{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ST3BI45VZVSNDQYI6MRQQEATP4","short_pith_number":"pith:ST3BI45V","schema_version":"1.0","canonical_sha256":"94f61473b5cd64d1c308f3230810137f1a50e4039bf188041e55dc7ef49a3c49","source":{"kind":"arxiv","id":"2412.09853","version":1},"attestation_state":"computed","paper":{"title":"Understand the Effectiveness of Shortcuts through the Lens of DCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC"],"primary_cat":"cs.LG","authors_text":"Yihua Liu, Yi-Shuai Niu, Youran Sun","submitted_at":"2024-12-13T04:46:17Z","abstract_excerpt":"Difference-of-Convex Algorithm (DCA) is a well-known nonconvex optimization algorithm for minimizing a nonconvex function that can be expressed as the difference of two convex ones. Many famous existing optimization algorithms, such as SGD and proximal point methods, can be viewed as special DCAs with specific DC decompositions, making it a powerful framework for optimization. On the other hand, shortcuts are a key architectural feature in modern deep neural networks, facilitating both training and optimization. We showed that the shortcut neural network gradient can be obtained by applying DC"},"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":"2412.09853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-13T04:46:17Z","cross_cats_sorted":["cs.NE","math.OC"],"title_canon_sha256":"f0b8d1bf73675e6b09a5dc02acc969d9d7757645b2ab09746ccdb857f787c7a7","abstract_canon_sha256":"1ad1475a7e36ac3e8a6a66851ddc1ad8350f557196abeea9ed91cdc60c98d20e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:42.701041Z","signature_b64":"CI3dDQ9f70Wk9NDSNMaDlSvg6isLaTtug+6ttVm/ZiTqbmfpoX3BIZ9eYyPO35Qa5TTNo2+MuVwL72MrSL36Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94f61473b5cd64d1c308f3230810137f1a50e4039bf188041e55dc7ef49a3c49","last_reissued_at":"2026-07-05T09:48:42.700511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:42.700511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understand the Effectiveness of Shortcuts through the Lens of DCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC"],"primary_cat":"cs.LG","authors_text":"Yihua Liu, Yi-Shuai Niu, Youran Sun","submitted_at":"2024-12-13T04:46:17Z","abstract_excerpt":"Difference-of-Convex Algorithm (DCA) is a well-known nonconvex optimization algorithm for minimizing a nonconvex function that can be expressed as the difference of two convex ones. Many famous existing optimization algorithms, such as SGD and proximal point methods, can be viewed as special DCAs with specific DC decompositions, making it a powerful framework for optimization. On the other hand, shortcuts are a key architectural feature in modern deep neural networks, facilitating both training and optimization. We showed that the shortcut neural network gradient can be obtained by applying DC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09853","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/2412.09853/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":"2412.09853","created_at":"2026-07-05T09:48:42.700582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09853v1","created_at":"2026-07-05T09:48:42.700582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09853","created_at":"2026-07-05T09:48:42.700582+00:00"},{"alias_kind":"pith_short_12","alias_value":"ST3BI45VZVSN","created_at":"2026-07-05T09:48:42.700582+00:00"},{"alias_kind":"pith_short_16","alias_value":"ST3BI45VZVSNDQYI","created_at":"2026-07-05T09:48:42.700582+00:00"},{"alias_kind":"pith_short_8","alias_value":"ST3BI45V","created_at":"2026-07-05T09:48:42.700582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16266","citing_title":"Patchwork: A compact representation for 3D polygonal shapes","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ST3BI45VZVSNDQYI6MRQQEATP4","json":"https://pith.science/pith/ST3BI45VZVSNDQYI6MRQQEATP4.json","graph_json":"https://pith.science/api/pith-number/ST3BI45VZVSNDQYI6MRQQEATP4/graph.json","events_json":"https://pith.science/api/pith-number/ST3BI45VZVSNDQYI6MRQQEATP4/events.json","paper":"https://pith.science/paper/ST3BI45V"},"agent_actions":{"view_html":"https://pith.science/pith/ST3BI45VZVSNDQYI6MRQQEATP4","download_json":"https://pith.science/pith/ST3BI45VZVSNDQYI6MRQQEATP4.json","view_paper":"https://pith.science/paper/ST3BI45V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09853&json=true","fetch_graph":"https://pith.science/api/pith-number/ST3BI45VZVSNDQYI6MRQQEATP4/graph.json","fetch_events":"https://pith.science/api/pith-number/ST3BI45VZVSNDQYI6MRQQEATP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ST3BI45VZVSNDQYI6MRQQEATP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ST3BI45VZVSNDQYI6MRQQEATP4/action/storage_attestation","attest_author":"https://pith.science/pith/ST3BI45VZVSNDQYI6MRQQEATP4/action/author_attestation","sign_citation":"https://pith.science/pith/ST3BI45VZVSNDQYI6MRQQEATP4/action/citation_signature","submit_replication":"https://pith.science/pith/ST3BI45VZVSNDQYI6MRQQEATP4/action/replication_record"}},"created_at":"2026-07-05T09:48:42.700582+00:00","updated_at":"2026-07-05T09:48:42.700582+00:00"}