{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PKM6RO7XIHTV4ARAYKDMGRRPCM","short_pith_number":"pith:PKM6RO7X","schema_version":"1.0","canonical_sha256":"7a99e8bbf741e75e0220c286c3462f133368572845b106a4c42d8635e6f866bd","source":{"kind":"arxiv","id":"2209.08310","version":1},"attestation_state":"computed","paper":{"title":"Learning to Weight Samples for Dynamic Early-exiting Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Deng, Chaofei Wang, Gao Huang, Junfen Cao, Shiji Song, Wenhui Huang, Yifan Pu, Yizeng Han, Zihang Lai","submitted_at":"2022-09-17T10:46:32Z","abstract_excerpt":"Early exiting is an effective paradigm for improving the inference efficiency of deep networks. By constructing classifiers with varying resource demands (the exits), such networks allow easy samples to be output at early exits, removing the need for executing deeper layers. While existing works mainly focus on the architectural design of multi-exit networks, the training strategies for such models are largely left unexplored. The current state-of-the-art models treat all samples the same during training. However, the early-exiting behavior during testing has been ignored, leading to a gap bet"},"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":"2209.08310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-17T10:46:32Z","cross_cats_sorted":[],"title_canon_sha256":"e95de770c23015346831f36cf5733da9f04588b458e9e6e66c6370eb3560de81","abstract_canon_sha256":"2e21704be56801d1b3793170e444dab90ffecf15346d2144dcd8d07e4e6d45b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:19.826792Z","signature_b64":"UjSXx6XuC/C0Dw4jTONJXMkzl2uag217t1T2PRsf7YOrNv/hPhCZcm/uW+9mDMir6jqZFHBO523f3q0JFLx8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a99e8bbf741e75e0220c286c3462f133368572845b106a4c42d8635e6f866bd","last_reissued_at":"2026-07-05T04:58:19.826448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:19.826448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Weight Samples for Dynamic Early-exiting Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Deng, Chaofei Wang, Gao Huang, Junfen Cao, Shiji Song, Wenhui Huang, Yifan Pu, Yizeng Han, Zihang Lai","submitted_at":"2022-09-17T10:46:32Z","abstract_excerpt":"Early exiting is an effective paradigm for improving the inference efficiency of deep networks. By constructing classifiers with varying resource demands (the exits), such networks allow easy samples to be output at early exits, removing the need for executing deeper layers. While existing works mainly focus on the architectural design of multi-exit networks, the training strategies for such models are largely left unexplored. The current state-of-the-art models treat all samples the same during training. However, the early-exiting behavior during testing has been ignored, leading to a gap bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08310","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/2209.08310/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":"2209.08310","created_at":"2026-07-05T04:58:19.826505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08310v1","created_at":"2026-07-05T04:58:19.826505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08310","created_at":"2026-07-05T04:58:19.826505+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKM6RO7XIHTV","created_at":"2026-07-05T04:58:19.826505+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKM6RO7XIHTV4ARA","created_at":"2026-07-05T04:58:19.826505+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKM6RO7X","created_at":"2026-07-05T04:58:19.826505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13059","citing_title":"Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKM6RO7XIHTV4ARAYKDMGRRPCM","json":"https://pith.science/pith/PKM6RO7XIHTV4ARAYKDMGRRPCM.json","graph_json":"https://pith.science/api/pith-number/PKM6RO7XIHTV4ARAYKDMGRRPCM/graph.json","events_json":"https://pith.science/api/pith-number/PKM6RO7XIHTV4ARAYKDMGRRPCM/events.json","paper":"https://pith.science/paper/PKM6RO7X"},"agent_actions":{"view_html":"https://pith.science/pith/PKM6RO7XIHTV4ARAYKDMGRRPCM","download_json":"https://pith.science/pith/PKM6RO7XIHTV4ARAYKDMGRRPCM.json","view_paper":"https://pith.science/paper/PKM6RO7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08310&json=true","fetch_graph":"https://pith.science/api/pith-number/PKM6RO7XIHTV4ARAYKDMGRRPCM/graph.json","fetch_events":"https://pith.science/api/pith-number/PKM6RO7XIHTV4ARAYKDMGRRPCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKM6RO7XIHTV4ARAYKDMGRRPCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKM6RO7XIHTV4ARAYKDMGRRPCM/action/storage_attestation","attest_author":"https://pith.science/pith/PKM6RO7XIHTV4ARAYKDMGRRPCM/action/author_attestation","sign_citation":"https://pith.science/pith/PKM6RO7XIHTV4ARAYKDMGRRPCM/action/citation_signature","submit_replication":"https://pith.science/pith/PKM6RO7XIHTV4ARAYKDMGRRPCM/action/replication_record"}},"created_at":"2026-07-05T04:58:19.826505+00:00","updated_at":"2026-07-05T04:58:19.826505+00:00"}