{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YPVL5ODCS645CM3L3ODHKR6EVZ","short_pith_number":"pith:YPVL5ODC","schema_version":"1.0","canonical_sha256":"c3eabeb86297b9d1336bdb867547c4ae76951d284a2971cde7d257ad09b54c1c","source":{"kind":"arxiv","id":"2508.02291","version":3},"attestation_state":"computed","paper":{"title":"FAIR-Pruner: A Flexible Framework for Automatic Layer-Wise Pruning via Tolerance of Difference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bingyi Jing, Chengyao Yu, Chenqing Lin, Kim Khoa Nguyen, Mohamed Cheriet, Mostafa Hussien, Ruixing Ming","submitted_at":"2025-08-04T10:59:07Z","abstract_excerpt":"Structured pruning is a standard tool for compressing deep neural networks, but its practical performance depends on how sparsity is allocated across layers. We propose FAIR-Pruner, a search-free framework for adaptive layer-wise structured pruning. FAIR-Pruner uses two within-layer rankings: a removal-oriented signal that proposes candidate units and a protection-oriented signal that identifies task-sensitive units. Its core component, Tolerance of Difference (ToD), measures the overlap between the removal prefix and the protected tail, and uses a shared tolerance level to induce non-uniform "},"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":"2508.02291","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T10:59:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21be8ed0cfd9783340f950c87ff111456993650945992d880181dcb070f28306","abstract_canon_sha256":"86a2aaad1190d0fc2e377dbdea0eb12244aa01be9b7e6583c53f196b562e42d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:07.437717Z","signature_b64":"WQqAwzq/L2PGqDgRoCqnXPeuvriI9tARYTOABR6PrdQLotPwPbxX1sKfE6VOE+TwRixHAibfE+3z4dweDCcuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3eabeb86297b9d1336bdb867547c4ae76951d284a2971cde7d257ad09b54c1c","last_reissued_at":"2026-05-21T01:05:07.436881Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:07.436881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAIR-Pruner: A Flexible Framework for Automatic Layer-Wise Pruning via Tolerance of Difference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bingyi Jing, Chengyao Yu, Chenqing Lin, Kim Khoa Nguyen, Mohamed Cheriet, Mostafa Hussien, Ruixing Ming","submitted_at":"2025-08-04T10:59:07Z","abstract_excerpt":"Structured pruning is a standard tool for compressing deep neural networks, but its practical performance depends on how sparsity is allocated across layers. We propose FAIR-Pruner, a search-free framework for adaptive layer-wise structured pruning. FAIR-Pruner uses two within-layer rankings: a removal-oriented signal that proposes candidate units and a protection-oriented signal that identifies task-sensitive units. Its core component, Tolerance of Difference (ToD), measures the overlap between the removal prefix and the protected tail, and uses a shared tolerance level to induce non-uniform "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02291","kind":"arxiv","version":3},"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/2508.02291/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":"2508.02291","created_at":"2026-05-21T01:05:07.437036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02291v3","created_at":"2026-05-21T01:05:07.437036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02291","created_at":"2026-05-21T01:05:07.437036+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPVL5ODCS645","created_at":"2026-05-21T01:05:07.437036+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPVL5ODCS645CM3L","created_at":"2026-05-21T01:05:07.437036+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPVL5ODC","created_at":"2026-05-21T01:05:07.437036+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/YPVL5ODCS645CM3L3ODHKR6EVZ","json":"https://pith.science/pith/YPVL5ODCS645CM3L3ODHKR6EVZ.json","graph_json":"https://pith.science/api/pith-number/YPVL5ODCS645CM3L3ODHKR6EVZ/graph.json","events_json":"https://pith.science/api/pith-number/YPVL5ODCS645CM3L3ODHKR6EVZ/events.json","paper":"https://pith.science/paper/YPVL5ODC"},"agent_actions":{"view_html":"https://pith.science/pith/YPVL5ODCS645CM3L3ODHKR6EVZ","download_json":"https://pith.science/pith/YPVL5ODCS645CM3L3ODHKR6EVZ.json","view_paper":"https://pith.science/paper/YPVL5ODC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02291&json=true","fetch_graph":"https://pith.science/api/pith-number/YPVL5ODCS645CM3L3ODHKR6EVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YPVL5ODCS645CM3L3ODHKR6EVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPVL5ODCS645CM3L3ODHKR6EVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPVL5ODCS645CM3L3ODHKR6EVZ/action/storage_attestation","attest_author":"https://pith.science/pith/YPVL5ODCS645CM3L3ODHKR6EVZ/action/author_attestation","sign_citation":"https://pith.science/pith/YPVL5ODCS645CM3L3ODHKR6EVZ/action/citation_signature","submit_replication":"https://pith.science/pith/YPVL5ODCS645CM3L3ODHKR6EVZ/action/replication_record"}},"created_at":"2026-05-21T01:05:07.437036+00:00","updated_at":"2026-05-21T01:05:07.437036+00:00"}