{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YD4S3XPSEW62L2R6EKOTJHBQF2","short_pith_number":"pith:YD4S3XPS","canonical_record":{"source":{"id":"2312.08022","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T09:49:59Z","cross_cats_sorted":[],"title_canon_sha256":"b46e032b91d91657998f037ca41f60f9783a2ffdfa1e40af5100b48b39e6b58c","abstract_canon_sha256":"7ffcc6f7aa4897e8783c2b59547dd914e2dcb3b69f9d5fc59bdb56ed2ed68000"},"schema_version":"1.0"},"canonical_sha256":"c0f92dddf225bda5ea3e229d349c302eb5882031f0a529592b8dcb98ae7a238e","source":{"kind":"arxiv","id":"2312.08022","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08022","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08022v1","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08022","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"YD4S3XPSEW62","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"YD4S3XPSEW62L2R6","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"YD4S3XPS","created_at":"2026-07-05T07:23:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YD4S3XPSEW62L2R6EKOTJHBQF2","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08022","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T09:49:59Z","cross_cats_sorted":[],"title_canon_sha256":"b46e032b91d91657998f037ca41f60f9783a2ffdfa1e40af5100b48b39e6b58c","abstract_canon_sha256":"7ffcc6f7aa4897e8783c2b59547dd914e2dcb3b69f9d5fc59bdb56ed2ed68000"},"schema_version":"1.0"},"canonical_sha256":"c0f92dddf225bda5ea3e229d349c302eb5882031f0a529592b8dcb98ae7a238e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:40.286219Z","signature_b64":"L72XFmxDZtEfhCC0EtBSYRy+FHpH0RVbJDZ3bnQGDBSf8bILpKKXGO9UBEEKy09FlKviirGh3lWm2MlqD+e3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0f92dddf225bda5ea3e229d349c302eb5882031f0a529592b8dcb98ae7a238e","last_reissued_at":"2026-07-05T07:23:40.285812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:40.285812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08022","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:23:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dsAjuiNmKsYdGj7q0I2Lb3m/LP3dIjSHoQRTViITBSdkgO6vtG514dAr6/GnmGlP9VM9IGSJIJavtRYXQ6QzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:23:14.302692Z"},"content_sha256":"98a613748fd0e64a941b1c6917b9d6bb4ae7f5d48cb282c0645b8df82cf5d8a3","schema_version":"1.0","event_id":"sha256:98a613748fd0e64a941b1c6917b9d6bb4ae7f5d48cb282c0645b8df82cf5d8a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YD4S3XPSEW62L2R6EKOTJHBQF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mono3DVG: 3D Visual Grounding in Monocular Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yang Zhan, Yuan Yuan, Zhitong Xiong","submitted_at":"2023-12-13T09:49:59Z","abstract_excerpt":"We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets with their corresponding geometric text descriptions, generated by ChatGPT and refined manually. To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization. Depth predictor is designed to expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08022","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/2312.08022/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:23:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ljq4kIkvmhHV6lv9zI52fcyKVecIrI9wi4m+EgR6+Hh2m3PTVoxUsFdEotoJUung19wWNohMtrmA5z8yLQFpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:23:14.303218Z"},"content_sha256":"1fb4e03519d91639cca93c99bfd0bf8bfa3d139d8303203c2cba063bb992edd1","schema_version":"1.0","event_id":"sha256:1fb4e03519d91639cca93c99bfd0bf8bfa3d139d8303203c2cba063bb992edd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YD4S3XPSEW62L2R6EKOTJHBQF2/bundle.json","state_url":"https://pith.science/pith/YD4S3XPSEW62L2R6EKOTJHBQF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YD4S3XPSEW62L2R6EKOTJHBQF2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-24T00:23:14Z","links":{"resolver":"https://pith.science/pith/YD4S3XPSEW62L2R6EKOTJHBQF2","bundle":"https://pith.science/pith/YD4S3XPSEW62L2R6EKOTJHBQF2/bundle.json","state":"https://pith.science/pith/YD4S3XPSEW62L2R6EKOTJHBQF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YD4S3XPSEW62L2R6EKOTJHBQF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YD4S3XPSEW62L2R6EKOTJHBQF2","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":"7ffcc6f7aa4897e8783c2b59547dd914e2dcb3b69f9d5fc59bdb56ed2ed68000","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T09:49:59Z","title_canon_sha256":"b46e032b91d91657998f037ca41f60f9783a2ffdfa1e40af5100b48b39e6b58c"},"schema_version":"1.0","source":{"id":"2312.08022","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08022","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08022v1","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08022","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"YD4S3XPSEW62","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"YD4S3XPSEW62L2R6","created_at":"2026-07-05T07:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"YD4S3XPS","created_at":"2026-07-05T07:23:40Z"}],"graph_snapshots":[{"event_id":"sha256:1fb4e03519d91639cca93c99bfd0bf8bfa3d139d8303203c2cba063bb992edd1","target":"graph","created_at":"2026-07-05T07:23:40Z","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/2312.08022/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets with their corresponding geometric text descriptions, generated by ChatGPT and refined manually. To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization. Depth predictor is designed to expl","authors_text":"Yang Zhan, Yuan Yuan, Zhitong Xiong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T09:49:59Z","title":"Mono3DVG: 3D Visual Grounding in Monocular Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08022","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":"sha256:98a613748fd0e64a941b1c6917b9d6bb4ae7f5d48cb282c0645b8df82cf5d8a3","target":"record","created_at":"2026-07-05T07:23:40Z","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":"7ffcc6f7aa4897e8783c2b59547dd914e2dcb3b69f9d5fc59bdb56ed2ed68000","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T09:49:59Z","title_canon_sha256":"b46e032b91d91657998f037ca41f60f9783a2ffdfa1e40af5100b48b39e6b58c"},"schema_version":"1.0","source":{"id":"2312.08022","kind":"arxiv","version":1}},"canonical_sha256":"c0f92dddf225bda5ea3e229d349c302eb5882031f0a529592b8dcb98ae7a238e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0f92dddf225bda5ea3e229d349c302eb5882031f0a529592b8dcb98ae7a238e","first_computed_at":"2026-07-05T07:23:40.285812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:40.285812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L72XFmxDZtEfhCC0EtBSYRy+FHpH0RVbJDZ3bnQGDBSf8bILpKKXGO9UBEEKy09FlKviirGh3lWm2MlqD+e3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:40.286219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08022","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98a613748fd0e64a941b1c6917b9d6bb4ae7f5d48cb282c0645b8df82cf5d8a3","sha256:1fb4e03519d91639cca93c99bfd0bf8bfa3d139d8303203c2cba063bb992edd1"],"state_sha256":"507d2a2ff6b874db30595378c0de76f235f0efc697ff2d922b54b1a4baa743f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dk768XO1xNWYVHUlAds/K17jh/35STuZjwO23L6i2BP3jI9HXcXN8A5NqPZkJSYr7W3aUdM5C8hg03vAlNf1AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T00:23:14.308155Z","bundle_sha256":"7219422ea7c756799710d3f62d63688d06ba21097851f4e53c88903f2ed9a40f"}}