{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YW4VTQRLRG2EE5K76VRM5WKWW4","short_pith_number":"pith:YW4VTQRL","canonical_record":{"source":{"id":"2508.05405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-07T13:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"3914e5881a158780ab33129bd397954b4095061ddf315d5c2527a669c7810da6","abstract_canon_sha256":"73d8b3b7f17f439c235dcef853d73f376424e3d0cf0a939adabf40dd21465fba"},"schema_version":"1.0"},"canonical_sha256":"c5b959c22b89b442755ff562ced956b71734660b880d2e35125ec83f6edd532d","source":{"kind":"arxiv","id":"2508.05405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05405","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05405v1","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05405","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"YW4VTQRLRG2E","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"pith_short_16","alias_value":"YW4VTQRLRG2EE5K7","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"pith_short_8","alias_value":"YW4VTQRL","created_at":"2026-07-05T11:50:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YW4VTQRLRG2EE5K76VRM5WKWW4","target":"record","payload":{"canonical_record":{"source":{"id":"2508.05405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-07T13:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"3914e5881a158780ab33129bd397954b4095061ddf315d5c2527a669c7810da6","abstract_canon_sha256":"73d8b3b7f17f439c235dcef853d73f376424e3d0cf0a939adabf40dd21465fba"},"schema_version":"1.0"},"canonical_sha256":"c5b959c22b89b442755ff562ced956b71734660b880d2e35125ec83f6edd532d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:12.575911Z","signature_b64":"2/BcVQGQaVHclvpzaPMi3/xL/Ga8gppDs5jPqKTIF9vrVOMQ3njcEhFgnNarbjLrvOU8HhbxiJ02/qlgS5QXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5b959c22b89b442755ff562ced956b71734660b880d2e35125ec83f6edd532d","last_reissued_at":"2026-07-05T11:50:12.575426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:12.575426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.05405","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":"2026-07-05T11:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DmcsyfYnxmbk3MVWSmAziCCnYHdavVYiyYKv2VV+4ENUupSo8kBIwIQNdCW3pyrPl3qtdOgugiuZ2BmRgeirCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:56:53.650809Z"},"content_sha256":"b22ef77a81a09233563eb3a00fdd866721a723940a82b491f6d14da0b1a53a5d","schema_version":"1.0","event_id":"sha256:b22ef77a81a09233563eb3a00fdd866721a723940a82b491f6d14da0b1a53a5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YW4VTQRLRG2EE5K76VRM5WKWW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"B\\\"orje F. Karlsson, Bo Zheng, Jun Song, Pi Bu, Qi Zhu, Tengtao Song, Xinrun Xu, Ye Wang, Zhiming Ding, Ziming Wang","submitted_at":"2025-08-07T13:58:19Z","abstract_excerpt":"Although Vision Language Models (VLMs) exhibit strong perceptual abilities and impressive visual reasoning, they struggle with attention to detail and precise action planning in complex, dynamic environments, leading to subpar performance. Real-world tasks typically require complex interactions, advanced spatial reasoning, long-term planning, and continuous strategy refinement, usually necessitating understanding the physics rules of the target scenario. However, evaluating these capabilities in real-world scenarios is often prohibitively expensive. To bridge this gap, we introduce DeepPHY, a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05405","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/2508.05405/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":"2026-07-05T11:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vECwbfbkEl5V4w73qJVazpwk5N/LQklKgoacBAD9GgGCuOXF5xUN2/HjRR7NTwWoGNWiw8PdHNyKBDuCqxyPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:56:53.651169Z"},"content_sha256":"b6dba7ab4e23fd0482bc86f4259d7186a5e4fe391eb101b60520552e0315ae9c","schema_version":"1.0","event_id":"sha256:b6dba7ab4e23fd0482bc86f4259d7186a5e4fe391eb101b60520552e0315ae9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YW4VTQRLRG2EE5K76VRM5WKWW4/bundle.json","state_url":"https://pith.science/pith/YW4VTQRLRG2EE5K76VRM5WKWW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YW4VTQRLRG2EE5K76VRM5WKWW4/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":"2026-07-09T03:56:53Z","links":{"resolver":"https://pith.science/pith/YW4VTQRLRG2EE5K76VRM5WKWW4","bundle":"https://pith.science/pith/YW4VTQRLRG2EE5K76VRM5WKWW4/bundle.json","state":"https://pith.science/pith/YW4VTQRLRG2EE5K76VRM5WKWW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YW4VTQRLRG2EE5K76VRM5WKWW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YW4VTQRLRG2EE5K76VRM5WKWW4","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":"73d8b3b7f17f439c235dcef853d73f376424e3d0cf0a939adabf40dd21465fba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-07T13:58:19Z","title_canon_sha256":"3914e5881a158780ab33129bd397954b4095061ddf315d5c2527a669c7810da6"},"schema_version":"1.0","source":{"id":"2508.05405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05405","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05405v1","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05405","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"YW4VTQRLRG2E","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"pith_short_16","alias_value":"YW4VTQRLRG2EE5K7","created_at":"2026-07-05T11:50:12Z"},{"alias_kind":"pith_short_8","alias_value":"YW4VTQRL","created_at":"2026-07-05T11:50:12Z"}],"graph_snapshots":[{"event_id":"sha256:b6dba7ab4e23fd0482bc86f4259d7186a5e4fe391eb101b60520552e0315ae9c","target":"graph","created_at":"2026-07-05T11:50:12Z","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/2508.05405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Vision Language Models (VLMs) exhibit strong perceptual abilities and impressive visual reasoning, they struggle with attention to detail and precise action planning in complex, dynamic environments, leading to subpar performance. Real-world tasks typically require complex interactions, advanced spatial reasoning, long-term planning, and continuous strategy refinement, usually necessitating understanding the physics rules of the target scenario. However, evaluating these capabilities in real-world scenarios is often prohibitively expensive. To bridge this gap, we introduce DeepPHY, a ","authors_text":"B\\\"orje F. Karlsson, Bo Zheng, Jun Song, Pi Bu, Qi Zhu, Tengtao Song, Xinrun Xu, Ye Wang, Zhiming Ding, Ziming Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-07T13:58:19Z","title":"DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05405","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:b22ef77a81a09233563eb3a00fdd866721a723940a82b491f6d14da0b1a53a5d","target":"record","created_at":"2026-07-05T11:50:12Z","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":"73d8b3b7f17f439c235dcef853d73f376424e3d0cf0a939adabf40dd21465fba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-07T13:58:19Z","title_canon_sha256":"3914e5881a158780ab33129bd397954b4095061ddf315d5c2527a669c7810da6"},"schema_version":"1.0","source":{"id":"2508.05405","kind":"arxiv","version":1}},"canonical_sha256":"c5b959c22b89b442755ff562ced956b71734660b880d2e35125ec83f6edd532d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5b959c22b89b442755ff562ced956b71734660b880d2e35125ec83f6edd532d","first_computed_at":"2026-07-05T11:50:12.575426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:12.575426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2/BcVQGQaVHclvpzaPMi3/xL/Ga8gppDs5jPqKTIF9vrVOMQ3njcEhFgnNarbjLrvOU8HhbxiJ02/qlgS5QXAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:12.575911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b22ef77a81a09233563eb3a00fdd866721a723940a82b491f6d14da0b1a53a5d","sha256:b6dba7ab4e23fd0482bc86f4259d7186a5e4fe391eb101b60520552e0315ae9c"],"state_sha256":"20785cf8750ce2661feb360eb0170e4ba2bb87aad2dd52794e8872ef1ded023b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N0RrIb2BHvBgXa5RGzw+BQ+4hKn2sXKwNe3r/vcBlwV6xNboqoanZdcnZ9P3vZHjDEFpzicVIQpOE20n+xHXAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:56:53.653119Z","bundle_sha256":"598d99f5b07ece98f3d205a4d018bdb5fbaa33cd49d2f3dcd05644ec07d66b70"}}