{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MKDQXZXYQM65FXBX2JOLHBVWWG","short_pith_number":"pith:MKDQXZXY","canonical_record":{"source":{"id":"2504.16074","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:53:29Z","cross_cats_sorted":[],"title_canon_sha256":"5699bcf5d7ec6de15994fd88eadec401032a96810532f6674fb3eca61ef08cbf","abstract_canon_sha256":"15cf134a205150d81bb2922e38f2273a0d66f6a1e7984eb5cb2959398716fa17"},"schema_version":"1.0"},"canonical_sha256":"62870be6f8833dd2dc37d25cb386b6b195b386371bf4c3cf92c620d55f638080","source":{"kind":"arxiv","id":"2504.16074","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16074","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16074v2","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16074","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"MKDQXZXYQM65","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"MKDQXZXYQM65FXBX","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"MKDQXZXY","created_at":"2026-07-05T11:04:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MKDQXZXYQM65FXBX2JOLHBVWWG","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16074","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:53:29Z","cross_cats_sorted":[],"title_canon_sha256":"5699bcf5d7ec6de15994fd88eadec401032a96810532f6674fb3eca61ef08cbf","abstract_canon_sha256":"15cf134a205150d81bb2922e38f2273a0d66f6a1e7984eb5cb2959398716fa17"},"schema_version":"1.0"},"canonical_sha256":"62870be6f8833dd2dc37d25cb386b6b195b386371bf4c3cf92c620d55f638080","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:49.693612Z","signature_b64":"2h+XFO/zCBcNy3/q0+2YNLeBcH2+X6Fj8mc1IUDn+Pr+GfELBcKmCLiH1ezAOvasEswLCAE9235RG3OUhncICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62870be6f8833dd2dc37d25cb386b6b195b386371bf4c3cf92c620d55f638080","last_reissued_at":"2026-07-05T11:04:49.693081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:49.693081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16074","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":"2026-07-05T11:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nahwBwyQe4gEjWCHX25Osn6ReC2eKfbH3gaKTOQv/dc10k91LXMNqswQw62bFJN9jyxeZcE4pr4F8ytsgebaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T05:28:12.175132Z"},"content_sha256":"8777b947607683c8f6dae0b2f0434b82155c5f9735f85446b6bef3a6c48b486e","schema_version":"1.0","event_id":"sha256:8777b947607683c8f6dae0b2f0434b82155c5f9735f85446b6bef3a6c48b486e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MKDQXZXYQM65FXBX2JOLHBVWWG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anqi Lv, Binran Wang, Bohan Zhang, Boxuan Jing, Changkun Shao, Chencheng Tang, Chenyang Wang, Fan Cui, Feiyu Tao, Fengyuan Wang, Haoling Chang, Haoxu Zhang, Hua Xing Zhu, Jiahang Chen, Jiaming Ji, Jianxiang Li, Jiashen Wei, Jiawei Lin, Jing-Jun Zhang, Jingtian Zhang, Laifu Man, Minghao Li, Ming-Xing Luo, Muhan Zhang, Qihua Sun, Qi Liu, Qing-Hong Cao, Qiuhao Xiong, Shaoyang Guo, Shi Qiu, Shutao Zhang, Tianyu Luo, Tianyu Zhang, Weike Wang, Xianqi Yin, Xiaotian Li, Xingqi Xia, Xudong Tian, Yaodong Yang, Yi Hu, Yixuan Yin, Yuku Zhang, Yunbo Sun, Yushu Mu, Yutong Ren, Zeyu Cai, Zhangyi Liu, Zheyu Shen, Zhongxuan Li, Zhou Liang, Zhuo-Yang Song, Ziheng Zhou, Ziyang Ni, Zizhuo Fu","submitted_at":"2025-04-22T17:53:29Z","abstract_excerpt":"Current benchmarks for evaluating the reasoning capabilities of Large Language Models (LLMs) face significant limitations: task oversimplification, data contamination, and flawed evaluation items. These deficiencies necessitate more rigorous assessment methods. To address these limitations, we introduce PHYBench, a benchmark of 500 original physics problems ranging from high school to Physics Olympiad difficulty. PHYBench addresses data contamination through original content and employs a systematic curation pipeline to eliminate flawed items. Evaluations show that PHYBench activates more toke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16074","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/2504.16074/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":"2026-07-05T11:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YAjc7Ko/7Yd6SJuHYRxeSPRoo5HpT12sGel/F/4dmzvl4IGluTc3cqt7k8X70evudPtsCGWPDrCMk4rusGcZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T05:28:12.175553Z"},"content_sha256":"0177e19117568e0f27ae360a2e5a5bec23a95be7c2ca0ad3774de02de3b25c7b","schema_version":"1.0","event_id":"sha256:0177e19117568e0f27ae360a2e5a5bec23a95be7c2ca0ad3774de02de3b25c7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKDQXZXYQM65FXBX2JOLHBVWWG/bundle.json","state_url":"https://pith.science/pith/MKDQXZXYQM65FXBX2JOLHBVWWG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKDQXZXYQM65FXBX2JOLHBVWWG/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":"2026-07-24T05:28:12Z","links":{"resolver":"https://pith.science/pith/MKDQXZXYQM65FXBX2JOLHBVWWG","bundle":"https://pith.science/pith/MKDQXZXYQM65FXBX2JOLHBVWWG/bundle.json","state":"https://pith.science/pith/MKDQXZXYQM65FXBX2JOLHBVWWG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKDQXZXYQM65FXBX2JOLHBVWWG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MKDQXZXYQM65FXBX2JOLHBVWWG","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":"15cf134a205150d81bb2922e38f2273a0d66f6a1e7984eb5cb2959398716fa17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:53:29Z","title_canon_sha256":"5699bcf5d7ec6de15994fd88eadec401032a96810532f6674fb3eca61ef08cbf"},"schema_version":"1.0","source":{"id":"2504.16074","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16074","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16074v2","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16074","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"MKDQXZXYQM65","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"MKDQXZXYQM65FXBX","created_at":"2026-07-05T11:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"MKDQXZXY","created_at":"2026-07-05T11:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:0177e19117568e0f27ae360a2e5a5bec23a95be7c2ca0ad3774de02de3b25c7b","target":"graph","created_at":"2026-07-05T11:04:49Z","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/2504.16074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current benchmarks for evaluating the reasoning capabilities of Large Language Models (LLMs) face significant limitations: task oversimplification, data contamination, and flawed evaluation items. These deficiencies necessitate more rigorous assessment methods. To address these limitations, we introduce PHYBench, a benchmark of 500 original physics problems ranging from high school to Physics Olympiad difficulty. PHYBench addresses data contamination through original content and employs a systematic curation pipeline to eliminate flawed items. Evaluations show that PHYBench activates more toke","authors_text":"Anqi Lv, Binran Wang, Bohan Zhang, Boxuan Jing, Changkun Shao, Chencheng Tang, Chenyang Wang, Fan Cui, Feiyu Tao, Fengyuan Wang, Haoling Chang, Haoxu Zhang, Hua Xing Zhu, Jiahang Chen, Jiaming Ji, Jianxiang Li, Jiashen Wei, Jiawei Lin, Jing-Jun Zhang, Jingtian Zhang, Laifu Man, Minghao Li, Ming-Xing Luo, Muhan Zhang, Qihua Sun, Qi Liu, Qing-Hong Cao, Qiuhao Xiong, Shaoyang Guo, Shi Qiu, Shutao Zhang, Tianyu Luo, Tianyu Zhang, Weike Wang, Xianqi Yin, Xiaotian Li, Xingqi Xia, Xudong Tian, Yaodong Yang, Yi Hu, Yixuan Yin, Yuku Zhang, Yunbo Sun, Yushu Mu, Yutong Ren, Zeyu Cai, Zhangyi Liu, Zheyu Shen, Zhongxuan Li, Zhou Liang, Zhuo-Yang Song, Ziheng Zhou, Ziyang Ni, Zizhuo Fu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:53:29Z","title":"PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16074","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":"sha256:8777b947607683c8f6dae0b2f0434b82155c5f9735f85446b6bef3a6c48b486e","target":"record","created_at":"2026-07-05T11:04:49Z","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":"15cf134a205150d81bb2922e38f2273a0d66f6a1e7984eb5cb2959398716fa17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:53:29Z","title_canon_sha256":"5699bcf5d7ec6de15994fd88eadec401032a96810532f6674fb3eca61ef08cbf"},"schema_version":"1.0","source":{"id":"2504.16074","kind":"arxiv","version":2}},"canonical_sha256":"62870be6f8833dd2dc37d25cb386b6b195b386371bf4c3cf92c620d55f638080","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62870be6f8833dd2dc37d25cb386b6b195b386371bf4c3cf92c620d55f638080","first_computed_at":"2026-07-05T11:04:49.693081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:49.693081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2h+XFO/zCBcNy3/q0+2YNLeBcH2+X6Fj8mc1IUDn+Pr+GfELBcKmCLiH1ezAOvasEswLCAE9235RG3OUhncICg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:49.693612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16074","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8777b947607683c8f6dae0b2f0434b82155c5f9735f85446b6bef3a6c48b486e","sha256:0177e19117568e0f27ae360a2e5a5bec23a95be7c2ca0ad3774de02de3b25c7b"],"state_sha256":"7df5fecd32e8569eea792effbf5a1f5e0203145e5fb267e80d3ebcb090a38497"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hTUFwjCvkDQUnaMzEGOlHsmz4ttj6czPD5N0r0DaVVV4w3OZd5aMWrUfqOsCQiH+xWNaSF2NZbBIMMG3ROBxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T05:28:12.178210Z","bundle_sha256":"5f6947c6de0a965caa0d315f07b06a05ada7fbeacef240fb0538f6b4608a0bf3"}}