{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MGAGJO6FNHF5D77EUTBGFIAQHU","short_pith_number":"pith:MGAGJO6F","schema_version":"1.0","canonical_sha256":"618064bbc569cbd1ffe4a4c262a0103d233a99d468012ce6cf8c00e6e02ff907","source":{"kind":"arxiv","id":"2605.30060","version":1},"attestation_state":"computed","paper":{"title":"Towards Consistent Video Geometry Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui-Liang Shen, Jingnan Gao, Kejie Qiu, Lingteng Qiu, Rui Peng, Runmin Zhang, Si-Yuan Cao, Siyu Zhu, Yichao Yan, Zhengyi Zhao, Zhu Yu","submitted_at":"2026-05-28T15:11:17Z","abstract_excerpt":"This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built upon a plain transformer architecture without task-specific architectural modifications, ViGeo supports streaming, full-sequence, and long-video inference within a unified model. The key design is dynamic chunking attention, which exposes the model to both bidirectional and causal temporal contexts during training and allows it to adapt its attention pattern at test time without retraining. To improve supervision quality, we further introduce a"},"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":"2605.30060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T15:11:17Z","cross_cats_sorted":[],"title_canon_sha256":"7d2acdb33b9ec44f705d6dd5453b90baa0ee260fd6a85f765084930497ab32e5","abstract_canon_sha256":"ba5f6bd8442b8fdf0a34ce2f788de581d5cd77bb42271d293e26524e0d8a5b49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:08.855561Z","signature_b64":"lUP1xhIr4lnJo7RcoAD4XFztpCcIXbKlg9WBZ7ZOSJ/4Xgb1riu9rOdZlQUGw+oJFxykle03YHWNg246aCGsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"618064bbc569cbd1ffe4a4c262a0103d233a99d468012ce6cf8c00e6e02ff907","last_reissued_at":"2026-05-29T02:06:08.855015Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:08.855015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Consistent Video Geometry Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui-Liang Shen, Jingnan Gao, Kejie Qiu, Lingteng Qiu, Rui Peng, Runmin Zhang, Si-Yuan Cao, Siyu Zhu, Yichao Yan, Zhengyi Zhao, Zhu Yu","submitted_at":"2026-05-28T15:11:17Z","abstract_excerpt":"This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built upon a plain transformer architecture without task-specific architectural modifications, ViGeo supports streaming, full-sequence, and long-video inference within a unified model. The key design is dynamic chunking attention, which exposes the model to both bidirectional and causal temporal contexts during training and allows it to adapt its attention pattern at test time without retraining. To improve supervision quality, we further introduce a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30060","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/2605.30060/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":"2605.30060","created_at":"2026-05-29T02:06:08.855105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30060v1","created_at":"2026-05-29T02:06:08.855105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30060","created_at":"2026-05-29T02:06:08.855105+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGAGJO6FNHF5","created_at":"2026-05-29T02:06:08.855105+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGAGJO6FNHF5D77E","created_at":"2026-05-29T02:06:08.855105+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGAGJO6F","created_at":"2026-05-29T02:06:08.855105+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/MGAGJO6FNHF5D77EUTBGFIAQHU","json":"https://pith.science/pith/MGAGJO6FNHF5D77EUTBGFIAQHU.json","graph_json":"https://pith.science/api/pith-number/MGAGJO6FNHF5D77EUTBGFIAQHU/graph.json","events_json":"https://pith.science/api/pith-number/MGAGJO6FNHF5D77EUTBGFIAQHU/events.json","paper":"https://pith.science/paper/MGAGJO6F"},"agent_actions":{"view_html":"https://pith.science/pith/MGAGJO6FNHF5D77EUTBGFIAQHU","download_json":"https://pith.science/pith/MGAGJO6FNHF5D77EUTBGFIAQHU.json","view_paper":"https://pith.science/paper/MGAGJO6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30060&json=true","fetch_graph":"https://pith.science/api/pith-number/MGAGJO6FNHF5D77EUTBGFIAQHU/graph.json","fetch_events":"https://pith.science/api/pith-number/MGAGJO6FNHF5D77EUTBGFIAQHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGAGJO6FNHF5D77EUTBGFIAQHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGAGJO6FNHF5D77EUTBGFIAQHU/action/storage_attestation","attest_author":"https://pith.science/pith/MGAGJO6FNHF5D77EUTBGFIAQHU/action/author_attestation","sign_citation":"https://pith.science/pith/MGAGJO6FNHF5D77EUTBGFIAQHU/action/citation_signature","submit_replication":"https://pith.science/pith/MGAGJO6FNHF5D77EUTBGFIAQHU/action/replication_record"}},"created_at":"2026-05-29T02:06:08.855105+00:00","updated_at":"2026-05-29T02:06:08.855105+00:00"}