{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CQEI36IJNBHHZC2CHBUTGJ2QMZ","short_pith_number":"pith:CQEI36IJ","canonical_record":{"source":{"id":"2605.14704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T11:21:41Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"fb13c269bda0be01455a9e6ad02abdb673621e71c92e40ae576b22d11b96e459","abstract_canon_sha256":"54637346a93f1dc6c32674dbf6a01de1093a6119253cb8b203a427902373360a"},"schema_version":"1.0"},"canonical_sha256":"14088df909684e7c8b4238693327506666bc4de6bf1c46cbd714cf846ebb3700","source":{"kind":"arxiv","id":"2605.14704","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14704","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14704v1","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14704","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"CQEI36IJNBHH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CQEI36IJNBHHZC2C","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CQEI36IJ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CQEI36IJNBHHZC2CHBUTGJ2QMZ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T11:21:41Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"fb13c269bda0be01455a9e6ad02abdb673621e71c92e40ae576b22d11b96e459","abstract_canon_sha256":"54637346a93f1dc6c32674dbf6a01de1093a6119253cb8b203a427902373360a"},"schema_version":"1.0"},"canonical_sha256":"14088df909684e7c8b4238693327506666bc4de6bf1c46cbd714cf846ebb3700","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:59.291047Z","signature_b64":"gUM/+qaJRu9pWmN7gICd4x8zJ5PjCXrRoOyda3IksvK03ZMMywKg9cahFhEDjprGKtU3lD7f0VvouZ7qgWFGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14088df909684e7c8b4238693327506666bc4de6bf1c46cbd714cf846ebb3700","last_reissued_at":"2026-05-17T23:38:59.290291Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:59.290291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14704","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":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bp24xGtpPJUs3nqeEAURVUfBgLq1Y9zRRHtSKfFD5XwfAP2BeM6CiK+R51cK9kmU1ESJTE/0FTdry815QzlOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:28:48.416043Z"},"content_sha256":"b5a9fe3553165e512134bba6162ddf88a7abd9918ccf039be4f5b4e09ab0ab75","schema_version":"1.0","event_id":"sha256:b5a9fe3553165e512134bba6162ddf88a7abd9918ccf039be4f5b4e09ab0ab75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CQEI36IJNBHHZC2CHBUTGJ2QMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Vision-language models cannot reliably locate invisible functional objects from task instructions and commonsense.","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Gueter Josmy Faure, Hung-Ting Su, Posheng Chen, Powen Cheng, Winston H. Hsu","submitted_at":"2026-05-14T11:21:41Z","abstract_excerpt":"In real-world scenes, target objects may reside in regions that are not visible. While humans can often infer the locations of occluded objects from context and commonsense knowledge, this capability remains a major challenge for vision-language models (VLMs). To address this gap, we introduce SceneFunRI, a benchmark for Reasoning the Invisible. Based on the SceneFun3D dataset, SceneFunRI formulates the task as a 2D spatial reasoning problem via a semi-automatic pipeline and comprises 855 instances. It requires models to infer the locations of invisible functional objects from task instruction"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The strongest baseline model (Gemini 3 Flash) only achieves an CAcc@75 of 15.20, an mIoU of 0.74, and a Dist of 28.65. These findings indicate that invisible-region reasoning remains an unstable capability in current VLMs.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The semi-automatic pipeline accurately creates 855 instances that genuinely require commonsense and spatial reasoning beyond superficial visual cues, rather than introducing artifacts that explain the low model performance.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SceneFunRI benchmark shows current VLMs struggle severely with inferring locations of invisible functional objects, with the strongest model (Gemini 3 Flash) reaching only 15.20 CAcc@75.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Vision-language models cannot reliably locate invisible functional objects from task instructions and commonsense.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"350d4c16af96344b115a740becd405acb297eb7087801705eee37fe15c38c56e"},"source":{"id":"2605.14704","kind":"arxiv","version":1},"verdict":{"id":"cc070207-2f90-435d-958a-98bbded92077","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:00:12.913741Z","strongest_claim":"The strongest baseline model (Gemini 3 Flash) only achieves an CAcc@75 of 15.20, an mIoU of 0.74, and a Dist of 28.65. These findings indicate that invisible-region reasoning remains an unstable capability in current VLMs.","one_line_summary":"SceneFunRI benchmark shows current VLMs struggle severely with inferring locations of invisible functional objects, with the strongest model (Gemini 3 Flash) reaching only 15.20 CAcc@75.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The semi-automatic pipeline accurately creates 855 instances that genuinely require commonsense and spatial reasoning beyond superficial visual cues, rather than introducing artifacts that explain the low model performance.","pith_extraction_headline":"Vision-language models cannot reliably locate invisible functional objects from task instructions and commonsense."},"references":{"count":38,"sample":[{"doi":"","year":2023,"title":"Image amodal completion: A survey.Computer Vision and Image Understanding, 229:103661, 2023","work_id":"5d8af2fe-47c5-4081-9bec-1f7dacd64cb0","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Open-world amodal appearance completion","work_id":"9543665c-f2f4-42eb-b51f-11d38d50848d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"It’s not easy being wrong: Large language models struggle with process of elimination reasoning","work_id":"a031f5c6-c8f8-4b2a-b1dd-5578f2641958","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Scaling spatial intelligence with multimodal foundation models","work_id":"ceb84861-8bdb-4822-864c-8e2d0ae4d322","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes","work_id":"53329c45-0a4d-4522-8b6a-451a787fa9e7","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":38,"snapshot_sha256":"fa2f7fb6a2787cb6480867914701f164a310afa2322f804f54cb0933e767fcbc","internal_anchors":4},"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":"cc070207-2f90-435d-958a-98bbded92077"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ECe5TwCKL1lZ/B0165VuXvAS8cdh7hanJfCKu3h6eu+TVbUuTTveItFodvISQAlt4LS/hSrBe6QicFD9qrknBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:28:48.417380Z"},"content_sha256":"8fcfa9b4c619741cb9cc1e16d777393b5181aeb120d9e29694f88fa1e16220c0","schema_version":"1.0","event_id":"sha256:8fcfa9b4c619741cb9cc1e16d777393b5181aeb120d9e29694f88fa1e16220c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQEI36IJNBHHZC2CHBUTGJ2QMZ/bundle.json","state_url":"https://pith.science/pith/CQEI36IJNBHHZC2CHBUTGJ2QMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQEI36IJNBHHZC2CHBUTGJ2QMZ/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":"2026-05-31T14:28:48Z","links":{"resolver":"https://pith.science/pith/CQEI36IJNBHHZC2CHBUTGJ2QMZ","bundle":"https://pith.science/pith/CQEI36IJNBHHZC2CHBUTGJ2QMZ/bundle.json","state":"https://pith.science/pith/CQEI36IJNBHHZC2CHBUTGJ2QMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQEI36IJNBHHZC2CHBUTGJ2QMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CQEI36IJNBHHZC2CHBUTGJ2QMZ","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":"54637346a93f1dc6c32674dbf6a01de1093a6119253cb8b203a427902373360a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T11:21:41Z","title_canon_sha256":"fb13c269bda0be01455a9e6ad02abdb673621e71c92e40ae576b22d11b96e459"},"schema_version":"1.0","source":{"id":"2605.14704","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14704","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14704v1","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14704","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"CQEI36IJNBHH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CQEI36IJNBHHZC2C","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CQEI36IJ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8fcfa9b4c619741cb9cc1e16d777393b5181aeb120d9e29694f88fa1e16220c0","target":"graph","created_at":"2026-05-17T23:38:59Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The strongest baseline model (Gemini 3 Flash) only achieves an CAcc@75 of 15.20, an mIoU of 0.74, and a Dist of 28.65. These findings indicate that invisible-region reasoning remains an unstable capability in current VLMs."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The semi-automatic pipeline accurately creates 855 instances that genuinely require commonsense and spatial reasoning beyond superficial visual cues, rather than introducing artifacts that explain the low model performance."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SceneFunRI benchmark shows current VLMs struggle severely with inferring locations of invisible functional objects, with the strongest model (Gemini 3 Flash) reaching only 15.20 CAcc@75."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Vision-language models cannot reliably locate invisible functional objects from task instructions and commonsense."}],"snapshot_sha256":"350d4c16af96344b115a740becd405acb297eb7087801705eee37fe15c38c56e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In real-world scenes, target objects may reside in regions that are not visible. While humans can often infer the locations of occluded objects from context and commonsense knowledge, this capability remains a major challenge for vision-language models (VLMs). To address this gap, we introduce SceneFunRI, a benchmark for Reasoning the Invisible. Based on the SceneFun3D dataset, SceneFunRI formulates the task as a 2D spatial reasoning problem via a semi-automatic pipeline and comprises 855 instances. It requires models to infer the locations of invisible functional objects from task instruction","authors_text":"Gueter Josmy Faure, Hung-Ting Su, Posheng Chen, Powen Cheng, Winston H. Hsu","cross_cats":["cs.AI","cs.RO"],"headline":"Vision-language models cannot reliably locate invisible functional objects from task instructions and commonsense.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T11:21:41Z","title":"SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization"},"references":{"count":38,"internal_anchors":4,"resolved_work":38,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Image amodal completion: A survey.Computer Vision and Image Understanding, 229:103661, 2023","work_id":"5d8af2fe-47c5-4081-9bec-1f7dacd64cb0","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Open-world amodal appearance completion","work_id":"9543665c-f2f4-42eb-b51f-11d38d50848d","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"It’s not easy being wrong: Large language models struggle with process of elimination reasoning","work_id":"a031f5c6-c8f8-4b2a-b1dd-5578f2641958","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Scaling spatial intelligence with multimodal foundation models","work_id":"ceb84861-8bdb-4822-864c-8e2d0ae4d322","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes","work_id":"53329c45-0a4d-4522-8b6a-451a787fa9e7","year":2024}],"snapshot_sha256":"fa2f7fb6a2787cb6480867914701f164a310afa2322f804f54cb0933e767fcbc"},"source":{"id":"2605.14704","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:00:12.913741Z","id":"cc070207-2f90-435d-958a-98bbded92077","model_set":{"reader":"grok-4.3"},"one_line_summary":"SceneFunRI benchmark shows current VLMs struggle severely with inferring locations of invisible functional objects, with the strongest model (Gemini 3 Flash) reaching only 15.20 CAcc@75.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Vision-language models cannot reliably locate invisible functional objects from task instructions and commonsense.","strongest_claim":"The strongest baseline model (Gemini 3 Flash) only achieves an CAcc@75 of 15.20, an mIoU of 0.74, and a Dist of 28.65. These findings indicate that invisible-region reasoning remains an unstable capability in current VLMs.","weakest_assumption":"The semi-automatic pipeline accurately creates 855 instances that genuinely require commonsense and spatial reasoning beyond superficial visual cues, rather than introducing artifacts that explain the low model performance."}},"verdict_id":"cc070207-2f90-435d-958a-98bbded92077"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b5a9fe3553165e512134bba6162ddf88a7abd9918ccf039be4f5b4e09ab0ab75","target":"record","created_at":"2026-05-17T23:38:59Z","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":"54637346a93f1dc6c32674dbf6a01de1093a6119253cb8b203a427902373360a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T11:21:41Z","title_canon_sha256":"fb13c269bda0be01455a9e6ad02abdb673621e71c92e40ae576b22d11b96e459"},"schema_version":"1.0","source":{"id":"2605.14704","kind":"arxiv","version":1}},"canonical_sha256":"14088df909684e7c8b4238693327506666bc4de6bf1c46cbd714cf846ebb3700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14088df909684e7c8b4238693327506666bc4de6bf1c46cbd714cf846ebb3700","first_computed_at":"2026-05-17T23:38:59.290291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:59.290291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gUM/+qaJRu9pWmN7gICd4x8zJ5PjCXrRoOyda3IksvK03ZMMywKg9cahFhEDjprGKtU3lD7f0VvouZ7qgWFGCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:59.291047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14704","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5a9fe3553165e512134bba6162ddf88a7abd9918ccf039be4f5b4e09ab0ab75","sha256:8fcfa9b4c619741cb9cc1e16d777393b5181aeb120d9e29694f88fa1e16220c0"],"state_sha256":"3c1a6f15544bc86fe1b56f4bfc39624b04696dd9962104f0e6d370127c0206ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTpsxt6Y3rxsU6fXBulTB3QxYUUBGGqdj2LlvGqxkgF8+hO6UDCS36ZYYkM1z50XW8eqPI4BQFXckZcdSNJBDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T14:28:48.423118Z","bundle_sha256":"5ed0704d9d27050319777a537cbae0d0143e45ffb0b671cbb52ccdec94eaaf86"}}