{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T7BGU7JDCC2YILVGAF5D3ZW2VQ","short_pith_number":"pith:T7BGU7JD","canonical_record":{"source":{"id":"2409.09788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T16:45:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2ab8f2ba84d33970ccb4dab2da678d951efa02b87eaa0a4bd4d2d6dfcb9e6204","abstract_canon_sha256":"ae26cde13f6e5325f19b6176a5896bc50f2ac5b6a9cea693f64e6bace5ca1074"},"schema_version":"1.0"},"canonical_sha256":"9fc26a7d2310b5842ea6017a3de6daac091163171b292ce1c53099e701b5ebd8","source":{"kind":"arxiv","id":"2409.09788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09788","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09788v1","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09788","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"pith_short_12","alias_value":"T7BGU7JDCC2Y","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"pith_short_16","alias_value":"T7BGU7JDCC2YILVG","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"pith_short_8","alias_value":"T7BGU7JD","created_at":"2026-07-05T09:07:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T7BGU7JDCC2YILVGAF5D3ZW2VQ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.09788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T16:45:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2ab8f2ba84d33970ccb4dab2da678d951efa02b87eaa0a4bd4d2d6dfcb9e6204","abstract_canon_sha256":"ae26cde13f6e5325f19b6176a5896bc50f2ac5b6a9cea693f64e6bace5ca1074"},"schema_version":"1.0"},"canonical_sha256":"9fc26a7d2310b5842ea6017a3de6daac091163171b292ce1c53099e701b5ebd8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:14.719203Z","signature_b64":"FvHafwMFlh/LIbsQnTJMNtSh65ZNyft1Rbx64qPCbaLLHWLs3aYe3SLviC8C0WDV0KjXU6oOv046ho/SX4qIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fc26a7d2310b5842ea6017a3de6daac091163171b292ce1c53099e701b5ebd8","last_reissued_at":"2026-07-05T09:07:14.718683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:14.718683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.09788","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":"2026-07-05T09:07:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qao4h0p08JYA90YzvU+/Co1EWMsq/Y3lg1g7EjHJ1wwbps5w5QgE6RG9ggz7CwX8d7TMD5A4EvDJV+vBm8wyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:30:29.779603Z"},"content_sha256":"48a5bac19ae9bd175ef811d1ae9253d050c01ca3465d4f673ac445dba5c4e438","schema_version":"1.0","event_id":"sha256:48a5bac19ae9bd175ef811d1ae9253d050c01ca3465d4f673ac445dba5c4e438"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T7BGU7JDCC2YILVGAF5D3ZW2VQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"David Acuna, Rafid Mahmood, Sanja Fidler, Yuan-Hong Liao","submitted_at":"2024-09-15T16:45:42Z","abstract_excerpt":"Despite recent advances demonstrating vision-language models' (VLMs) abilities to describe complex relationships in images using natural language, their capability to quantitatively reason about object sizes and distances remains underexplored. In this work, we introduce a manually annotated benchmark, Q-Spatial Bench, with 271 questions across five categories designed for quantitative spatial reasoning and systematically investigate the performance of state-of-the-art VLMs on this task. Our analysis reveals that reasoning about distances between objects is particularly challenging for SoTA VL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09788","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/2409.09788/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":"2026-07-05T09:07:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YuBP9qqfyG9RN98U6U9qg5p1M7o6ulDrevpHVXLKCJ3BVTPZBhRGh5K/x30NQb7OCs8qzwDGnV7ZrQeKsE2nBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:30:29.779973Z"},"content_sha256":"169f84fa5886e4d41eb8d00d5170a3b9b314f1904bb0d9a00245cb2204230b45","schema_version":"1.0","event_id":"sha256:169f84fa5886e4d41eb8d00d5170a3b9b314f1904bb0d9a00245cb2204230b45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7BGU7JDCC2YILVGAF5D3ZW2VQ/bundle.json","state_url":"https://pith.science/pith/T7BGU7JDCC2YILVGAF5D3ZW2VQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7BGU7JDCC2YILVGAF5D3ZW2VQ/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":"2026-07-09T03:30:29Z","links":{"resolver":"https://pith.science/pith/T7BGU7JDCC2YILVGAF5D3ZW2VQ","bundle":"https://pith.science/pith/T7BGU7JDCC2YILVGAF5D3ZW2VQ/bundle.json","state":"https://pith.science/pith/T7BGU7JDCC2YILVGAF5D3ZW2VQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7BGU7JDCC2YILVGAF5D3ZW2VQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T7BGU7JDCC2YILVGAF5D3ZW2VQ","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":"ae26cde13f6e5325f19b6176a5896bc50f2ac5b6a9cea693f64e6bace5ca1074","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T16:45:42Z","title_canon_sha256":"2ab8f2ba84d33970ccb4dab2da678d951efa02b87eaa0a4bd4d2d6dfcb9e6204"},"schema_version":"1.0","source":{"id":"2409.09788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09788","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09788v1","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09788","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"pith_short_12","alias_value":"T7BGU7JDCC2Y","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"pith_short_16","alias_value":"T7BGU7JDCC2YILVG","created_at":"2026-07-05T09:07:14Z"},{"alias_kind":"pith_short_8","alias_value":"T7BGU7JD","created_at":"2026-07-05T09:07:14Z"}],"graph_snapshots":[{"event_id":"sha256:169f84fa5886e4d41eb8d00d5170a3b9b314f1904bb0d9a00245cb2204230b45","target":"graph","created_at":"2026-07-05T09:07:14Z","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/2409.09788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances demonstrating vision-language models' (VLMs) abilities to describe complex relationships in images using natural language, their capability to quantitatively reason about object sizes and distances remains underexplored. In this work, we introduce a manually annotated benchmark, Q-Spatial Bench, with 271 questions across five categories designed for quantitative spatial reasoning and systematically investigate the performance of state-of-the-art VLMs on this task. Our analysis reveals that reasoning about distances between objects is particularly challenging for SoTA VL","authors_text":"David Acuna, Rafid Mahmood, Sanja Fidler, Yuan-Hong Liao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T16:45:42Z","title":"Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09788","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":"sha256:48a5bac19ae9bd175ef811d1ae9253d050c01ca3465d4f673ac445dba5c4e438","target":"record","created_at":"2026-07-05T09:07:14Z","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":"ae26cde13f6e5325f19b6176a5896bc50f2ac5b6a9cea693f64e6bace5ca1074","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T16:45:42Z","title_canon_sha256":"2ab8f2ba84d33970ccb4dab2da678d951efa02b87eaa0a4bd4d2d6dfcb9e6204"},"schema_version":"1.0","source":{"id":"2409.09788","kind":"arxiv","version":1}},"canonical_sha256":"9fc26a7d2310b5842ea6017a3de6daac091163171b292ce1c53099e701b5ebd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fc26a7d2310b5842ea6017a3de6daac091163171b292ce1c53099e701b5ebd8","first_computed_at":"2026-07-05T09:07:14.718683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:14.718683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FvHafwMFlh/LIbsQnTJMNtSh65ZNyft1Rbx64qPCbaLLHWLs3aYe3SLviC8C0WDV0KjXU6oOv046ho/SX4qIBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:14.719203Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48a5bac19ae9bd175ef811d1ae9253d050c01ca3465d4f673ac445dba5c4e438","sha256:169f84fa5886e4d41eb8d00d5170a3b9b314f1904bb0d9a00245cb2204230b45"],"state_sha256":"b59eb94782b22ae8e7be49c215b3ccbe38a3b414072aee0d5b1bd25839637ff7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EHNf4lelHuCupIKK+q+pC5HGLNLtcQ5bEqsF3058hH1gUbsOVyWgpgu/e2srfPkr+7MBIvO90kcRFcm6WBLcDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:30:29.782061Z","bundle_sha256":"1f20c4889fe0a3f4b48b50b3b93c73bc6b267e009a854375e5a2ae4b1bd74203"}}