{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HB4SIMBOA5L2MKH5ZOIWT7KJ65","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":"4f89d38af184d9e7198a317ba6102d6da157a604f511429db3a42ac5cda373bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T04:05:17Z","title_canon_sha256":"582c17eb44a86a3911c47eb49b1789de7a11de5e14e758ed21d1840a0062b705"},"schema_version":"1.0","source":{"id":"2607.01677","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01677","created_at":"2026-07-03T01:17:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01677v1","created_at":"2026-07-03T01:17:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01677","created_at":"2026-07-03T01:17:26Z"},{"alias_kind":"pith_short_12","alias_value":"HB4SIMBOA5L2","created_at":"2026-07-03T01:17:26Z"},{"alias_kind":"pith_short_16","alias_value":"HB4SIMBOA5L2MKH5","created_at":"2026-07-03T01:17:26Z"},{"alias_kind":"pith_short_8","alias_value":"HB4SIMBO","created_at":"2026-07-03T01:17:26Z"}],"graph_snapshots":[{"event_id":"sha256:17f20a9be3b48b92e4e8b899b73375c4acf1fef54474864cef341935366a587f","target":"graph","created_at":"2026-07-03T01:17:26Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.01677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-frame accuracy but suffer from temporal drift due to limited context windows, while generative methods improve consistency and generalization at the cost of extensive training data (10M+ samples) and lack of geometric precision. In response to these issues, we introduce \\textbf{ICDepth}, a framework that adapts pre-trained text-to-video diffusion transformers for vid","authors_text":"Jiaxin Xie, Mingzhe Zheng, Qifeng Chen, Xuanhua He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T04:05:17Z","title":"ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01677","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7a5b2090f6a4645c84ba33fb3b6f069da3566eaac398dc7fb0be0d8c0ea5b947","target":"record","created_at":"2026-07-03T01:17:26Z","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":"4f89d38af184d9e7198a317ba6102d6da157a604f511429db3a42ac5cda373bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T04:05:17Z","title_canon_sha256":"582c17eb44a86a3911c47eb49b1789de7a11de5e14e758ed21d1840a0062b705"},"schema_version":"1.0","source":{"id":"2607.01677","kind":"arxiv","version":1}},"canonical_sha256":"387924302e0757a628fdcb9169fd49f7524f084f3b1f7835bfd5c5cbaf579443","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"387924302e0757a628fdcb9169fd49f7524f084f3b1f7835bfd5c5cbaf579443","first_computed_at":"2026-07-03T01:17:26.526554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:26.526554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T8JyM0yhwV0EzhIgAl/LCBbbEFvC0Q9ByQemgA2wk5htHk8FQh9XqAo3+UhdBHDY0GYLEsAS1RIaemjOlAUmAA==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:26.527217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01677","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a5b2090f6a4645c84ba33fb3b6f069da3566eaac398dc7fb0be0d8c0ea5b947","sha256:17f20a9be3b48b92e4e8b899b73375c4acf1fef54474864cef341935366a587f"],"state_sha256":"fad0ccd59c2d29aea9ec5690edeb08eb4fa3a9823c87b52382a1e368c0e55992"}