{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YIDJOLNEKGUVWCFKAWHJQ7IFG3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3280ebc5d0db3aba2b8188bd53a6d39ece7ab10aa9c4cd54af9b40267cbd167b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-10T09:21:51Z","title_canon_sha256":"4b257d9f8995d2c0f483a01713d7caedbc60573071ed65d383a6df38455acf37"},"schema_version":"1.0","source":{"id":"2604.09142","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09142","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09142v2","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09142","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"YIDJOLNEKGUV","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"pith_short_16","alias_value":"YIDJOLNEKGUVWCFK","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"pith_short_8","alias_value":"YIDJOLNE","created_at":"2026-06-30T02:17:20Z"}],"graph_snapshots":[{"event_id":"sha256:68dc60cf42d09daf99283a4268bec3b17b3604a3562f45185988968d004dda6e","target":"graph","created_at":"2026-06-30T02:17:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Trained exclusively on synthetic data such as SceneFlow, GREATEN-IGEV achieves outstanding Syn-to-Real performance. Specifically, it reduces errors by 30% on ETH3D, 8.5% on the non-Lambertian Booster, and 14.1% on KITTI-2015, compared to FoundationStereo, Monster-Stereo, and DEFOM-Stereo, respectively."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That surface normals can be obtained or estimated reliably enough in real scenes to serve as domain-invariant cues, and that the gated fusion module will consistently suppress misleading image textures without introducing new artifacts in occluded or non-Lambertian regions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GREATEN fuses surface normals with image features via gated contextual-geometric fusion and efficient sparse attentions to cut stereo matching errors by up to 30% on real datasets when trained solely on synthetic data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Surface normals provide domain-invariant geometric cues that improve zero-shot generalization in stereo matching from synthetic to real data."}],"snapshot_sha256":"fc2beb080f28c46d056b3d9c91212495e847e24950b40b137cf2c73bd224ac3b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.09142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite remarkable advances in image-driven stereo matching over the past decade, Synthetic-to-Realistic ZeroShot (Syn-to-Real) generalization remains an open challenge. This suboptimal generalization performance mainly stems from cross-domain shifts and ill-posed ambiguities inherent in image textures, particularly in occluded, textureless, repetitive, and non-Lambertian (specular/transparent) regions. To improve Synto-Real generalization, we propose GREATEN, a framework that incorporates surface normals as domain-invariant, object-intrinsic, and discriminative geometric cues to compensate fo","authors_text":"Cheng Huang, Jiahao Li, Jianping Wang, Xinhong Chen, Yung-Hui Li, Zhengmin Jiang","cross_cats":[],"headline":"Surface normals provide domain-invariant geometric cues that improve zero-shot generalization in stereo matching from synthetic to real data.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-10T09:21:51Z","title":"Geometry Reinforced Efficient Attention Tuning Equipped with Normals for Robust Stereo Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.09142","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T17:48:03.616235Z","id":"b7018f9d-3b16-41dd-af5c-9b5fe4b3851b","model_set":{"reader":"grok-4.3"},"one_line_summary":"GREATEN fuses surface normals with image features via gated contextual-geometric fusion and efficient sparse attentions to cut stereo matching errors by up to 30% on real datasets when trained solely on synthetic data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Surface normals provide domain-invariant geometric cues that improve zero-shot generalization in stereo matching from synthetic to real data.","strongest_claim":"Trained exclusively on synthetic data such as SceneFlow, GREATEN-IGEV achieves outstanding Syn-to-Real performance. Specifically, it reduces errors by 30% on ETH3D, 8.5% on the non-Lambertian Booster, and 14.1% on KITTI-2015, compared to FoundationStereo, Monster-Stereo, and DEFOM-Stereo, respectively.","weakest_assumption":"That surface normals can be obtained or estimated reliably enough in real scenes to serve as domain-invariant cues, and that the gated fusion module will consistently suppress misleading image textures without introducing new artifacts in occluded or non-Lambertian regions."}},"verdict_id":"b7018f9d-3b16-41dd-af5c-9b5fe4b3851b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:265173ae081d93b32221fbb509881f1eb859b533470125319a862957e12c9543","target":"record","created_at":"2026-06-30T02:17:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3280ebc5d0db3aba2b8188bd53a6d39ece7ab10aa9c4cd54af9b40267cbd167b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-10T09:21:51Z","title_canon_sha256":"4b257d9f8995d2c0f483a01713d7caedbc60573071ed65d383a6df38455acf37"},"schema_version":"1.0","source":{"id":"2604.09142","kind":"arxiv","version":2}},"canonical_sha256":"c206972da451a95b08aa058e987d0536eb0e77ceff439dc6777ecdc3fd0acc14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c206972da451a95b08aa058e987d0536eb0e77ceff439dc6777ecdc3fd0acc14","first_computed_at":"2026-06-30T02:17:20.478836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:20.478836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qL/JmK50BaqTJuDo4BhYiYEyJchDXO3jU46LAP6ntdVrssFdYCnVWQAvWzPFS7kSvADQFkooO05wUMWp81SVAg==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:20.479411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.09142","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:265173ae081d93b32221fbb509881f1eb859b533470125319a862957e12c9543","sha256:68dc60cf42d09daf99283a4268bec3b17b3604a3562f45185988968d004dda6e"],"state_sha256":"1c27badcf7eba682808b3e7c2b61e7af0cce6832444fc89cc82784b7cf7a900b"}