{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CBPOB2EO2CBDGSE2BSLEMUILAL","short_pith_number":"pith:CBPOB2EO","schema_version":"1.0","canonical_sha256":"105ee0e88ed08233489a0c9646510b02c3943648a7ee41d5b035e4f55b6cb065","source":{"kind":"arxiv","id":"1911.07033","version":2},"attestation_state":"computed","paper":{"title":"S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bingzhe Wu, Guangyu Sun, Shiwan Zhao, Weichen Bi, Zheng Liang, Zhihang Yuan","submitted_at":"2019-11-16T13:49:44Z","abstract_excerpt":"Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight pruning), dynamic inference adaptively adjusts the inference process according to each input sample, which can considerably reduce the computational cost on \"easy\" samples while maintaining the overall model performance. In this paper, we introduce a general framework, S2DNAS, which can transform various static CNN models to support dynamic inference via neural architecture search. To this end, based on a given CNN mo"},"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":"1911.07033","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-16T13:49:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"44d1c392029d832aeb2bbea03d782af63c19221a24fb18c6eeaf6b173599b71c","abstract_canon_sha256":"70ba23b6491f2bff2a960c6db6a6125278d3e682ed84e1db135d43f223d8e780"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:44.611025Z","signature_b64":"jCXNWc7ClDrTQEo5VwokY7s5t9NXSHFyB14D9GAQiO5CBS7/2AVzd4VYq01EnrNYPdjtGBDct4iZ5k5vF8+oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"105ee0e88ed08233489a0c9646510b02c3943648a7ee41d5b035e4f55b6cb065","last_reissued_at":"2026-07-05T00:26:44.610581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:44.610581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bingzhe Wu, Guangyu Sun, Shiwan Zhao, Weichen Bi, Zheng Liang, Zhihang Yuan","submitted_at":"2019-11-16T13:49:44Z","abstract_excerpt":"Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight pruning), dynamic inference adaptively adjusts the inference process according to each input sample, which can considerably reduce the computational cost on \"easy\" samples while maintaining the overall model performance. In this paper, we introduce a general framework, S2DNAS, which can transform various static CNN models to support dynamic inference via neural architecture search. To this end, based on a given CNN mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07033","kind":"arxiv","version":2},"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/1911.07033/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":"1911.07033","created_at":"2026-07-05T00:26:44.610648+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07033v2","created_at":"2026-07-05T00:26:44.610648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07033","created_at":"2026-07-05T00:26:44.610648+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBPOB2EO2CBD","created_at":"2026-07-05T00:26:44.610648+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBPOB2EO2CBDGSE2","created_at":"2026-07-05T00:26:44.610648+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBPOB2EO","created_at":"2026-07-05T00:26:44.610648+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/CBPOB2EO2CBDGSE2BSLEMUILAL","json":"https://pith.science/pith/CBPOB2EO2CBDGSE2BSLEMUILAL.json","graph_json":"https://pith.science/api/pith-number/CBPOB2EO2CBDGSE2BSLEMUILAL/graph.json","events_json":"https://pith.science/api/pith-number/CBPOB2EO2CBDGSE2BSLEMUILAL/events.json","paper":"https://pith.science/paper/CBPOB2EO"},"agent_actions":{"view_html":"https://pith.science/pith/CBPOB2EO2CBDGSE2BSLEMUILAL","download_json":"https://pith.science/pith/CBPOB2EO2CBDGSE2BSLEMUILAL.json","view_paper":"https://pith.science/paper/CBPOB2EO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07033&json=true","fetch_graph":"https://pith.science/api/pith-number/CBPOB2EO2CBDGSE2BSLEMUILAL/graph.json","fetch_events":"https://pith.science/api/pith-number/CBPOB2EO2CBDGSE2BSLEMUILAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBPOB2EO2CBDGSE2BSLEMUILAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBPOB2EO2CBDGSE2BSLEMUILAL/action/storage_attestation","attest_author":"https://pith.science/pith/CBPOB2EO2CBDGSE2BSLEMUILAL/action/author_attestation","sign_citation":"https://pith.science/pith/CBPOB2EO2CBDGSE2BSLEMUILAL/action/citation_signature","submit_replication":"https://pith.science/pith/CBPOB2EO2CBDGSE2BSLEMUILAL/action/replication_record"}},"created_at":"2026-07-05T00:26:44.610648+00:00","updated_at":"2026-07-05T00:26:44.610648+00:00"}