{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R56WWKV5VAFUSL6JLZ3JNSBKIN","short_pith_number":"pith:R56WWKV5","schema_version":"1.0","canonical_sha256":"8f7d6b2abda80b492fc95e7696c82a434404d85b0d6445ea1679cc1bab5d5317","source":{"kind":"arxiv","id":"2406.13246","version":2},"attestation_state":"computed","paper":{"title":"GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jana Kosecka, Navid Rajabi","submitted_at":"2024-06-19T06:15:26Z","abstract_excerpt":"The ability to understand and reason about spatial relationships between objects in images is an important component of visual reasoning. This skill rests on the ability to recognize and localize objects of interest and determine their spatial relation. Early vision and language models (VLMs) have been shown to struggle to recognize spatial relations. We extend the previously released What'sUp dataset and propose a novel comprehensive evaluation for spatial relationship understanding that highlights the strengths and weaknesses of 27 different models. In addition to the VLMs evaluated in What'"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.13246","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T06:15:26Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"95a380a0d1e6964b73e33e9f8f9355d0b182894398caa36cc956087e0733325e","abstract_canon_sha256":"1a710eb62cee16572545e48fdc1a542671e2c963c30570b578e173c43ef1ff8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:52.787202Z","signature_b64":"BWtcsvYEu2w/30ZVXKj0ohPZieaf0MXbinv715Eq8PikwJA2JHVQiILNhPrjEfjoLN2jzlUWeHPHlCeJDVs3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f7d6b2abda80b492fc95e7696c82a434404d85b0d6445ea1679cc1bab5d5317","last_reissued_at":"2026-07-05T09:18:52.786727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:52.786727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jana Kosecka, Navid Rajabi","submitted_at":"2024-06-19T06:15:26Z","abstract_excerpt":"The ability to understand and reason about spatial relationships between objects in images is an important component of visual reasoning. This skill rests on the ability to recognize and localize objects of interest and determine their spatial relation. Early vision and language models (VLMs) have been shown to struggle to recognize spatial relations. We extend the previously released What'sUp dataset and propose a novel comprehensive evaluation for spatial relationship understanding that highlights the strengths and weaknesses of 27 different models. In addition to the VLMs evaluated in What'"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13246","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/2406.13246/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.13246","created_at":"2026-07-05T09:18:52.786783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13246v2","created_at":"2026-07-05T09:18:52.786783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13246","created_at":"2026-07-05T09:18:52.786783+00:00"},{"alias_kind":"pith_short_12","alias_value":"R56WWKV5VAFU","created_at":"2026-07-05T09:18:52.786783+00:00"},{"alias_kind":"pith_short_16","alias_value":"R56WWKV5VAFUSL6J","created_at":"2026-07-05T09:18:52.786783+00:00"},{"alias_kind":"pith_short_8","alias_value":"R56WWKV5","created_at":"2026-07-05T09:18:52.786783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30557","citing_title":"Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23898","citing_title":"SPACENUM: Revisiting Spatial Numerical Understanding in VLMs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07148","citing_title":"Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R56WWKV5VAFUSL6JLZ3JNSBKIN","json":"https://pith.science/pith/R56WWKV5VAFUSL6JLZ3JNSBKIN.json","graph_json":"https://pith.science/api/pith-number/R56WWKV5VAFUSL6JLZ3JNSBKIN/graph.json","events_json":"https://pith.science/api/pith-number/R56WWKV5VAFUSL6JLZ3JNSBKIN/events.json","paper":"https://pith.science/paper/R56WWKV5"},"agent_actions":{"view_html":"https://pith.science/pith/R56WWKV5VAFUSL6JLZ3JNSBKIN","download_json":"https://pith.science/pith/R56WWKV5VAFUSL6JLZ3JNSBKIN.json","view_paper":"https://pith.science/paper/R56WWKV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13246&json=true","fetch_graph":"https://pith.science/api/pith-number/R56WWKV5VAFUSL6JLZ3JNSBKIN/graph.json","fetch_events":"https://pith.science/api/pith-number/R56WWKV5VAFUSL6JLZ3JNSBKIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R56WWKV5VAFUSL6JLZ3JNSBKIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R56WWKV5VAFUSL6JLZ3JNSBKIN/action/storage_attestation","attest_author":"https://pith.science/pith/R56WWKV5VAFUSL6JLZ3JNSBKIN/action/author_attestation","sign_citation":"https://pith.science/pith/R56WWKV5VAFUSL6JLZ3JNSBKIN/action/citation_signature","submit_replication":"https://pith.science/pith/R56WWKV5VAFUSL6JLZ3JNSBKIN/action/replication_record"}},"created_at":"2026-07-05T09:18:52.786783+00:00","updated_at":"2026-07-05T09:18:52.786783+00:00"}