{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L5JB2337VTSDJRXCAHRFKXFDFH","short_pith_number":"pith:L5JB2337","canonical_record":{"source":{"id":"2501.16411","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:59:58Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"84bee8c6391382b0578069050500cc4db7b1784705f6aa47aaf43166c88f1039","abstract_canon_sha256":"f939fbeb41379bbcb261c1688c72fd36c80537890cd24b8510a123505f176e5a"},"schema_version":"1.0"},"canonical_sha256":"5f521d6f7face434c6e201e2555ca329e50ee5decdae2d1b216c9c6eaabb8bd1","source":{"kind":"arxiv","id":"2501.16411","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16411","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16411v2","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16411","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"pith_short_12","alias_value":"L5JB2337VTSD","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"pith_short_16","alias_value":"L5JB2337VTSDJRXC","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"pith_short_8","alias_value":"L5JB2337","created_at":"2026-07-05T10:06:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L5JB2337VTSDJRXCAHRFKXFDFH","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16411","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:59:58Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"84bee8c6391382b0578069050500cc4db7b1784705f6aa47aaf43166c88f1039","abstract_canon_sha256":"f939fbeb41379bbcb261c1688c72fd36c80537890cd24b8510a123505f176e5a"},"schema_version":"1.0"},"canonical_sha256":"5f521d6f7face434c6e201e2555ca329e50ee5decdae2d1b216c9c6eaabb8bd1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:47.959846Z","signature_b64":"aZ+woXldk/Bjnzvb13nBBJmeaHoJeePDPltk+CxKzXs8Etx+E/h4JeKmZqLNAYwmy4RWiWd/J2LZzyAVEVwNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f521d6f7face434c6e201e2555ca329e50ee5decdae2d1b216c9c6eaabb8bd1","last_reissued_at":"2026-07-05T10:06:47.959353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:47.959353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16411","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:06:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TSfEDm6sDu7affOXjtxpHIKCHj+LqPPyv0kXa5J3SSt8u3UDDuohv9S1X+OjkroDql/yX3HEXm7CqJommMzSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:24:20.387914Z"},"content_sha256":"7b2cb74aafdd8fb0a172d85204af290079ab1930803feeda0f5f2f8b8b24685e","schema_version":"1.0","event_id":"sha256:7b2cb74aafdd8fb0a172d85204af290079ab1930803feeda0f5f2f8b8b24685e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L5JB2337VTSDJRXCAHRFKXFDFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Boyi Li, Daniel Seita, Jiageng Mao, Vitor Guizilini, Wei Chow, Yue Wang","submitted_at":"2025-01-27T18:59:58Z","abstract_excerpt":"Understanding the physical world is a fundamental challenge in embodied AI, critical for enabling agents to perform complex tasks and operate safely in real-world environments. While Vision-Language Models (VLMs) have shown great promise in reasoning and task planning for embodied agents, their ability to comprehend physical phenomena remains extremely limited. To close this gap, we introduce PhysBench, a comprehensive benchmark designed to evaluate VLMs' physical world understanding capability across a diverse set of tasks. PhysBench contains 10,002 entries of interleaved video-image-text dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16411","kind":"arxiv","version":2},"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/2501.16411/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":"2026-07-05T10:06:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o7zre9r4IgOmQh67kOMKc5eqgGpAYPTVabo589HZ/24OHfx95TmunDGHAlEy41gi7lp96/zTh9wyv1WgluCHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:24:20.388854Z"},"content_sha256":"52f7287aa66cf295334a461e06c8aaca39f71ef9adfbf8c6e35f562f4068a407","schema_version":"1.0","event_id":"sha256:52f7287aa66cf295334a461e06c8aaca39f71ef9adfbf8c6e35f562f4068a407"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L5JB2337VTSDJRXCAHRFKXFDFH/bundle.json","state_url":"https://pith.science/pith/L5JB2337VTSDJRXCAHRFKXFDFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L5JB2337VTSDJRXCAHRFKXFDFH/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":"2026-08-04T19:24:20Z","links":{"resolver":"https://pith.science/pith/L5JB2337VTSDJRXCAHRFKXFDFH","bundle":"https://pith.science/pith/L5JB2337VTSDJRXCAHRFKXFDFH/bundle.json","state":"https://pith.science/pith/L5JB2337VTSDJRXCAHRFKXFDFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L5JB2337VTSDJRXCAHRFKXFDFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L5JB2337VTSDJRXCAHRFKXFDFH","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":"f939fbeb41379bbcb261c1688c72fd36c80537890cd24b8510a123505f176e5a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:59:58Z","title_canon_sha256":"84bee8c6391382b0578069050500cc4db7b1784705f6aa47aaf43166c88f1039"},"schema_version":"1.0","source":{"id":"2501.16411","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16411","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16411v2","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16411","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"pith_short_12","alias_value":"L5JB2337VTSD","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"pith_short_16","alias_value":"L5JB2337VTSDJRXC","created_at":"2026-07-05T10:06:47Z"},{"alias_kind":"pith_short_8","alias_value":"L5JB2337","created_at":"2026-07-05T10:06:47Z"}],"graph_snapshots":[{"event_id":"sha256:52f7287aa66cf295334a461e06c8aaca39f71ef9adfbf8c6e35f562f4068a407","target":"graph","created_at":"2026-07-05T10:06:47Z","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/2501.16411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the physical world is a fundamental challenge in embodied AI, critical for enabling agents to perform complex tasks and operate safely in real-world environments. While Vision-Language Models (VLMs) have shown great promise in reasoning and task planning for embodied agents, their ability to comprehend physical phenomena remains extremely limited. To close this gap, we introduce PhysBench, a comprehensive benchmark designed to evaluate VLMs' physical world understanding capability across a diverse set of tasks. PhysBench contains 10,002 entries of interleaved video-image-text dat","authors_text":"Boyi Li, Daniel Seita, Jiageng Mao, Vitor Guizilini, Wei Chow, Yue Wang","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:59:58Z","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16411","kind":"arxiv","version":2},"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":"sha256:7b2cb74aafdd8fb0a172d85204af290079ab1930803feeda0f5f2f8b8b24685e","target":"record","created_at":"2026-07-05T10:06:47Z","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":"f939fbeb41379bbcb261c1688c72fd36c80537890cd24b8510a123505f176e5a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T18:59:58Z","title_canon_sha256":"84bee8c6391382b0578069050500cc4db7b1784705f6aa47aaf43166c88f1039"},"schema_version":"1.0","source":{"id":"2501.16411","kind":"arxiv","version":2}},"canonical_sha256":"5f521d6f7face434c6e201e2555ca329e50ee5decdae2d1b216c9c6eaabb8bd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f521d6f7face434c6e201e2555ca329e50ee5decdae2d1b216c9c6eaabb8bd1","first_computed_at":"2026-07-05T10:06:47.959353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:47.959353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aZ+woXldk/Bjnzvb13nBBJmeaHoJeePDPltk+CxKzXs8Etx+E/h4JeKmZqLNAYwmy4RWiWd/J2LZzyAVEVwNBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:47.959846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16411","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b2cb74aafdd8fb0a172d85204af290079ab1930803feeda0f5f2f8b8b24685e","sha256:52f7287aa66cf295334a461e06c8aaca39f71ef9adfbf8c6e35f562f4068a407"],"state_sha256":"0eb80a02b9c091d1e6a6d746d32f7e3b6c48bf5380be13c20369a8cbee53a329"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EZGAHQxP/0vMsNMe/R1UTRlTKWIvqE/t9Qg+o4XSN7p4Y3gJkU6izLCUe1P9vQLYCVRcQnqYBlpllPxazosZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:24:20.397947Z","bundle_sha256":"55cacda20e53e2aa92594c20619ad47616b8a2417d1187ae92fb30d7eab6fb2d"}}