{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D5G4CPAYPSH3D3LIDVP432VLJI","short_pith_number":"pith:D5G4CPAY","canonical_record":{"source":{"id":"2506.21876","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T03:24:29Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0152f35933fdc8ffe165660684ba89a250f9f07b8387c7bd4052c3e7d4cdeab5","abstract_canon_sha256":"8ff8680d8d6a8ea7dc1291d72853473fdc34538392a1f945bd3ef46c2980aecb"},"schema_version":"1.0"},"canonical_sha256":"1f4dc13c187c8fb1ed681d5fcdeaab4a24fffe7df0bb47d7d206c222bb2bf984","source":{"kind":"arxiv","id":"2506.21876","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21876","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21876v1","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21876","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"D5G4CPAYPSH3","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"D5G4CPAYPSH3D3LI","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"D5G4CPAY","created_at":"2026-07-05T11:28:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D5G4CPAYPSH3D3LIDVP432VLJI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21876","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T03:24:29Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0152f35933fdc8ffe165660684ba89a250f9f07b8387c7bd4052c3e7d4cdeab5","abstract_canon_sha256":"8ff8680d8d6a8ea7dc1291d72853473fdc34538392a1f945bd3ef46c2980aecb"},"schema_version":"1.0"},"canonical_sha256":"1f4dc13c187c8fb1ed681d5fcdeaab4a24fffe7df0bb47d7d206c222bb2bf984","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:03.277754Z","signature_b64":"eimHPj9oaigkv/SvkJBzXXMvRcjIXX2PSLWY/IVccFiIFGREnMz6tqAhq8ZJKBVdTnCi2YRtESASyXOioT66DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f4dc13c187c8fb1ed681d5fcdeaab4a24fffe7df0bb47d7d206c222bb2bf984","last_reissued_at":"2026-07-05T11:28:03.277222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:03.277222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21876","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":"2026-07-05T11:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8n3Ev77fgwmQ6VRcNp+wFDxU/PKZor9CqsTSEHTQeAN9fEFYLZ6duQ7yAaTxEoHrX8kb2+FqrCtFg7pex46DAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:08:42.405994Z"},"content_sha256":"50324a7a6b3e53d2887e52817013da6825b45075e6e3bb296a40f5956dd28f06","schema_version":"1.0","event_id":"sha256:50324a7a6b3e53d2887e52817013da6825b45075e6e3bb296a40f5956dd28f06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D5G4CPAYPSH3D3LIDVP432VLJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Benhao Huang, Bo Ai, Chao-Jung Lai, Chuanyang Jin, David Danks, Gautham Kishore, Hao Su, Jiannan Xiang, Jiaxi Yang, Junrong Chen, Kevin Liu, Lianhui Qin, Lu Sun, Mengyang Liu, Qiyue Gao, Ruolan Yang, Stone Tao, Tianmin Shu, Xinqi Huang, Xinyu Fang, Xinyu Pi, Zeming Chen, Zhiting Hu, Ziqiao Ma","submitted_at":"2025-06-27T03:24:29Z","abstract_excerpt":"Internal world models (WMs) enable agents to understand the world's state and predict transitions, serving as the basis for advanced deliberative reasoning. Recent large Vision-Language Models (VLMs), such as OpenAI o3, GPT-4o and Gemini, exhibit potential as general-purpose WMs. While the latest studies have evaluated and shown limitations in specific capabilities such as visual understanding, a systematic evaluation of VLMs' fundamental WM abilities remains absent. Drawing on comparative psychology and cognitive science, we propose a two-stage framework that assesses Perception (visual, spat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21876","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/2506.21876/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZL2TTl22WF0+yLqRkvfpioIYDxvXl3v2WgqbjdQIziP7YRatxN3bNT31qvNE7ARFMD0BU67iX10gSOeybewDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:08:42.406575Z"},"content_sha256":"5a28f1eb5472b4f53f56d0dc9b6843b8a23103cc42d7e754850a62fa1456272c","schema_version":"1.0","event_id":"sha256:5a28f1eb5472b4f53f56d0dc9b6843b8a23103cc42d7e754850a62fa1456272c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D5G4CPAYPSH3D3LIDVP432VLJI/bundle.json","state_url":"https://pith.science/pith/D5G4CPAYPSH3D3LIDVP432VLJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D5G4CPAYPSH3D3LIDVP432VLJI/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":"2026-08-04T03:08:42Z","links":{"resolver":"https://pith.science/pith/D5G4CPAYPSH3D3LIDVP432VLJI","bundle":"https://pith.science/pith/D5G4CPAYPSH3D3LIDVP432VLJI/bundle.json","state":"https://pith.science/pith/D5G4CPAYPSH3D3LIDVP432VLJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D5G4CPAYPSH3D3LIDVP432VLJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D5G4CPAYPSH3D3LIDVP432VLJI","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":"8ff8680d8d6a8ea7dc1291d72853473fdc34538392a1f945bd3ef46c2980aecb","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T03:24:29Z","title_canon_sha256":"0152f35933fdc8ffe165660684ba89a250f9f07b8387c7bd4052c3e7d4cdeab5"},"schema_version":"1.0","source":{"id":"2506.21876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21876","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21876v1","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21876","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"D5G4CPAYPSH3","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"D5G4CPAYPSH3D3LI","created_at":"2026-07-05T11:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"D5G4CPAY","created_at":"2026-07-05T11:28:03Z"}],"graph_snapshots":[{"event_id":"sha256:5a28f1eb5472b4f53f56d0dc9b6843b8a23103cc42d7e754850a62fa1456272c","target":"graph","created_at":"2026-07-05T11:28:03Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.21876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Internal world models (WMs) enable agents to understand the world's state and predict transitions, serving as the basis for advanced deliberative reasoning. Recent large Vision-Language Models (VLMs), such as OpenAI o3, GPT-4o and Gemini, exhibit potential as general-purpose WMs. While the latest studies have evaluated and shown limitations in specific capabilities such as visual understanding, a systematic evaluation of VLMs' fundamental WM abilities remains absent. Drawing on comparative psychology and cognitive science, we propose a two-stage framework that assesses Perception (visual, spat","authors_text":"Benhao Huang, Bo Ai, Chao-Jung Lai, Chuanyang Jin, David Danks, Gautham Kishore, Hao Su, Jiannan Xiang, Jiaxi Yang, Junrong Chen, Kevin Liu, Lianhui Qin, Lu Sun, Mengyang Liu, Qiyue Gao, Ruolan Yang, Stone Tao, Tianmin Shu, Xinqi Huang, Xinyu Fang, Xinyu Pi, Zeming Chen, Zhiting Hu, Ziqiao Ma","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T03:24:29Z","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21876","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:50324a7a6b3e53d2887e52817013da6825b45075e6e3bb296a40f5956dd28f06","target":"record","created_at":"2026-07-05T11:28:03Z","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":"8ff8680d8d6a8ea7dc1291d72853473fdc34538392a1f945bd3ef46c2980aecb","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T03:24:29Z","title_canon_sha256":"0152f35933fdc8ffe165660684ba89a250f9f07b8387c7bd4052c3e7d4cdeab5"},"schema_version":"1.0","source":{"id":"2506.21876","kind":"arxiv","version":1}},"canonical_sha256":"1f4dc13c187c8fb1ed681d5fcdeaab4a24fffe7df0bb47d7d206c222bb2bf984","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f4dc13c187c8fb1ed681d5fcdeaab4a24fffe7df0bb47d7d206c222bb2bf984","first_computed_at":"2026-07-05T11:28:03.277222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:03.277222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eimHPj9oaigkv/SvkJBzXXMvRcjIXX2PSLWY/IVccFiIFGREnMz6tqAhq8ZJKBVdTnCi2YRtESASyXOioT66DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:03.277754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50324a7a6b3e53d2887e52817013da6825b45075e6e3bb296a40f5956dd28f06","sha256:5a28f1eb5472b4f53f56d0dc9b6843b8a23103cc42d7e754850a62fa1456272c"],"state_sha256":"1fbfbbfc7a536a876860416b3f7fe7e09ad917da6e57f66dbc59f9828764573e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hx3vajgH3RIjvYWl0kiw9GTcJjr77rqcSrb8UgsjUNcnYOVRENvAov/soT2XyP14Tifap2JGSrXUetMsJSOLAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:08:42.410612Z","bundle_sha256":"61dc453c7e7bbec02d754dfade66c91e3c6ac4e4646db8912ba0814d91b9e75f"}}