{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NRBIH63RRXNUUFCNZRCGZ5NJQM","short_pith_number":"pith:NRBIH63R","canonical_record":{"source":{"id":"2408.07422","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T10:00:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e48620ecb4c0697000a6b7e00b2da764e5ebf670f3da52d1109a7db68298e1e","abstract_canon_sha256":"6be4e9635f51c8cbdb16ec098d32077e844ad465ccee6f7bdcb21e3c36ae63fa"},"schema_version":"1.0"},"canonical_sha256":"6c4283fb718ddb4a144dcc446cf5a9832515d278b2ff27a24448a99069d55b52","source":{"kind":"arxiv","id":"2408.07422","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07422","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07422v2","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07422","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"NRBIH63RRXNU","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"pith_short_16","alias_value":"NRBIH63RRXNUUFCN","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"pith_short_8","alias_value":"NRBIH63R","created_at":"2026-07-05T10:13:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NRBIH63RRXNUUFCNZRCGZ5NJQM","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07422","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T10:00:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e48620ecb4c0697000a6b7e00b2da764e5ebf670f3da52d1109a7db68298e1e","abstract_canon_sha256":"6be4e9635f51c8cbdb16ec098d32077e844ad465ccee6f7bdcb21e3c36ae63fa"},"schema_version":"1.0"},"canonical_sha256":"6c4283fb718ddb4a144dcc446cf5a9832515d278b2ff27a24448a99069d55b52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:42.386186Z","signature_b64":"dN1Uvy2eKNV/vIrTQHyQl04hEEGgKSZZ0wmv2Vo8KeSy50GQFliAwVxlz9bhiGPQUjDZ/0dl+fo1RhfvfAORCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c4283fb718ddb4a144dcc446cf5a9832515d278b2ff27a24448a99069d55b52","last_reissued_at":"2026-07-05T10:13:42.385677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:42.385677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07422","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUh8s2HlBe9h2ECLDWWsGMEl6wTFJAbyegdE1ASgBBKFbKE29RdboeYaVdqvwMjQ0psBV3vJLMNBrfCjb0d0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:35:57.781715Z"},"content_sha256":"5f6b9ce9774ba2d189e88bd64c7a69a2a390add8fd86b18dd44b41f5cf744578","schema_version":"1.0","event_id":"sha256:5f6b9ce9774ba2d189e88bd64c7a69a2a390add8fd86b18dd44b41f5cf744578"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NRBIH63RRXNUUFCNZRCGZ5NJQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMI3D: MLLM-based 3D Perception from a Single 2D Image","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fan Yang, Guiguang Ding, Haonan Lu, Hui Chen, Jungong Han, Sicheng Zhao, Yanhao Zhang","submitted_at":"2024-08-14T10:00:16Z","abstract_excerpt":"Recent advancements in autonomous driving, augmented reality, robotics, and embodied intelligence have necessitated 3D perception algorithms. However, current 3D perception methods, especially specialized small models, exhibit poor generalization in open scenarios. On the other hand, multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks, due to weak 3D local spatial object perception, poor text-based geometric numerical output, and inability to handle camera focal variations. To address these challenges, we propose the following solutions: Spatial-Enha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07422","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/2408.07422/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":"2026-07-05T10:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+b6bfuVZyrMMQ0cLkZRBcGMVxxCSghD5X/jfyBF3kSAeuN4hPLIY47gQFlzbBlh7yQJjJcmvpZyjKsjzor2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:35:57.782834Z"},"content_sha256":"5cb911f0b1a215b755fc2a3a878608159984850e437f558e6ef9f3de08f6bce1","schema_version":"1.0","event_id":"sha256:5cb911f0b1a215b755fc2a3a878608159984850e437f558e6ef9f3de08f6bce1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NRBIH63RRXNUUFCNZRCGZ5NJQM/bundle.json","state_url":"https://pith.science/pith/NRBIH63RRXNUUFCNZRCGZ5NJQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NRBIH63RRXNUUFCNZRCGZ5NJQM/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":"2026-08-17T18:35:57Z","links":{"resolver":"https://pith.science/pith/NRBIH63RRXNUUFCNZRCGZ5NJQM","bundle":"https://pith.science/pith/NRBIH63RRXNUUFCNZRCGZ5NJQM/bundle.json","state":"https://pith.science/pith/NRBIH63RRXNUUFCNZRCGZ5NJQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NRBIH63RRXNUUFCNZRCGZ5NJQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NRBIH63RRXNUUFCNZRCGZ5NJQM","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":"6be4e9635f51c8cbdb16ec098d32077e844ad465ccee6f7bdcb21e3c36ae63fa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T10:00:16Z","title_canon_sha256":"1e48620ecb4c0697000a6b7e00b2da764e5ebf670f3da52d1109a7db68298e1e"},"schema_version":"1.0","source":{"id":"2408.07422","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07422","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07422v2","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07422","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"NRBIH63RRXNU","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"pith_short_16","alias_value":"NRBIH63RRXNUUFCN","created_at":"2026-07-05T10:13:42Z"},{"alias_kind":"pith_short_8","alias_value":"NRBIH63R","created_at":"2026-07-05T10:13:42Z"}],"graph_snapshots":[{"event_id":"sha256:5cb911f0b1a215b755fc2a3a878608159984850e437f558e6ef9f3de08f6bce1","target":"graph","created_at":"2026-07-05T10:13:42Z","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/2408.07422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in autonomous driving, augmented reality, robotics, and embodied intelligence have necessitated 3D perception algorithms. However, current 3D perception methods, especially specialized small models, exhibit poor generalization in open scenarios. On the other hand, multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks, due to weak 3D local spatial object perception, poor text-based geometric numerical output, and inability to handle camera focal variations. To address these challenges, we propose the following solutions: Spatial-Enha","authors_text":"Fan Yang, Guiguang Ding, Haonan Lu, Hui Chen, Jungong Han, Sicheng Zhao, Yanhao Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T10:00:16Z","title":"LLMI3D: MLLM-based 3D Perception from a Single 2D Image"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07422","kind":"arxiv","version":2},"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":"sha256:5f6b9ce9774ba2d189e88bd64c7a69a2a390add8fd86b18dd44b41f5cf744578","target":"record","created_at":"2026-07-05T10:13:42Z","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":"6be4e9635f51c8cbdb16ec098d32077e844ad465ccee6f7bdcb21e3c36ae63fa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T10:00:16Z","title_canon_sha256":"1e48620ecb4c0697000a6b7e00b2da764e5ebf670f3da52d1109a7db68298e1e"},"schema_version":"1.0","source":{"id":"2408.07422","kind":"arxiv","version":2}},"canonical_sha256":"6c4283fb718ddb4a144dcc446cf5a9832515d278b2ff27a24448a99069d55b52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c4283fb718ddb4a144dcc446cf5a9832515d278b2ff27a24448a99069d55b52","first_computed_at":"2026-07-05T10:13:42.385677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:42.385677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dN1Uvy2eKNV/vIrTQHyQl04hEEGgKSZZ0wmv2Vo8KeSy50GQFliAwVxlz9bhiGPQUjDZ/0dl+fo1RhfvfAORCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:42.386186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07422","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f6b9ce9774ba2d189e88bd64c7a69a2a390add8fd86b18dd44b41f5cf744578","sha256:5cb911f0b1a215b755fc2a3a878608159984850e437f558e6ef9f3de08f6bce1"],"state_sha256":"b286e1c220df6a6a843b5525364e25e1acaff0082e42b6210772ccc7ed83302e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wtxlxBWPYKCaPEIIuj7HGtYJXSWy95wwENN1QFOF2xd/AM11jSN9oMtaMfUJcXCM14rYWvWCpVqETY9qtGTvDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:35:57.790990Z","bundle_sha256":"9bc1edc40899a656b13456768aec07f002b1d4573856f6af2012b0299b6ea5ca"}}