{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZOK66OHQB2QDB7FBPBP6ERQOKY","short_pith_number":"pith:ZOK66OHQ","schema_version":"1.0","canonical_sha256":"cb95ef38f00ea030fca1785fe2460e5619a9865c8a53e3f789ca7d729eef0910","source":{"kind":"arxiv","id":"2211.04800","version":1},"attestation_state":"computed","paper":{"title":"Designing Network Design Strategies Through Gradient Path Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chien-Yao Wang, Hong-Yuan Mark Liao, I-Hau Yeh","submitted_at":"2022-11-09T10:51:57Z","abstract_excerpt":"Designing a high-efficiency and high-quality expressive network architecture has always been the most important research topic in the field of deep learning. Most of today's network design strategies focus on how to integrate features extracted from different layers, and how to design computing units to effectively extract these features, thereby enhancing the expressiveness of the network. This paper proposes a new network design strategy, i.e., to design the network architecture based on gradient path analysis. On the whole, most of today's mainstream network design strategies are based on f"},"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":"2211.04800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-09T10:51:57Z","cross_cats_sorted":[],"title_canon_sha256":"f0ae3ba5145472b141ae5936759225be4ef796796a3233874bd3382e3d849543","abstract_canon_sha256":"3aadb3d950681c52c147be862bd89be4c4d0db5032966a91435dc7e41d238917"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:42.118757Z","signature_b64":"CsZ4AY6wFOWrpoxaTPPUB8ciQL+zCqa9E9aQqH0NbJkydk6z/T6zXAgiVim5NNxsqvDc/5K08bDnvOe51STOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb95ef38f00ea030fca1785fe2460e5619a9865c8a53e3f789ca7d729eef0910","last_reissued_at":"2026-07-05T05:14:42.118336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:42.118336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing Network Design Strategies Through Gradient Path Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chien-Yao Wang, Hong-Yuan Mark Liao, I-Hau Yeh","submitted_at":"2022-11-09T10:51:57Z","abstract_excerpt":"Designing a high-efficiency and high-quality expressive network architecture has always been the most important research topic in the field of deep learning. Most of today's network design strategies focus on how to integrate features extracted from different layers, and how to design computing units to effectively extract these features, thereby enhancing the expressiveness of the network. This paper proposes a new network design strategy, i.e., to design the network architecture based on gradient path analysis. On the whole, most of today's mainstream network design strategies are based on f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04800","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/2211.04800/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":"2211.04800","created_at":"2026-07-05T05:14:42.118396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.04800v1","created_at":"2026-07-05T05:14:42.118396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04800","created_at":"2026-07-05T05:14:42.118396+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOK66OHQB2QD","created_at":"2026-07-05T05:14:42.118396+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOK66OHQB2QDB7FB","created_at":"2026-07-05T05:14:42.118396+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOK66OHQ","created_at":"2026-07-05T05:14:42.118396+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.16739","citing_title":"Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detection","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12524","citing_title":"YOLOv12: Attention-Centric Real-Time Object Detectors","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOK66OHQB2QDB7FBPBP6ERQOKY","json":"https://pith.science/pith/ZOK66OHQB2QDB7FBPBP6ERQOKY.json","graph_json":"https://pith.science/api/pith-number/ZOK66OHQB2QDB7FBPBP6ERQOKY/graph.json","events_json":"https://pith.science/api/pith-number/ZOK66OHQB2QDB7FBPBP6ERQOKY/events.json","paper":"https://pith.science/paper/ZOK66OHQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZOK66OHQB2QDB7FBPBP6ERQOKY","download_json":"https://pith.science/pith/ZOK66OHQB2QDB7FBPBP6ERQOKY.json","view_paper":"https://pith.science/paper/ZOK66OHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.04800&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOK66OHQB2QDB7FBPBP6ERQOKY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOK66OHQB2QDB7FBPBP6ERQOKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOK66OHQB2QDB7FBPBP6ERQOKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOK66OHQB2QDB7FBPBP6ERQOKY/action/storage_attestation","attest_author":"https://pith.science/pith/ZOK66OHQB2QDB7FBPBP6ERQOKY/action/author_attestation","sign_citation":"https://pith.science/pith/ZOK66OHQB2QDB7FBPBP6ERQOKY/action/citation_signature","submit_replication":"https://pith.science/pith/ZOK66OHQB2QDB7FBPBP6ERQOKY/action/replication_record"}},"created_at":"2026-07-05T05:14:42.118396+00:00","updated_at":"2026-07-05T05:14:42.118396+00:00"}