{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SGXVOQE3J7D2O2M4KQ2SLFTOMJ","short_pith_number":"pith:SGXVOQE3","schema_version":"1.0","canonical_sha256":"91af57409b4fc7a7699c543525966e6273e4d78ade77c02ad96f42beaaf20576","source":{"kind":"arxiv","id":"1908.06294","version":1},"attestation_state":"computed","paper":{"title":"Improved Techniques for Training Adaptive Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Huang, Hao Li, Hong Zhang, Ruigang Yang, Xiaojuan Qi","submitted_at":"2019-08-17T10:53:53Z","abstract_excerpt":"Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust their structure conditioned on each input. While existing research on adaptive inference mainly focuses on designing more advanced architectures, this paper investigates how to train such networks more effectively. Specifically, we consider a typical adaptive deep network with multiple intermediate classifiers. We present three techniques to improve its train"},"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":"1908.06294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-17T10:53:53Z","cross_cats_sorted":[],"title_canon_sha256":"97fd0445efeeedb540606f2dd28a330b7e9a2342be4ab6917ba0304b66a64ff7","abstract_canon_sha256":"5cc510d2f2201d671c6ef37d706e5848815eaac3816c6885b24118a29d1c445c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:14.327186Z","signature_b64":"FpDsciGWtr1wJJQ37+nKJ3CFeLoJF379j/6gVR/ovE4XzEXO25+k3MsfYOu8RlD0wrJms15iWO+pBrI7vdOfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91af57409b4fc7a7699c543525966e6273e4d78ade77c02ad96f42beaaf20576","last_reissued_at":"2026-07-04T23:58:14.326750Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:14.326750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Techniques for Training Adaptive Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Huang, Hao Li, Hong Zhang, Ruigang Yang, Xiaojuan Qi","submitted_at":"2019-08-17T10:53:53Z","abstract_excerpt":"Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust their structure conditioned on each input. While existing research on adaptive inference mainly focuses on designing more advanced architectures, this paper investigates how to train such networks more effectively. Specifically, we consider a typical adaptive deep network with multiple intermediate classifiers. We present three techniques to improve its train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06294","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/1908.06294/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":"1908.06294","created_at":"2026-07-04T23:58:14.326821+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06294v1","created_at":"2026-07-04T23:58:14.326821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06294","created_at":"2026-07-04T23:58:14.326821+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGXVOQE3J7D2","created_at":"2026-07-04T23:58:14.326821+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGXVOQE3J7D2O2M4","created_at":"2026-07-04T23:58:14.326821+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGXVOQE3","created_at":"2026-07-04T23:58:14.326821+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/SGXVOQE3J7D2O2M4KQ2SLFTOMJ","json":"https://pith.science/pith/SGXVOQE3J7D2O2M4KQ2SLFTOMJ.json","graph_json":"https://pith.science/api/pith-number/SGXVOQE3J7D2O2M4KQ2SLFTOMJ/graph.json","events_json":"https://pith.science/api/pith-number/SGXVOQE3J7D2O2M4KQ2SLFTOMJ/events.json","paper":"https://pith.science/paper/SGXVOQE3"},"agent_actions":{"view_html":"https://pith.science/pith/SGXVOQE3J7D2O2M4KQ2SLFTOMJ","download_json":"https://pith.science/pith/SGXVOQE3J7D2O2M4KQ2SLFTOMJ.json","view_paper":"https://pith.science/paper/SGXVOQE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06294&json=true","fetch_graph":"https://pith.science/api/pith-number/SGXVOQE3J7D2O2M4KQ2SLFTOMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SGXVOQE3J7D2O2M4KQ2SLFTOMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGXVOQE3J7D2O2M4KQ2SLFTOMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGXVOQE3J7D2O2M4KQ2SLFTOMJ/action/storage_attestation","attest_author":"https://pith.science/pith/SGXVOQE3J7D2O2M4KQ2SLFTOMJ/action/author_attestation","sign_citation":"https://pith.science/pith/SGXVOQE3J7D2O2M4KQ2SLFTOMJ/action/citation_signature","submit_replication":"https://pith.science/pith/SGXVOQE3J7D2O2M4KQ2SLFTOMJ/action/replication_record"}},"created_at":"2026-07-04T23:58:14.326821+00:00","updated_at":"2026-07-04T23:58:14.326821+00:00"}