{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UXKCP4VWA6JEBMADQ4S2ZXOBCZ","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":"8e7515614090554cd7402014b3e86b06b86152eaa9f47610e396738a78608535","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T13:11:54Z","title_canon_sha256":"7592fd0883041cccfac7ae87ecfe2faf5bf6eea261a0b434693f3713b17860df"},"schema_version":"1.0","source":{"id":"2605.10525","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10525","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10525v4","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10525","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"UXKCP4VWA6JE","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"UXKCP4VWA6JEBMAD","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"UXKCP4VW","created_at":"2026-05-20T01:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:ea0b30eb40fb2b003630f9ef5f79cf4bcb7976e08009ceee696aa6d4a79889a0","target":"graph","created_at":"2026-05-20T01:05:16Z","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":"GemDepth achieves state-of-the-art performance across multiple datasets, particularly in complex dynamic scenarios."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That predicting inter-frame camera poses and injecting the resulting geometric embeddings is a prerequisite for strict 3D consistency under rotations or drastic view changes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GemDepth predicts inter-frame camera poses to inject geometric embeddings into a spatio-temporal transformer, yielding state-of-the-art 3D-consistent video depth."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GemDepth achieves 3D-consistent video depth by predicting camera poses to embed geometric structure into a transformer."}],"snapshot_sha256":"80438595b31431519e9ea6dba5fdfcec63c4fc113798ed2fe9aa4c191b71c601"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d92fc18f344a799a4924c04fa3abe32d116481688887298c9abf89a54530d1bb"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T14:42:07.908786Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T11:01:17.869831Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:12:29.466117Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10525/integrity.json","findings":[],"snapshot_sha256":"e541b2a2e5568f4f98af6b2ca3dc7af5ac45400cd5819c7fbb84046f6aacb765","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial blurring in fine-detail regions and temporal inconsistencies. We argue that current approaches, which primarily rely on temporal smoothing via Transformers, struggle to maintain strict 3D geometric consistency-particularly under rotations or drastic view changes. To address this, we propose GemDepth, a framework built on the insight that an explicit awareness of camera motion and global 3D structure is a prerequisite for 3D consistency. Distincti","authors_text":"Hanrui Cheng, Junda Cheng, Longliang Liu, Wenjing Liao, Xin Yang, Yuecheng Liu, Yuzhou Wang","cross_cats":[],"headline":"GemDepth achieves 3D-consistent video depth by predicting camera poses to embed geometric structure into a transformer.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T13:11:54Z","title":"GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10525","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-14T21:24:42.864887Z","id":"67b9e8b1-0d64-4492-8b1e-b1ea42ed182c","model_set":{"reader":"grok-4.3"},"one_line_summary":"GemDepth predicts inter-frame camera poses to inject geometric embeddings into a spatio-temporal transformer, yielding state-of-the-art 3D-consistent video depth.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GemDepth achieves 3D-consistent video depth by predicting camera poses to embed geometric structure into a transformer.","strongest_claim":"GemDepth achieves state-of-the-art performance across multiple datasets, particularly in complex dynamic scenarios.","weakest_assumption":"That predicting inter-frame camera poses and injecting the resulting geometric embeddings is a prerequisite for strict 3D consistency under rotations or drastic view changes."}},"verdict_id":"67b9e8b1-0d64-4492-8b1e-b1ea42ed182c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cca389705ef3c7bd996369b7eb6cba018a622218145bdbeefa6caf95982ff958","target":"record","created_at":"2026-05-20T01:05:16Z","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":"8e7515614090554cd7402014b3e86b06b86152eaa9f47610e396738a78608535","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T13:11:54Z","title_canon_sha256":"7592fd0883041cccfac7ae87ecfe2faf5bf6eea261a0b434693f3713b17860df"},"schema_version":"1.0","source":{"id":"2605.10525","kind":"arxiv","version":4}},"canonical_sha256":"a5d427f2b6079240b0038725acddc116698d8a0c5ccdf57e8e95d8585a3eaa94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5d427f2b6079240b0038725acddc116698d8a0c5ccdf57e8e95d8585a3eaa94","first_computed_at":"2026-05-20T01:05:16.497143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:16.497143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aC9kaS6gHpViXwSViUy1q7HwFgiTfGcoAvOsVtIxCJ48FXeOQ3KYY6r3fCT93ExI3rJ8cLYI81u7hpUUJvU/DA==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:16.497732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10525","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cca389705ef3c7bd996369b7eb6cba018a622218145bdbeefa6caf95982ff958","sha256:ea0b30eb40fb2b003630f9ef5f79cf4bcb7976e08009ceee696aa6d4a79889a0"],"state_sha256":"678d62ada5347f0343b5e751bc2c25e71291ef35aa3b8a69e9a870cca50e7af0"}