{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HB4SIMBOA5L2MKH5ZOIWT7KJ65","short_pith_number":"pith:HB4SIMBO","schema_version":"1.0","canonical_sha256":"387924302e0757a628fdcb9169fd49f7524f084f3b1f7835bfd5c5cbaf579443","source":{"kind":"arxiv","id":"2607.01677","version":1},"attestation_state":"computed","paper":{"title":"ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaxin Xie, Mingzhe Zheng, Qifeng Chen, Xuanhua He","submitted_at":"2026-07-02T04:05:17Z","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"},"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":"2607.01677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T04:05:17Z","cross_cats_sorted":[],"title_canon_sha256":"582c17eb44a86a3911c47eb49b1789de7a11de5e14e758ed21d1840a0062b705","abstract_canon_sha256":"4f89d38af184d9e7198a317ba6102d6da157a604f511429db3a42ac5cda373bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:26.527217Z","signature_b64":"T8JyM0yhwV0EzhIgAl/LCBbbEFvC0Q9ByQemgA2wk5htHk8FQh9XqAo3+UhdBHDY0GYLEsAS1RIaemjOlAUmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"387924302e0757a628fdcb9169fd49f7524f084f3b1f7835bfd5c5cbaf579443","last_reissued_at":"2026-07-03T01:17:26.526554Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:26.526554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaxin Xie, Mingzhe Zheng, Qifeng Chen, Xuanhua He","submitted_at":"2026-07-02T04:05:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01677","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/2607.01677/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":"2607.01677","created_at":"2026-07-03T01:17:26.526647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01677v1","created_at":"2026-07-03T01:17:26.526647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01677","created_at":"2026-07-03T01:17:26.526647+00:00"},{"alias_kind":"pith_short_12","alias_value":"HB4SIMBOA5L2","created_at":"2026-07-03T01:17:26.526647+00:00"},{"alias_kind":"pith_short_16","alias_value":"HB4SIMBOA5L2MKH5","created_at":"2026-07-03T01:17:26.526647+00:00"},{"alias_kind":"pith_short_8","alias_value":"HB4SIMBO","created_at":"2026-07-03T01:17:26.526647+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/HB4SIMBOA5L2MKH5ZOIWT7KJ65","json":"https://pith.science/pith/HB4SIMBOA5L2MKH5ZOIWT7KJ65.json","graph_json":"https://pith.science/api/pith-number/HB4SIMBOA5L2MKH5ZOIWT7KJ65/graph.json","events_json":"https://pith.science/api/pith-number/HB4SIMBOA5L2MKH5ZOIWT7KJ65/events.json","paper":"https://pith.science/paper/HB4SIMBO"},"agent_actions":{"view_html":"https://pith.science/pith/HB4SIMBOA5L2MKH5ZOIWT7KJ65","download_json":"https://pith.science/pith/HB4SIMBOA5L2MKH5ZOIWT7KJ65.json","view_paper":"https://pith.science/paper/HB4SIMBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01677&json=true","fetch_graph":"https://pith.science/api/pith-number/HB4SIMBOA5L2MKH5ZOIWT7KJ65/graph.json","fetch_events":"https://pith.science/api/pith-number/HB4SIMBOA5L2MKH5ZOIWT7KJ65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HB4SIMBOA5L2MKH5ZOIWT7KJ65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HB4SIMBOA5L2MKH5ZOIWT7KJ65/action/storage_attestation","attest_author":"https://pith.science/pith/HB4SIMBOA5L2MKH5ZOIWT7KJ65/action/author_attestation","sign_citation":"https://pith.science/pith/HB4SIMBOA5L2MKH5ZOIWT7KJ65/action/citation_signature","submit_replication":"https://pith.science/pith/HB4SIMBOA5L2MKH5ZOIWT7KJ65/action/replication_record"}},"created_at":"2026-07-03T01:17:26.526647+00:00","updated_at":"2026-07-03T01:17:26.526647+00:00"}