{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ADUVKJQLVHBYP7MHOYAZ5EFO7N","short_pith_number":"pith:ADUVKJQL","schema_version":"1.0","canonical_sha256":"00e955260ba9c387fd8776019e90aefb4b1e9a1b409cba4e6d085176d8e24cf9","source":{"kind":"arxiv","id":"2607.00491","version":1},"attestation_state":"computed","paper":{"title":"MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Leyuan Yu, Minghao Liu, Naoto Yokoya, Qunshu Lin, Sheng Zhou, Weihao Xuan, Xiaokai Bai, Xiao Tang, Xinyuan Li","submitted_at":"2026-07-01T06:19:54Z","abstract_excerpt":"Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input. Existing what-if tasks typically vary the observer while keeping the scene fixed. Can VLMs instead predict the consequences of hypothetically moving or rotating an object? We introduce MindEdit-Bench, a benchmark of six spatial reasoning tasks built from three-photo smartphone triplets of newly captured indoor scenes via an automatic in-the-wild 3D scene-graph extraction pipeline. Four tasks probe perception and perspective transformation over observ"},"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":"2607.00491","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T06:19:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0b4f070cb54188aa8580e7ac30775298dca5e009ca5611c496c4ba29ce9b4ebd","abstract_canon_sha256":"1eb6eca650c764089e99f46ddbf05236a0474898d51240623b200f41e37f26df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:44.927844Z","signature_b64":"zCouTNwSzCGiyuBNKwKgNH4zgUjcjBXNPjO4cxkWAvz1OGP5+ksU5vglz4ilAGbDCgDFb1cEugzvzu+QoVmYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00e955260ba9c387fd8776019e90aefb4b1e9a1b409cba4e6d085176d8e24cf9","last_reissued_at":"2026-07-02T01:17:44.927426Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:44.927426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Leyuan Yu, Minghao Liu, Naoto Yokoya, Qunshu Lin, Sheng Zhou, Weihao Xuan, Xiaokai Bai, Xiao Tang, Xinyuan Li","submitted_at":"2026-07-01T06:19:54Z","abstract_excerpt":"Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input. Existing what-if tasks typically vary the observer while keeping the scene fixed. Can VLMs instead predict the consequences of hypothetically moving or rotating an object? We introduce MindEdit-Bench, a benchmark of six spatial reasoning tasks built from three-photo smartphone triplets of newly captured indoor scenes via an automatic in-the-wild 3D scene-graph extraction pipeline. Four tasks probe perception and perspective transformation over observ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00491","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/2607.00491/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":"2607.00491","created_at":"2026-07-02T01:17:44.927491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00491v1","created_at":"2026-07-02T01:17:44.927491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00491","created_at":"2026-07-02T01:17:44.927491+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADUVKJQLVHBY","created_at":"2026-07-02T01:17:44.927491+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADUVKJQLVHBYP7MH","created_at":"2026-07-02T01:17:44.927491+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADUVKJQL","created_at":"2026-07-02T01:17:44.927491+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/ADUVKJQLVHBYP7MHOYAZ5EFO7N","json":"https://pith.science/pith/ADUVKJQLVHBYP7MHOYAZ5EFO7N.json","graph_json":"https://pith.science/api/pith-number/ADUVKJQLVHBYP7MHOYAZ5EFO7N/graph.json","events_json":"https://pith.science/api/pith-number/ADUVKJQLVHBYP7MHOYAZ5EFO7N/events.json","paper":"https://pith.science/paper/ADUVKJQL"},"agent_actions":{"view_html":"https://pith.science/pith/ADUVKJQLVHBYP7MHOYAZ5EFO7N","download_json":"https://pith.science/pith/ADUVKJQLVHBYP7MHOYAZ5EFO7N.json","view_paper":"https://pith.science/paper/ADUVKJQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00491&json=true","fetch_graph":"https://pith.science/api/pith-number/ADUVKJQLVHBYP7MHOYAZ5EFO7N/graph.json","fetch_events":"https://pith.science/api/pith-number/ADUVKJQLVHBYP7MHOYAZ5EFO7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADUVKJQLVHBYP7MHOYAZ5EFO7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADUVKJQLVHBYP7MHOYAZ5EFO7N/action/storage_attestation","attest_author":"https://pith.science/pith/ADUVKJQLVHBYP7MHOYAZ5EFO7N/action/author_attestation","sign_citation":"https://pith.science/pith/ADUVKJQLVHBYP7MHOYAZ5EFO7N/action/citation_signature","submit_replication":"https://pith.science/pith/ADUVKJQLVHBYP7MHOYAZ5EFO7N/action/replication_record"}},"created_at":"2026-07-02T01:17:44.927491+00:00","updated_at":"2026-07-02T01:17:44.927491+00:00"}