{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YLPFQLVLHIADCUI2BDIXPMA2W7","short_pith_number":"pith:YLPFQLVL","schema_version":"1.0","canonical_sha256":"c2de582eab3a0031511a08d177b01ab7cfa5e9b1dbf0f76f7504183cfe9171c9","source":{"kind":"arxiv","id":"2605.30900","version":1},"attestation_state":"computed","paper":{"title":"BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.app-ph"],"primary_cat":"cs.AI","authors_text":"Ben Wang, Bing Zhao, Chengliang Xu, Hu Wei, Peiyao Xiao, Ruochen Gao, Xiaogang Li, Zeyu Wang, Zichao Chen","submitted_at":"2026-05-29T06:34:15Z","abstract_excerpt":"Current multimodal models handle static image recognition well, but intuitive physical reasoning remains a weakness. Predicting how objects will move and interact from a single image is still difficult for these systems. We present BilliardPhys-Bench, a benchmark for physical reasoning in synthetic billiards environments. Its procedural engine generates randomized scenarios with friction and elastic collisions. The benchmark tests three abilities: (1) predicting ball-to-ball collisions, (2) reasoning about wall bounces, and (3) estimating final ball positions after motion stops. We evaluate re"},"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":"2605.30900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T06:34:15Z","cross_cats_sorted":["physics.app-ph"],"title_canon_sha256":"a29f5c9df15e7fd5a946ac175f264046d4727dabcb71b66aff34adf9f04a413e","abstract_canon_sha256":"8cc6278e0450c8b79cbb2755ba964b109798ec1cbedf3883296d67c06124434d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:24.569938Z","signature_b64":"A8VqLPU2XWQRqyohaDgoPaBzjviGxAb7Gt5C6ylsqFraeF8UwUmTqKAho1oCL6Gqk6+mZWNbgCeer4D8iIUCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2de582eab3a0031511a08d177b01ab7cfa5e9b1dbf0f76f7504183cfe9171c9","last_reissued_at":"2026-06-01T01:03:24.569273Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:24.569273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.app-ph"],"primary_cat":"cs.AI","authors_text":"Ben Wang, Bing Zhao, Chengliang Xu, Hu Wei, Peiyao Xiao, Ruochen Gao, Xiaogang Li, Zeyu Wang, Zichao Chen","submitted_at":"2026-05-29T06:34:15Z","abstract_excerpt":"Current multimodal models handle static image recognition well, but intuitive physical reasoning remains a weakness. Predicting how objects will move and interact from a single image is still difficult for these systems. We present BilliardPhys-Bench, a benchmark for physical reasoning in synthetic billiards environments. Its procedural engine generates randomized scenarios with friction and elastic collisions. The benchmark tests three abilities: (1) predicting ball-to-ball collisions, (2) reasoning about wall bounces, and (3) estimating final ball positions after motion stops. We evaluate re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30900","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/2605.30900/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":"2605.30900","created_at":"2026-06-01T01:03:24.569400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30900v1","created_at":"2026-06-01T01:03:24.569400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30900","created_at":"2026-06-01T01:03:24.569400+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLPFQLVLHIAD","created_at":"2026-06-01T01:03:24.569400+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLPFQLVLHIADCUI2","created_at":"2026-06-01T01:03:24.569400+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLPFQLVL","created_at":"2026-06-01T01:03:24.569400+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/YLPFQLVLHIADCUI2BDIXPMA2W7","json":"https://pith.science/pith/YLPFQLVLHIADCUI2BDIXPMA2W7.json","graph_json":"https://pith.science/api/pith-number/YLPFQLVLHIADCUI2BDIXPMA2W7/graph.json","events_json":"https://pith.science/api/pith-number/YLPFQLVLHIADCUI2BDIXPMA2W7/events.json","paper":"https://pith.science/paper/YLPFQLVL"},"agent_actions":{"view_html":"https://pith.science/pith/YLPFQLVLHIADCUI2BDIXPMA2W7","download_json":"https://pith.science/pith/YLPFQLVLHIADCUI2BDIXPMA2W7.json","view_paper":"https://pith.science/paper/YLPFQLVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30900&json=true","fetch_graph":"https://pith.science/api/pith-number/YLPFQLVLHIADCUI2BDIXPMA2W7/graph.json","fetch_events":"https://pith.science/api/pith-number/YLPFQLVLHIADCUI2BDIXPMA2W7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLPFQLVLHIADCUI2BDIXPMA2W7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLPFQLVLHIADCUI2BDIXPMA2W7/action/storage_attestation","attest_author":"https://pith.science/pith/YLPFQLVLHIADCUI2BDIXPMA2W7/action/author_attestation","sign_citation":"https://pith.science/pith/YLPFQLVLHIADCUI2BDIXPMA2W7/action/citation_signature","submit_replication":"https://pith.science/pith/YLPFQLVLHIADCUI2BDIXPMA2W7/action/replication_record"}},"created_at":"2026-06-01T01:03:24.569400+00:00","updated_at":"2026-06-01T01:03:24.569400+00:00"}