{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JMXLQNZJPXWU2R4T4XRTHU5KUW","short_pith_number":"pith:JMXLQNZJ","schema_version":"1.0","canonical_sha256":"4b2eb837297ded4d4793e5e333d3aaa59609829f3b8213c7c0d5992b91f23dfe","source":{"kind":"arxiv","id":"2412.01800","version":1},"attestation_state":"computed","paper":{"title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ge Zhang, Hangyu Guo, Haoran Tang, Haoze Zhao, Ian Reid, Jiaheng Liu, Meng Cao, Qiang Sun, Ruyang Liu, Xiaodan Liang","submitted_at":"2024-12-02T18:47:25Z","abstract_excerpt":"Recent advancements in video-based large language models (Video LLMs) have witnessed the emergence of diverse capabilities to reason and interpret dynamic visual content. Among them, gameplay videos stand out as a distinctive data source, often containing glitches that defy physics commonsense. This characteristic renders them an effective benchmark for assessing the under-explored capability of physical commonsense understanding in video LLMs. In this paper, we propose PhysGame as a pioneering benchmark to evaluate physical commonsense violations in gameplay videos. PhysGame comprises 880 vid"},"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":"2412.01800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:47:25Z","cross_cats_sorted":[],"title_canon_sha256":"9390c0c8ce939279a712755c4a30f41eea207817e746406370f92c00bb4e9621","abstract_canon_sha256":"a550083a38a6c1d8e7fd8262215a05b22cdedf056158030e6666a90bd17e654d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:19.878137Z","signature_b64":"tRTawJP0Q3rh+/L+xHal52W0nKr+OFG2nArJVOSYT8ksyrbQCCBLV02dOpFiN/YPYP19HXHp8FbedJcnnmYPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b2eb837297ded4d4793e5e333d3aaa59609829f3b8213c7c0d5992b91f23dfe","last_reissued_at":"2026-07-05T09:43:19.877580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:19.877580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ge Zhang, Hangyu Guo, Haoran Tang, Haoze Zhao, Ian Reid, Jiaheng Liu, Meng Cao, Qiang Sun, Ruyang Liu, Xiaodan Liang","submitted_at":"2024-12-02T18:47:25Z","abstract_excerpt":"Recent advancements in video-based large language models (Video LLMs) have witnessed the emergence of diverse capabilities to reason and interpret dynamic visual content. Among them, gameplay videos stand out as a distinctive data source, often containing glitches that defy physics commonsense. This characteristic renders them an effective benchmark for assessing the under-explored capability of physical commonsense understanding in video LLMs. In this paper, we propose PhysGame as a pioneering benchmark to evaluate physical commonsense violations in gameplay videos. PhysGame comprises 880 vid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01800","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/2412.01800/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":"2412.01800","created_at":"2026-07-05T09:43:19.877644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01800v1","created_at":"2026-07-05T09:43:19.877644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01800","created_at":"2026-07-05T09:43:19.877644+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMXLQNZJPXWU","created_at":"2026-07-05T09:43:19.877644+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMXLQNZJPXWU2R4T","created_at":"2026-07-05T09:43:19.877644+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMXLQNZJ","created_at":"2026-07-05T09:43:19.877644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21443","citing_title":"TempGlitch: Evaluating Vision-Language Models for Temporal Glitch Detection in Gameplay Videos","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09038","citing_title":"Do generative video models understand physical principles?","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10806","citing_title":"PhyGround: Benchmarking Physical Reasoning in Generative World Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11082","citing_title":"RESP: Reference-guided Sequential Prompting for Visual Glitch Detection in Video Games","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07818","citing_title":"Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMXLQNZJPXWU2R4T4XRTHU5KUW","json":"https://pith.science/pith/JMXLQNZJPXWU2R4T4XRTHU5KUW.json","graph_json":"https://pith.science/api/pith-number/JMXLQNZJPXWU2R4T4XRTHU5KUW/graph.json","events_json":"https://pith.science/api/pith-number/JMXLQNZJPXWU2R4T4XRTHU5KUW/events.json","paper":"https://pith.science/paper/JMXLQNZJ"},"agent_actions":{"view_html":"https://pith.science/pith/JMXLQNZJPXWU2R4T4XRTHU5KUW","download_json":"https://pith.science/pith/JMXLQNZJPXWU2R4T4XRTHU5KUW.json","view_paper":"https://pith.science/paper/JMXLQNZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01800&json=true","fetch_graph":"https://pith.science/api/pith-number/JMXLQNZJPXWU2R4T4XRTHU5KUW/graph.json","fetch_events":"https://pith.science/api/pith-number/JMXLQNZJPXWU2R4T4XRTHU5KUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMXLQNZJPXWU2R4T4XRTHU5KUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMXLQNZJPXWU2R4T4XRTHU5KUW/action/storage_attestation","attest_author":"https://pith.science/pith/JMXLQNZJPXWU2R4T4XRTHU5KUW/action/author_attestation","sign_citation":"https://pith.science/pith/JMXLQNZJPXWU2R4T4XRTHU5KUW/action/citation_signature","submit_replication":"https://pith.science/pith/JMXLQNZJPXWU2R4T4XRTHU5KUW/action/replication_record"}},"created_at":"2026-07-05T09:43:19.877644+00:00","updated_at":"2026-07-05T09:43:19.877644+00:00"}