{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UR5W6RKVJWTQIGSNZCZESQ3JHS","short_pith_number":"pith:UR5W6RKV","schema_version":"1.0","canonical_sha256":"a47b6f45554da7041a4dc8b24943693c96840d629311a21541513a90c2d415f6","source":{"kind":"arxiv","id":"2502.04359","version":1},"attestation_state":"computed","paper":{"title":"Exploring Spatial Language Grounding Through Referring Expressions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Akshar Tumu, Parisa Kordjamshidi","submitted_at":"2025-02-04T22:58:15Z","abstract_excerpt":"Spatial Reasoning is an important component of human cognition and is an area in which the latest Vision-language models (VLMs) show signs of difficulty. The current analysis works use image captioning tasks and visual question answering. In this work, we propose using the Referring Expression Comprehension task instead as a platform for the evaluation of spatial reasoning by VLMs. This platform provides the opportunity for a deeper analysis of spatial comprehension and grounding abilities when there is 1) ambiguity in object detection, 2) complex spatial expressions with a longer sentence str"},"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":"2502.04359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T22:58:15Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"45ac5e544835e0e99be0601bede411991624e0aea48e8f1c3cbe924046a2b507","abstract_canon_sha256":"c2635942d95bef13155a5e49219e40c6f066bd47abee784c47068362cced3264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:50.274722Z","signature_b64":"aemiA8bYN3i9h3etb1rbT4yhRWN/CX4HO+ZwWe9FLGcHJyq9P+UonRYdZixngbhk/hxaUhs3iuTbyeE1pdjIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a47b6f45554da7041a4dc8b24943693c96840d629311a21541513a90c2d415f6","last_reissued_at":"2026-07-05T10:10:50.274223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:50.274223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Spatial Language Grounding Through Referring Expressions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Akshar Tumu, Parisa Kordjamshidi","submitted_at":"2025-02-04T22:58:15Z","abstract_excerpt":"Spatial Reasoning is an important component of human cognition and is an area in which the latest Vision-language models (VLMs) show signs of difficulty. The current analysis works use image captioning tasks and visual question answering. In this work, we propose using the Referring Expression Comprehension task instead as a platform for the evaluation of spatial reasoning by VLMs. This platform provides the opportunity for a deeper analysis of spatial comprehension and grounding abilities when there is 1) ambiguity in object detection, 2) complex spatial expressions with a longer sentence str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04359","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/2502.04359/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":"2502.04359","created_at":"2026-07-05T10:10:50.274280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04359v1","created_at":"2026-07-05T10:10:50.274280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04359","created_at":"2026-07-05T10:10:50.274280+00:00"},{"alias_kind":"pith_short_12","alias_value":"UR5W6RKVJWTQ","created_at":"2026-07-05T10:10:50.274280+00:00"},{"alias_kind":"pith_short_16","alias_value":"UR5W6RKVJWTQIGSN","created_at":"2026-07-05T10:10:50.274280+00:00"},{"alias_kind":"pith_short_8","alias_value":"UR5W6RKV","created_at":"2026-07-05T10:10:50.274280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UR5W6RKVJWTQIGSNZCZESQ3JHS","json":"https://pith.science/pith/UR5W6RKVJWTQIGSNZCZESQ3JHS.json","graph_json":"https://pith.science/api/pith-number/UR5W6RKVJWTQIGSNZCZESQ3JHS/graph.json","events_json":"https://pith.science/api/pith-number/UR5W6RKVJWTQIGSNZCZESQ3JHS/events.json","paper":"https://pith.science/paper/UR5W6RKV"},"agent_actions":{"view_html":"https://pith.science/pith/UR5W6RKVJWTQIGSNZCZESQ3JHS","download_json":"https://pith.science/pith/UR5W6RKVJWTQIGSNZCZESQ3JHS.json","view_paper":"https://pith.science/paper/UR5W6RKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04359&json=true","fetch_graph":"https://pith.science/api/pith-number/UR5W6RKVJWTQIGSNZCZESQ3JHS/graph.json","fetch_events":"https://pith.science/api/pith-number/UR5W6RKVJWTQIGSNZCZESQ3JHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UR5W6RKVJWTQIGSNZCZESQ3JHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UR5W6RKVJWTQIGSNZCZESQ3JHS/action/storage_attestation","attest_author":"https://pith.science/pith/UR5W6RKVJWTQIGSNZCZESQ3JHS/action/author_attestation","sign_citation":"https://pith.science/pith/UR5W6RKVJWTQIGSNZCZESQ3JHS/action/citation_signature","submit_replication":"https://pith.science/pith/UR5W6RKVJWTQIGSNZCZESQ3JHS/action/replication_record"}},"created_at":"2026-07-05T10:10:50.274280+00:00","updated_at":"2026-07-05T10:10:50.274280+00:00"}