{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AOL7L6UUQ6ZUZDVOB36DZAJBGB","short_pith_number":"pith:AOL7L6UU","canonical_record":{"source":{"id":"2411.13112","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T08:14:01Z","cross_cats_sorted":[],"title_canon_sha256":"30937b39b44f5ba523e0a8cdea8321e075b0286e0a07eacfbba38ca632fcfeed","abstract_canon_sha256":"f96f5eb88a401352926453ba5d1980905a82bc5bbc1a02ce0d0237cc7ce81314"},"schema_version":"1.0"},"canonical_sha256":"0397f5fa9487b34c8eae0efc3c8121304071fdcabfe1f0baf34666728820937a","source":{"kind":"arxiv","id":"2411.13112","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13112","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13112v3","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13112","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"AOL7L6UUQ6ZU","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"AOL7L6UUQ6ZUZDVO","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"AOL7L6UU","created_at":"2026-07-05T11:10:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AOL7L6UUQ6ZUZDVOB36DZAJBGB","target":"record","payload":{"canonical_record":{"source":{"id":"2411.13112","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T08:14:01Z","cross_cats_sorted":[],"title_canon_sha256":"30937b39b44f5ba523e0a8cdea8321e075b0286e0a07eacfbba38ca632fcfeed","abstract_canon_sha256":"f96f5eb88a401352926453ba5d1980905a82bc5bbc1a02ce0d0237cc7ce81314"},"schema_version":"1.0"},"canonical_sha256":"0397f5fa9487b34c8eae0efc3c8121304071fdcabfe1f0baf34666728820937a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:33.305515Z","signature_b64":"IBNgHVoHVm26XxzYdIt82nhuLpyC43D5ahDbL4llw5DgIYSoTNVW+hYT0k0Gj0mMzFTP8JufGOapyKe8/Na9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0397f5fa9487b34c8eae0efc3c8121304071fdcabfe1f0baf34666728820937a","last_reissued_at":"2026-07-05T11:10:33.304959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:33.304959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.13112","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s6O03XPVl4e4kECjGWY/czsCJo9ynQYEeMTsDRMXMO7daU35ImRUJm6TEPLyQanB3utYVqRFWTD71y9EbPS1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:06:19.231468Z"},"content_sha256":"f937d5fcf5a5ea28a9ceb3149f5a834f871313eba7a803fff3aeb8c5380843cb","schema_version":"1.0","event_id":"sha256:f937d5fcf5a5ea28a9ceb3149f5a834f871313eba7a803fff3aeb8c5380843cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AOL7L6UUQ6ZUZDVOB36DZAJBGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenming Zhang, Dujun Nie, Hao Zhao, Long Chen, Ruijun Zhang, Shuai Liu, Wenke Huang, Xianda Guo, Yiqun Duan, Yuhang He","submitted_at":"2024-11-20T08:14:01Z","abstract_excerpt":"Accurate spatial reasoning in outdoor environments - covering geometry, object pose, and inter-object relationships - is fundamental to downstream tasks such as mapping, motion forecasting, and high-level planning in autonomous driving. We introduce SURDS, a large-scale benchmark designed to systematically evaluate the spatial reasoning capabilities of vision language models (VLMs). Built on the nuScenes dataset, SURDS comprises 41,080 vision-question-answer training instances and 9,250 evaluation samples, spanning six spatial categories: orientation, depth estimation, pixel-level localization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13112","kind":"arxiv","version":3},"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/2411.13112/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":"2026-07-05T11:10:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUO/ApGwF0Pghfdhw4Kxbz077pMHtvA4fNNa+bvtbNumXAbp9GHnMnMnU5wNDVzvL0zD1fRGnLAMi1tlp9lMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:06:19.231985Z"},"content_sha256":"b6c3ee53c461a6adf6b404948593ea2756e4f8ef539955350e18e27b7b800466","schema_version":"1.0","event_id":"sha256:b6c3ee53c461a6adf6b404948593ea2756e4f8ef539955350e18e27b7b800466"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AOL7L6UUQ6ZUZDVOB36DZAJBGB/bundle.json","state_url":"https://pith.science/pith/AOL7L6UUQ6ZUZDVOB36DZAJBGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AOL7L6UUQ6ZUZDVOB36DZAJBGB/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":"2026-08-20T06:06:19Z","links":{"resolver":"https://pith.science/pith/AOL7L6UUQ6ZUZDVOB36DZAJBGB","bundle":"https://pith.science/pith/AOL7L6UUQ6ZUZDVOB36DZAJBGB/bundle.json","state":"https://pith.science/pith/AOL7L6UUQ6ZUZDVOB36DZAJBGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AOL7L6UUQ6ZUZDVOB36DZAJBGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AOL7L6UUQ6ZUZDVOB36DZAJBGB","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":"f96f5eb88a401352926453ba5d1980905a82bc5bbc1a02ce0d0237cc7ce81314","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T08:14:01Z","title_canon_sha256":"30937b39b44f5ba523e0a8cdea8321e075b0286e0a07eacfbba38ca632fcfeed"},"schema_version":"1.0","source":{"id":"2411.13112","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13112","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13112v3","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13112","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"AOL7L6UUQ6ZU","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"AOL7L6UUQ6ZUZDVO","created_at":"2026-07-05T11:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"AOL7L6UU","created_at":"2026-07-05T11:10:33Z"}],"graph_snapshots":[{"event_id":"sha256:b6c3ee53c461a6adf6b404948593ea2756e4f8ef539955350e18e27b7b800466","target":"graph","created_at":"2026-07-05T11:10:33Z","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/2411.13112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate spatial reasoning in outdoor environments - covering geometry, object pose, and inter-object relationships - is fundamental to downstream tasks such as mapping, motion forecasting, and high-level planning in autonomous driving. We introduce SURDS, a large-scale benchmark designed to systematically evaluate the spatial reasoning capabilities of vision language models (VLMs). Built on the nuScenes dataset, SURDS comprises 41,080 vision-question-answer training instances and 9,250 evaluation samples, spanning six spatial categories: orientation, depth estimation, pixel-level localization","authors_text":"Chenming Zhang, Dujun Nie, Hao Zhao, Long Chen, Ruijun Zhang, Shuai Liu, Wenke Huang, Xianda Guo, Yiqun Duan, Yuhang He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T08:14:01Z","title":"SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13112","kind":"arxiv","version":3},"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:f937d5fcf5a5ea28a9ceb3149f5a834f871313eba7a803fff3aeb8c5380843cb","target":"record","created_at":"2026-07-05T11:10:33Z","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":"f96f5eb88a401352926453ba5d1980905a82bc5bbc1a02ce0d0237cc7ce81314","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T08:14:01Z","title_canon_sha256":"30937b39b44f5ba523e0a8cdea8321e075b0286e0a07eacfbba38ca632fcfeed"},"schema_version":"1.0","source":{"id":"2411.13112","kind":"arxiv","version":3}},"canonical_sha256":"0397f5fa9487b34c8eae0efc3c8121304071fdcabfe1f0baf34666728820937a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0397f5fa9487b34c8eae0efc3c8121304071fdcabfe1f0baf34666728820937a","first_computed_at":"2026-07-05T11:10:33.304959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:33.304959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IBNgHVoHVm26XxzYdIt82nhuLpyC43D5ahDbL4llw5DgIYSoTNVW+hYT0k0Gj0mMzFTP8JufGOapyKe8/Na9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:33.305515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13112","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f937d5fcf5a5ea28a9ceb3149f5a834f871313eba7a803fff3aeb8c5380843cb","sha256:b6c3ee53c461a6adf6b404948593ea2756e4f8ef539955350e18e27b7b800466"],"state_sha256":"561614b455a7dff2a010393a03ba9ac0474a6ac65778cc9e17c90ee88417e6bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zi222fFt2BpZfLrJphpXILH5aMfCUIiKmr1y2r++4r1ankfEQEQJpNw9Ws5YqyMOdOmKYHF/Y8K7XQv5NWC3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:06:19.236832Z","bundle_sha256":"319a171176dc13a337a2642d48253dc928327298ba7179a387984868c952803b"}}