{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TCM37ODQZFHGSXEDARJFYRERLS","short_pith_number":"pith:TCM37ODQ","schema_version":"1.0","canonical_sha256":"9899bfb870c94e695c8304525c44915cb0a7696d656816dc95b3bcbe6bdf25c3","source":{"kind":"arxiv","id":"2001.00705","version":1},"attestation_state":"computed","paper":{"title":"Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianghao Shen, Pengfei Xu, Yingyan Lin, Yonggan Fu, Yue Wang, Zhangyang Wang","submitted_at":"2020-01-03T03:12:17Z","abstract_excerpt":"While increasingly deep networks are still in general desired for achieving state-of-the-art performance, for many specific inputs a simpler network might already suffice. Existing works exploited this observation by learning to skip convolutional layers in an input-dependent manner. However, we argue their binary decision scheme, i.e., either fully executing or completely bypassing one layer for a specific input, can be enhanced by introducing finer-grained, \"softer\" decisions. We therefore propose a Dynamic Fractional Skipping (DFS) framework. The core idea of DFS is to hypothesize layer-wis"},"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":"2001.00705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-03T03:12:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c581338a13a4707ad4552d38dcec311fad5ed07d335b32c4f7a12f216d8b57d0","abstract_canon_sha256":"a3200315a49498dbe7b58d7a22b1efe083781b0ae79e7b85172df95ccba8f16a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:31.593802Z","signature_b64":"U2xJRZGXCmbty9oluyrvyJZHZgX+XCHsBnv1E+Ep/lWBZYH5u+ZFxYNdfTpn6eERuEutR7t8Nx2nn+BEdHgJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9899bfb870c94e695c8304525c44915cb0a7696d656816dc95b3bcbe6bdf25c3","last_reissued_at":"2026-07-05T00:29:31.593397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:31.593397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianghao Shen, Pengfei Xu, Yingyan Lin, Yonggan Fu, Yue Wang, Zhangyang Wang","submitted_at":"2020-01-03T03:12:17Z","abstract_excerpt":"While increasingly deep networks are still in general desired for achieving state-of-the-art performance, for many specific inputs a simpler network might already suffice. Existing works exploited this observation by learning to skip convolutional layers in an input-dependent manner. However, we argue their binary decision scheme, i.e., either fully executing or completely bypassing one layer for a specific input, can be enhanced by introducing finer-grained, \"softer\" decisions. We therefore propose a Dynamic Fractional Skipping (DFS) framework. The core idea of DFS is to hypothesize layer-wis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00705","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/2001.00705/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":"2001.00705","created_at":"2026-07-05T00:29:31.593445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.00705v1","created_at":"2026-07-05T00:29:31.593445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00705","created_at":"2026-07-05T00:29:31.593445+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCM37ODQZFHG","created_at":"2026-07-05T00:29:31.593445+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCM37ODQZFHGSXED","created_at":"2026-07-05T00:29:31.593445+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCM37ODQ","created_at":"2026-07-05T00:29:31.593445+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/TCM37ODQZFHGSXEDARJFYRERLS","json":"https://pith.science/pith/TCM37ODQZFHGSXEDARJFYRERLS.json","graph_json":"https://pith.science/api/pith-number/TCM37ODQZFHGSXEDARJFYRERLS/graph.json","events_json":"https://pith.science/api/pith-number/TCM37ODQZFHGSXEDARJFYRERLS/events.json","paper":"https://pith.science/paper/TCM37ODQ"},"agent_actions":{"view_html":"https://pith.science/pith/TCM37ODQZFHGSXEDARJFYRERLS","download_json":"https://pith.science/pith/TCM37ODQZFHGSXEDARJFYRERLS.json","view_paper":"https://pith.science/paper/TCM37ODQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.00705&json=true","fetch_graph":"https://pith.science/api/pith-number/TCM37ODQZFHGSXEDARJFYRERLS/graph.json","fetch_events":"https://pith.science/api/pith-number/TCM37ODQZFHGSXEDARJFYRERLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCM37ODQZFHGSXEDARJFYRERLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCM37ODQZFHGSXEDARJFYRERLS/action/storage_attestation","attest_author":"https://pith.science/pith/TCM37ODQZFHGSXEDARJFYRERLS/action/author_attestation","sign_citation":"https://pith.science/pith/TCM37ODQZFHGSXEDARJFYRERLS/action/citation_signature","submit_replication":"https://pith.science/pith/TCM37ODQZFHGSXEDARJFYRERLS/action/replication_record"}},"created_at":"2026-07-05T00:29:31.593445+00:00","updated_at":"2026-07-05T00:29:31.593445+00:00"}