{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BHAFHJP6F4DSXZEOVLIGJBAO6K","short_pith_number":"pith:BHAFHJP6","schema_version":"1.0","canonical_sha256":"09c053a5fe2f072be48eaad064840ef28fc67c32218dfec25c83e3e57b428ee4","source":{"kind":"arxiv","id":"2201.04021","version":1},"attestation_state":"computed","paper":{"title":"Optimization Planning for 3D ConvNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong-Wah Ngo, Tao Mei, Ting Yao, Zhaofan Qiu","submitted_at":"2022-01-11T16:13:31Z","abstract_excerpt":"It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video clips and then is followed by learning long-term temporal dependency using lengthy clips, while gradually decaying the learning rate from high to low as training progresses. The fact that such process comes along with several heuristic settings motivates the study to seek an optimal \"path\" to automate the entire training. In this paper, we decompose the path"},"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":"2201.04021","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-11T16:13:31Z","cross_cats_sorted":[],"title_canon_sha256":"b119c8306cb85ab32a0ed2b307ed41bd698c7f8ed8dfef26e8972537697d67be","abstract_canon_sha256":"201d385744a2ebade5a81203835b49342908db9bef52c863ed9748cf173aabf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:36.606461Z","signature_b64":"iUPdabM43TVK0aJNMhgFcgcBwCDLTxLBPGEEbNUsJZa9kR24aQowEeWkTanxuKC3bQ3OOrna/T4+kP+Fw2QsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09c053a5fe2f072be48eaad064840ef28fc67c32218dfec25c83e3e57b428ee4","last_reissued_at":"2026-07-05T03:47:36.606076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:36.606076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimization Planning for 3D ConvNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong-Wah Ngo, Tao Mei, Ting Yao, Zhaofan Qiu","submitted_at":"2022-01-11T16:13:31Z","abstract_excerpt":"It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video clips and then is followed by learning long-term temporal dependency using lengthy clips, while gradually decaying the learning rate from high to low as training progresses. The fact that such process comes along with several heuristic settings motivates the study to seek an optimal \"path\" to automate the entire training. In this paper, we decompose the path"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04021","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/2201.04021/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":"2201.04021","created_at":"2026-07-05T03:47:36.606130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.04021v1","created_at":"2026-07-05T03:47:36.606130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04021","created_at":"2026-07-05T03:47:36.606130+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHAFHJP6F4DS","created_at":"2026-07-05T03:47:36.606130+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHAFHJP6F4DSXZEO","created_at":"2026-07-05T03:47:36.606130+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHAFHJP6","created_at":"2026-07-05T03:47:36.606130+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/BHAFHJP6F4DSXZEOVLIGJBAO6K","json":"https://pith.science/pith/BHAFHJP6F4DSXZEOVLIGJBAO6K.json","graph_json":"https://pith.science/api/pith-number/BHAFHJP6F4DSXZEOVLIGJBAO6K/graph.json","events_json":"https://pith.science/api/pith-number/BHAFHJP6F4DSXZEOVLIGJBAO6K/events.json","paper":"https://pith.science/paper/BHAFHJP6"},"agent_actions":{"view_html":"https://pith.science/pith/BHAFHJP6F4DSXZEOVLIGJBAO6K","download_json":"https://pith.science/pith/BHAFHJP6F4DSXZEOVLIGJBAO6K.json","view_paper":"https://pith.science/paper/BHAFHJP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.04021&json=true","fetch_graph":"https://pith.science/api/pith-number/BHAFHJP6F4DSXZEOVLIGJBAO6K/graph.json","fetch_events":"https://pith.science/api/pith-number/BHAFHJP6F4DSXZEOVLIGJBAO6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHAFHJP6F4DSXZEOVLIGJBAO6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHAFHJP6F4DSXZEOVLIGJBAO6K/action/storage_attestation","attest_author":"https://pith.science/pith/BHAFHJP6F4DSXZEOVLIGJBAO6K/action/author_attestation","sign_citation":"https://pith.science/pith/BHAFHJP6F4DSXZEOVLIGJBAO6K/action/citation_signature","submit_replication":"https://pith.science/pith/BHAFHJP6F4DSXZEOVLIGJBAO6K/action/replication_record"}},"created_at":"2026-07-05T03:47:36.606130+00:00","updated_at":"2026-07-05T03:47:36.606130+00:00"}