{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EO545M46FKJFMW4GBH7K4MKCMP","short_pith_number":"pith:EO545M46","schema_version":"1.0","canonical_sha256":"23bbceb39e2a92565b8609feae314263fc3b18b775a842f077fd8b378d3626ae","source":{"kind":"arxiv","id":"2503.16535","version":2},"attestation_state":"computed","paper":{"title":"Vision-Language Embodiment for Monocular Depth Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoyu Lu, Jinchang Zhang","submitted_at":"2025-03-18T18:05:16Z","abstract_excerpt":"Depth estimation is a core problem in robotic perception and vision tasks, but 3D reconstruction from a single image presents inherent uncertainties. Current depth estimation models primarily rely on inter-image relationships for supervised training, often overlooking the intrinsic information provided by the camera itself. We propose a method that embodies the camera model and its physical characteristics into a deep learning model, computing embodied scene depth through real-time interactions with road environments. The model can calculate embodied scene depth in real-time based on immediate"},"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":"2503.16535","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T18:05:16Z","cross_cats_sorted":[],"title_canon_sha256":"57cf79fd63e8770beee89ef86f9a6de5752a40cfa641abcbb19bfa37cf7998fc","abstract_canon_sha256":"a322383928926557bbb4ba8b66147750c02823034eb2cb8907c188e072a73a51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:57.713987Z","signature_b64":"hYcZMDJfJVWidyHh+G50dppcAkvNh3LjQgH8mJ3vTmlrILZYRaorQMrr+5HULRcL13SHPFjsPwZqxui0m5syBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23bbceb39e2a92565b8609feae314263fc3b18b775a842f077fd8b378d3626ae","last_reissued_at":"2026-07-05T10:47:57.713523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:57.713523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Embodiment for Monocular Depth Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoyu Lu, Jinchang Zhang","submitted_at":"2025-03-18T18:05:16Z","abstract_excerpt":"Depth estimation is a core problem in robotic perception and vision tasks, but 3D reconstruction from a single image presents inherent uncertainties. Current depth estimation models primarily rely on inter-image relationships for supervised training, often overlooking the intrinsic information provided by the camera itself. We propose a method that embodies the camera model and its physical characteristics into a deep learning model, computing embodied scene depth through real-time interactions with road environments. The model can calculate embodied scene depth in real-time based on immediate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16535","kind":"arxiv","version":2},"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/2503.16535/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":"2503.16535","created_at":"2026-07-05T10:47:57.713577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16535v2","created_at":"2026-07-05T10:47:57.713577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16535","created_at":"2026-07-05T10:47:57.713577+00:00"},{"alias_kind":"pith_short_12","alias_value":"EO545M46FKJF","created_at":"2026-07-05T10:47:57.713577+00:00"},{"alias_kind":"pith_short_16","alias_value":"EO545M46FKJFMW4G","created_at":"2026-07-05T10:47:57.713577+00:00"},{"alias_kind":"pith_short_8","alias_value":"EO545M46","created_at":"2026-07-05T10:47:57.713577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22394","citing_title":"Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EO545M46FKJFMW4GBH7K4MKCMP","json":"https://pith.science/pith/EO545M46FKJFMW4GBH7K4MKCMP.json","graph_json":"https://pith.science/api/pith-number/EO545M46FKJFMW4GBH7K4MKCMP/graph.json","events_json":"https://pith.science/api/pith-number/EO545M46FKJFMW4GBH7K4MKCMP/events.json","paper":"https://pith.science/paper/EO545M46"},"agent_actions":{"view_html":"https://pith.science/pith/EO545M46FKJFMW4GBH7K4MKCMP","download_json":"https://pith.science/pith/EO545M46FKJFMW4GBH7K4MKCMP.json","view_paper":"https://pith.science/paper/EO545M46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16535&json=true","fetch_graph":"https://pith.science/api/pith-number/EO545M46FKJFMW4GBH7K4MKCMP/graph.json","fetch_events":"https://pith.science/api/pith-number/EO545M46FKJFMW4GBH7K4MKCMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EO545M46FKJFMW4GBH7K4MKCMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EO545M46FKJFMW4GBH7K4MKCMP/action/storage_attestation","attest_author":"https://pith.science/pith/EO545M46FKJFMW4GBH7K4MKCMP/action/author_attestation","sign_citation":"https://pith.science/pith/EO545M46FKJFMW4GBH7K4MKCMP/action/citation_signature","submit_replication":"https://pith.science/pith/EO545M46FKJFMW4GBH7K4MKCMP/action/replication_record"}},"created_at":"2026-07-05T10:47:57.713577+00:00","updated_at":"2026-07-05T10:47:57.713577+00:00"}