{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B42LD3RDC4MA4YPHIRG3GGR5RK","short_pith_number":"pith:B42LD3RD","schema_version":"1.0","canonical_sha256":"0f34b1ee2317180e61e7444db31a3d8a89f8b6a1d9ec2e9839eb74785cd391cf","source":{"kind":"arxiv","id":"2607.21072","version":1},"attestation_state":"computed","paper":{"title":"Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaixiang Yao, Miao Pan, Wenqi Zhang, Xiaohe Zhou, Xuanyu Liu, Xuhong Zhang, Xu Wang","submitted_at":"2026-07-23T09:04:48Z","abstract_excerpt":"Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks are grounded in continuous visual scenes, where locations, regions, and paths are more naturally expressed by pointing, marking, or drawing than by reporting precise coordinates or discrete textual symbols. Yet existing spatial reasoning benchmarks usually require coordinates, options, or text, creating an answer-interface mismatch for image-generation models. This makes it difficult to evaluate image-generation models under the same task semant"},"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":"2607.21072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T09:04:48Z","cross_cats_sorted":[],"title_canon_sha256":"ba3fd3aa75660afbcc66b7b5e9ef02339807b809f9eff001adfe9484a6491d70","abstract_canon_sha256":"cb53f581baf7922c5f3e79da50866b6e90fe4717833fac017cea42dda2e49074"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:50.403004Z","signature_b64":"RpW3l2E5xbI178N1/tVCxc0052FXKQCBhFrYmJu1NZa/5JG0o4PZ1DNp9CICwepKhvblJGgEzgMNrzcmREedDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f34b1ee2317180e61e7444db31a3d8a89f8b6a1d9ec2e9839eb74785cd391cf","last_reissued_at":"2026-07-24T01:23:50.402120Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:50.402120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaixiang Yao, Miao Pan, Wenqi Zhang, Xiaohe Zhou, Xuanyu Liu, Xuhong Zhang, Xu Wang","submitted_at":"2026-07-23T09:04:48Z","abstract_excerpt":"Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks are grounded in continuous visual scenes, where locations, regions, and paths are more naturally expressed by pointing, marking, or drawing than by reporting precise coordinates or discrete textual symbols. Yet existing spatial reasoning benchmarks usually require coordinates, options, or text, creating an answer-interface mismatch for image-generation models. This makes it difficult to evaluate image-generation models under the same task semant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21072","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/2607.21072/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":"2607.21072","created_at":"2026-07-24T01:23:50.402590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21072v1","created_at":"2026-07-24T01:23:50.402590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21072","created_at":"2026-07-24T01:23:50.402590+00:00"},{"alias_kind":"pith_short_12","alias_value":"B42LD3RDC4MA","created_at":"2026-07-24T01:23:50.402590+00:00"},{"alias_kind":"pith_short_16","alias_value":"B42LD3RDC4MA4YPH","created_at":"2026-07-24T01:23:50.402590+00:00"},{"alias_kind":"pith_short_8","alias_value":"B42LD3RD","created_at":"2026-07-24T01:23:50.402590+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/B42LD3RDC4MA4YPHIRG3GGR5RK","json":"https://pith.science/pith/B42LD3RDC4MA4YPHIRG3GGR5RK.json","graph_json":"https://pith.science/api/pith-number/B42LD3RDC4MA4YPHIRG3GGR5RK/graph.json","events_json":"https://pith.science/api/pith-number/B42LD3RDC4MA4YPHIRG3GGR5RK/events.json","paper":"https://pith.science/paper/B42LD3RD"},"agent_actions":{"view_html":"https://pith.science/pith/B42LD3RDC4MA4YPHIRG3GGR5RK","download_json":"https://pith.science/pith/B42LD3RDC4MA4YPHIRG3GGR5RK.json","view_paper":"https://pith.science/paper/B42LD3RD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21072&json=true","fetch_graph":"https://pith.science/api/pith-number/B42LD3RDC4MA4YPHIRG3GGR5RK/graph.json","fetch_events":"https://pith.science/api/pith-number/B42LD3RDC4MA4YPHIRG3GGR5RK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B42LD3RDC4MA4YPHIRG3GGR5RK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B42LD3RDC4MA4YPHIRG3GGR5RK/action/storage_attestation","attest_author":"https://pith.science/pith/B42LD3RDC4MA4YPHIRG3GGR5RK/action/author_attestation","sign_citation":"https://pith.science/pith/B42LD3RDC4MA4YPHIRG3GGR5RK/action/citation_signature","submit_replication":"https://pith.science/pith/B42LD3RDC4MA4YPHIRG3GGR5RK/action/replication_record"}},"created_at":"2026-07-24T01:23:50.402590+00:00","updated_at":"2026-07-24T01:23:50.402590+00:00"}