{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7KXMBIHZZVTIDWSD7V672ZDRSX","short_pith_number":"pith:7KXMBIHZ","schema_version":"1.0","canonical_sha256":"faaec0a0f9cd6681da43fd7dfd647195fa24fe2a438cbfa18a11ab2e56c3da8a","source":{"kind":"arxiv","id":"2203.15361","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Image Representation Learning with Geometric Set Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Pan, Lei Chu, Nenglun Chen, Wenping Wang, Yan Lu","submitted_at":"2022-03-29T08:57:33Z","abstract_excerpt":"We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply consistent semantics or object boundaries, and can act as strong cues to guide the learning of 2D image representations without semantic labels. Specifically, we introduce 3D geometric consistency into a contrastive learning framework to enforce the feature consistency within image views. We propose to use geometric consistency sets as constraints and adapt the Inf"},"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":"2203.15361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T08:57:33Z","cross_cats_sorted":[],"title_canon_sha256":"17774d3d2368c45eef563b01d1d06733ec0e210b23cc64d40421bbd557696821","abstract_canon_sha256":"53ab20556fc31864033b526c48dcd00866bb379a490507bde18d4a970cef8890"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:24.529649Z","signature_b64":"wZe5G6dJzhDBqqumuSn5J7lLl1ocN8/5mjCAiYVUVFGevdrsPH5P7WB/ZDDMA89BvJ0Phrkw5HWfIrxf7yHiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faaec0a0f9cd6681da43fd7dfd647195fa24fe2a438cbfa18a11ab2e56c3da8a","last_reissued_at":"2026-07-05T04:09:24.529183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:24.529183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Image Representation Learning with Geometric Set Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Pan, Lei Chu, Nenglun Chen, Wenping Wang, Yan Lu","submitted_at":"2022-03-29T08:57:33Z","abstract_excerpt":"We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply consistent semantics or object boundaries, and can act as strong cues to guide the learning of 2D image representations without semantic labels. Specifically, we introduce 3D geometric consistency into a contrastive learning framework to enforce the feature consistency within image views. We propose to use geometric consistency sets as constraints and adapt the Inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15361","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/2203.15361/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":"2203.15361","created_at":"2026-07-05T04:09:24.529248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15361v1","created_at":"2026-07-05T04:09:24.529248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15361","created_at":"2026-07-05T04:09:24.529248+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KXMBIHZZVTI","created_at":"2026-07-05T04:09:24.529248+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KXMBIHZZVTIDWSD","created_at":"2026-07-05T04:09:24.529248+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KXMBIHZ","created_at":"2026-07-05T04:09:24.529248+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/7KXMBIHZZVTIDWSD7V672ZDRSX","json":"https://pith.science/pith/7KXMBIHZZVTIDWSD7V672ZDRSX.json","graph_json":"https://pith.science/api/pith-number/7KXMBIHZZVTIDWSD7V672ZDRSX/graph.json","events_json":"https://pith.science/api/pith-number/7KXMBIHZZVTIDWSD7V672ZDRSX/events.json","paper":"https://pith.science/paper/7KXMBIHZ"},"agent_actions":{"view_html":"https://pith.science/pith/7KXMBIHZZVTIDWSD7V672ZDRSX","download_json":"https://pith.science/pith/7KXMBIHZZVTIDWSD7V672ZDRSX.json","view_paper":"https://pith.science/paper/7KXMBIHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15361&json=true","fetch_graph":"https://pith.science/api/pith-number/7KXMBIHZZVTIDWSD7V672ZDRSX/graph.json","fetch_events":"https://pith.science/api/pith-number/7KXMBIHZZVTIDWSD7V672ZDRSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KXMBIHZZVTIDWSD7V672ZDRSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KXMBIHZZVTIDWSD7V672ZDRSX/action/storage_attestation","attest_author":"https://pith.science/pith/7KXMBIHZZVTIDWSD7V672ZDRSX/action/author_attestation","sign_citation":"https://pith.science/pith/7KXMBIHZZVTIDWSD7V672ZDRSX/action/citation_signature","submit_replication":"https://pith.science/pith/7KXMBIHZZVTIDWSD7V672ZDRSX/action/replication_record"}},"created_at":"2026-07-05T04:09:24.529248+00:00","updated_at":"2026-07-05T04:09:24.529248+00:00"}