{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5DS65U7CIBXRYWKTG5RB3375N2","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":"0be0ebc78f5407b81239539e436bc916c8540651509a4c39c3c1aca89f94fc1f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-01T04:37:13Z","title_canon_sha256":"65226680152c468674f5d99427255ab5764827dd30161e589a878a8400c60fe5"},"schema_version":"1.0","source":{"id":"2502.00315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00315","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00315v1","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00315","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"5DS65U7CIBXR","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"5DS65U7CIBXRYWKT","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"5DS65U7C","created_at":"2026-07-05T10:08:32Z"}],"graph_snapshots":[{"event_id":"sha256:0b053e5b6b8614ac7eb58dbf332599f807f478b6df2988b39e7c5898465c6301","target":"graph","created_at":"2026-07-05T10:08:32Z","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/2502.00315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes novel methods to enhance the performance of monocular 3D object detection models by leveraging the generalized feature extraction capabilities of a vision foundation model. Unlike traditional CNN-based approaches, which often suffer from inaccurate depth estimation and rely on multi-stage object detection pipelines, this study employs a Vision Transformer (ViT)-based foundation model as the backbone, which excels at capturing global features for depth estimation. It integrates a detection transformer (DETR) architecture to improve both depth estimation and object detection ","authors_text":"David Hyunchul Shim, Jihyeok Kim, Seongwoo Moon, Sungwon Nah","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-01T04:37:13Z","title":"MonoDINO-DETR: Depth-Enhanced Monocular 3D Object Detection Using a Vision Foundation Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00315","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":"sha256:78713cb1fa5c161faf29b38a62d13806eac72bd7fe65cb8c7bcbb65fb3d3762d","target":"record","created_at":"2026-07-05T10:08:32Z","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":"0be0ebc78f5407b81239539e436bc916c8540651509a4c39c3c1aca89f94fc1f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-01T04:37:13Z","title_canon_sha256":"65226680152c468674f5d99427255ab5764827dd30161e589a878a8400c60fe5"},"schema_version":"1.0","source":{"id":"2502.00315","kind":"arxiv","version":1}},"canonical_sha256":"e8e5eed3e2406f1c595337621deffd6e81acadf2e34147dad3cb3db2bf8213b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8e5eed3e2406f1c595337621deffd6e81acadf2e34147dad3cb3db2bf8213b8","first_computed_at":"2026-07-05T10:08:32.028347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:32.028347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l4wLTbFzXtXA1Zy1aFR0diXbPrrBFsELFYRPMLoD6i+uej1ZzKuo0t6vYbFcbFWsMk9gPCeCOWkaPNqc3vHnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:32.028761Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78713cb1fa5c161faf29b38a62d13806eac72bd7fe65cb8c7bcbb65fb3d3762d","sha256:0b053e5b6b8614ac7eb58dbf332599f807f478b6df2988b39e7c5898465c6301"],"state_sha256":"1f1facc0dd27b0fafdd00455eedb9d5b7d1ccd9fc3e4ecb55a6558b6772bcdf9"}