{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZB32OW3FCRI7MU6ZPULCUBLLPH","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":"b1e6e50fba5e213158f38b660d8b094959a8fa4e8c1041bb86dbd095425abda7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-20T16:14:23Z","title_canon_sha256":"055a96addf8d500724775249feaa834a7fdff00879c42c733a00695e43094061"},"schema_version":"1.0","source":{"id":"2307.10984","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.10984","created_at":"2026-07-05T06:33:13Z"},{"alias_kind":"arxiv_version","alias_value":"2307.10984v1","created_at":"2026-07-05T06:33:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10984","created_at":"2026-07-05T06:33:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZB32OW3FCRI7","created_at":"2026-07-05T06:33:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZB32OW3FCRI7MU6Z","created_at":"2026-07-05T06:33:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZB32OW3F","created_at":"2026-07-05T06:33:13Z"}],"graph_snapshots":[{"event_id":"sha256:ae3d4c9bfed8a9249b5d7a2925111a6c349081274150d1708c2e683fe97027ab","target":"graph","created_at":"2026-07-05T06:33:13Z","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/2307.10984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reconstructing accurate 3D scenes from images is a long-standing vision task. Due to the ill-posedness of the single-image reconstruction problem, most well-established methods are built upon multi-view geometry. State-of-the-art (SOTA) monocular metric depth estimation methods can only handle a single camera model and are unable to perform mixed-data training due to the metric ambiguity. Meanwhile, SOTA monocular methods trained on large mixed datasets achieve zero-shot generalization by learning affine-invariant depths, which cannot recover real-world metrics. In this work, we show that the ","authors_text":"Chi Zhang, Chunhua Shen, Gang Yu, Hao Chen, Kaixuan Wang, Wei Yin, Xiaozhi Chen, Zhipeng Cai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-20T16:14:23Z","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10984","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":"sha256:77cc59a2b67b8f5a71e246d808211988b21c7b09833167a3423b6c5edf98ceb0","target":"record","created_at":"2026-07-05T06:33:13Z","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":"b1e6e50fba5e213158f38b660d8b094959a8fa4e8c1041bb86dbd095425abda7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-20T16:14:23Z","title_canon_sha256":"055a96addf8d500724775249feaa834a7fdff00879c42c733a00695e43094061"},"schema_version":"1.0","source":{"id":"2307.10984","kind":"arxiv","version":1}},"canonical_sha256":"c877a75b651451f653d97d162a056b79fd3a8f32c36da064b0c7bde40e8469ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c877a75b651451f653d97d162a056b79fd3a8f32c36da064b0c7bde40e8469ad","first_computed_at":"2026-07-05T06:33:13.721190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:13.721190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gf1DHdI6b8G28uK/gp2OLIY3Urky46ayr3FlMEQ8hI1gWcYR5Pc3wptyo3OKTKhkMGFTQf3BNT00KdexrH/CBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:13.721615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.10984","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77cc59a2b67b8f5a71e246d808211988b21c7b09833167a3423b6c5edf98ceb0","sha256:ae3d4c9bfed8a9249b5d7a2925111a6c349081274150d1708c2e683fe97027ab"],"state_sha256":"21203fd07ecec543c22062637d9b53ee78bc4a61847355404091d4245d5a02b0"}