spectrograms. Furthermore, during training, FastAST brings about significant speed improvements. The experiments indicate that FastAST can increase audio classific"},"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":"2406.07676","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T19:50:50Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"51defa1ec7c6735d42ba925c30007413213b947c506368d65821c2af9519f6f0","abstract_canon_sha256":"abb4db3a17aef3b10f63b2cab390ced7136e064e816cc13f9bc32ca5608cf624"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:36.661420Z","signature_b64":"dTrXOuKptlDu/N9uWTrX15jlFs1dHKfZtQwZBLmrGAFSwc2GJXPE8WTAH3sXc6muvVNehCTmexClc8uDQaBqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03dcfcd55b44b09177e60061eca8dd974796fa55a6f1e63906211f8096002355","last_reissued_at":"2026-07-05T08:30:36.660867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:36.660867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aalekhya Satya Narayani, Abhishek Dhiman, Karthik Gowda, Swarup Ranjan Behera","submitted_at":"2024-06-11T19:50:50Z","abstract_excerpt":"Audio classification models, particularly the Audio Spectrogram Transformer (AST), play a crucial role in efficient audio analysis. However, optimizing their efficiency without compromising accuracy remains a challenge. In this paper, we introduce FastAST, a framework that integrates Token Merging (ToMe) into the AST framework. FastAST enhances inference speed without requiring extensive retraining by merging similar tokens in audio spectrograms. Furthermore, during training, FastAST brings about significant speed improvements. The experiments indicate that FastAST can increase audio classific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07676","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/2406.07676/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":"2406.07676","created_at":"2026-07-05T08:30:36.660928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07676v1","created_at":"2026-07-05T08:30:36.660928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07676","created_at":"2026-07-05T08:30:36.660928+00:00"},{"alias_kind":"pith_short_12","alias_value":"APOPZVK3ISYJ","created_at":"2026-07-05T08:30:36.660928+00:00"},{"alias_kind":"pith_short_16","alias_value":"APOPZVK3ISYJC57G","created_at":"2026-07-05T08:30:36.660928+00:00"},{"alias_kind":"pith_short_8","alias_value":"APOPZVK3","created_at":"2026-07-05T08:30:36.660928+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/APOPZVK3ISYJC57GABQ6ZKG5S5","json":"https://pith.science/pith/APOPZVK3ISYJC57GABQ6ZKG5S5.json","graph_json":"https://pith.science/api/pith-number/APOPZVK3ISYJC57GABQ6ZKG5S5/graph.json","events_json":"https://pith.science/api/pith-number/APOPZVK3ISYJC57GABQ6ZKG5S5/events.json","paper":"https://pith.science/paper/APOPZVK3"},"agent_actions":{"view_html":"https://pith.science/pith/APOPZVK3ISYJC57GABQ6ZKG5S5","download_json":"https://pith.science/pith/APOPZVK3ISYJC57GABQ6ZKG5S5.json","view_paper":"https://pith.science/paper/APOPZVK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07676&json=true","fetch_graph":"https://pith.science/api/pith-number/APOPZVK3ISYJC57GABQ6ZKG5S5/graph.json","fetch_events":"https://pith.science/api/pith-number/APOPZVK3ISYJC57GABQ6ZKG5S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APOPZVK3ISYJC57GABQ6ZKG5S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APOPZVK3ISYJC57GABQ6ZKG5S5/action/storage_attestation","attest_author":"https://pith.science/pith/APOPZVK3ISYJC57GABQ6ZKG5S5/action/author_attestation","sign_citation":"https://pith.science/pith/APOPZVK3ISYJC57GABQ6ZKG5S5/action/citation_signature","submit_replication":"https://pith.science/pith/APOPZVK3ISYJC57GABQ6ZKG5S5/action/replication_record"}},"created_at":"2026-07-05T08:30:36.660928+00:00","updated_at":"2026-07-05T08:30:36.660928+00:00"}