{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HCMXL2AA2QZMPLZDNGHYIR65SB","short_pith_number":"pith:HCMXL2AA","schema_version":"1.0","canonical_sha256":"389975e800d432c7af23698f8447dd904493979a925c1c822250c6a0eb50c338","source":{"kind":"arxiv","id":"2008.06543","version":1},"attestation_state":"computed","paper":{"title":"AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chenchen Liu, Di Wang, Fuxun Yu, Xiang Chen, Yanzhi Wang","submitted_at":"2020-08-14T18:48:13Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) achieved great cognitive performance at the expense of considerable computation load. To relieve the computation load, many optimization works are developed to reduce the model redundancy by identifying and removing insignificant model components, such as weight sparsity and filter pruning. However, these works only evaluate model components' static significance with internal parameter information, ignoring their dynamic interaction with external inputs. With per-input feature activation, the model component significance can dynamically change, and thus the"},"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":"2008.06543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-14T18:48:13Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"20ffbfc486ba7dfdd609ffab7af1dc9f745cd69b4b4c5600ef65fcc4b7d4308f","abstract_canon_sha256":"1b7c6ce5977cb7a818980d564c130975f66a1ec11acde55b06ad62693379070c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:11.088240Z","signature_b64":"NxyCh3nkdBuHXa8TmS03veXjqNPsIuzMlJMQ/O5PSTozFSOUhqtrp1XqrFhSdep+gQ8sFIxxRGupGVaI7gfJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"389975e800d432c7af23698f8447dd904493979a925c1c822250c6a0eb50c338","last_reissued_at":"2026-07-05T01:27:11.087819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:11.087819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chenchen Liu, Di Wang, Fuxun Yu, Xiang Chen, Yanzhi Wang","submitted_at":"2020-08-14T18:48:13Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) achieved great cognitive performance at the expense of considerable computation load. To relieve the computation load, many optimization works are developed to reduce the model redundancy by identifying and removing insignificant model components, such as weight sparsity and filter pruning. However, these works only evaluate model components' static significance with internal parameter information, ignoring their dynamic interaction with external inputs. With per-input feature activation, the model component significance can dynamically change, and thus the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06543","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/2008.06543/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":"2008.06543","created_at":"2026-07-05T01:27:11.087875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06543v1","created_at":"2026-07-05T01:27:11.087875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06543","created_at":"2026-07-05T01:27:11.087875+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCMXL2AA2QZM","created_at":"2026-07-05T01:27:11.087875+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCMXL2AA2QZMPLZD","created_at":"2026-07-05T01:27:11.087875+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCMXL2AA","created_at":"2026-07-05T01:27:11.087875+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/HCMXL2AA2QZMPLZDNGHYIR65SB","json":"https://pith.science/pith/HCMXL2AA2QZMPLZDNGHYIR65SB.json","graph_json":"https://pith.science/api/pith-number/HCMXL2AA2QZMPLZDNGHYIR65SB/graph.json","events_json":"https://pith.science/api/pith-number/HCMXL2AA2QZMPLZDNGHYIR65SB/events.json","paper":"https://pith.science/paper/HCMXL2AA"},"agent_actions":{"view_html":"https://pith.science/pith/HCMXL2AA2QZMPLZDNGHYIR65SB","download_json":"https://pith.science/pith/HCMXL2AA2QZMPLZDNGHYIR65SB.json","view_paper":"https://pith.science/paper/HCMXL2AA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06543&json=true","fetch_graph":"https://pith.science/api/pith-number/HCMXL2AA2QZMPLZDNGHYIR65SB/graph.json","fetch_events":"https://pith.science/api/pith-number/HCMXL2AA2QZMPLZDNGHYIR65SB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCMXL2AA2QZMPLZDNGHYIR65SB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCMXL2AA2QZMPLZDNGHYIR65SB/action/storage_attestation","attest_author":"https://pith.science/pith/HCMXL2AA2QZMPLZDNGHYIR65SB/action/author_attestation","sign_citation":"https://pith.science/pith/HCMXL2AA2QZMPLZDNGHYIR65SB/action/citation_signature","submit_replication":"https://pith.science/pith/HCMXL2AA2QZMPLZDNGHYIR65SB/action/replication_record"}},"created_at":"2026-07-05T01:27:11.087875+00:00","updated_at":"2026-07-05T01:27:11.087875+00:00"}