{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NCVUURDFKNQYQGWFSFJK2OMHQ4","short_pith_number":"pith:NCVUURDF","canonical_record":{"source":{"id":"2507.00045","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T22:05:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a36cc468cebae109a4973e776762580c668b6d66d8fea29b90e66bf8b881463a","abstract_canon_sha256":"19fe163bad4fd265f850c5aa50e57578ca7ae373cdb10d4838e6f3bcf1363055"},"schema_version":"1.0"},"canonical_sha256":"68ab4a44655361881ac59152ad39878711a6dc4d5506fcedc6e6711da39b0518","source":{"kind":"arxiv","id":"2507.00045","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00045","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00045v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00045","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"NCVUURDFKNQY","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"NCVUURDFKNQYQGWF","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"NCVUURDF","created_at":"2026-07-05T11:29:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NCVUURDFKNQYQGWFSFJK2OMHQ4","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00045","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T22:05:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a36cc468cebae109a4973e776762580c668b6d66d8fea29b90e66bf8b881463a","abstract_canon_sha256":"19fe163bad4fd265f850c5aa50e57578ca7ae373cdb10d4838e6f3bcf1363055"},"schema_version":"1.0"},"canonical_sha256":"68ab4a44655361881ac59152ad39878711a6dc4d5506fcedc6e6711da39b0518","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:35.644261Z","signature_b64":"ICPGu/Gcl6gN6eKTUbcz2RbPWHiZjXuAdVgQAsiAj/ICy1TL2HMg9dJeJGGj3LMJZMubi/A1MIvsyeOoJVx8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68ab4a44655361881ac59152ad39878711a6dc4d5506fcedc6e6711da39b0518","last_reissued_at":"2026-07-05T11:29:35.643601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:35.643601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00045","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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKGFD9Q6Mi0zIP9NfIENEcplgEGTKUzKj7Eq1NtQYJ2HUB1r3n3v5HjIvkNqPeZPO7gJt4uVrNFS3tAHBbkRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:22:45.586730Z"},"content_sha256":"9473135e10af7f05bf5633f8344bcfc7e7eb797fa03800e4a234e43a20924c10","schema_version":"1.0","event_id":"sha256:9473135e10af7f05bf5633f8344bcfc7e7eb797fa03800e4a234e43a20924c10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NCVUURDFKNQYQGWFSFJK2OMHQ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chenguang Wang, Ming Li, Ruiyi Zhang, Tianyi Zhou, Xiyang Wu, Xiyao Wang, Yijun Liang, Yuhang Zhou, Yuqing Zhang","submitted_at":"2025-06-23T22:05:21Z","abstract_excerpt":"Recent agentic Multi-Modal Large Language Models (MLLMs) such as GPT-o3 have achieved near-ceiling scores on various existing benchmarks, motivating a demand for more challenging test tasks. These MLLMs have been reported to excel in a few expert-level tasks for humans, e.g., GeoGuesser, reflecting their potential as a detective who can notice minuscule cues in an image and weave them into coherent, situational explanations, leading to a reliable answer. But can they match the performance of excellent human detectives? To answer this question, we investigate some hard scenarios where GPT-o3 ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00045","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/2507.00045/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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n4Az9pmvbKtWeMI4Zrg5uHiwwGt7v4HnwMIeLqDwj6sZcAczL7gAkYk4IiJ6yXrRyoSe37flFTQQ/jPMzuo7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:22:45.587681Z"},"content_sha256":"e21656acfff7a287790ee3840151194979f4205a4cc5fd90051b668f5c2910f8","schema_version":"1.0","event_id":"sha256:e21656acfff7a287790ee3840151194979f4205a4cc5fd90051b668f5c2910f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCVUURDFKNQYQGWFSFJK2OMHQ4/bundle.json","state_url":"https://pith.science/pith/NCVUURDFKNQYQGWFSFJK2OMHQ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCVUURDFKNQYQGWFSFJK2OMHQ4/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":"2026-08-09T08:22:45Z","links":{"resolver":"https://pith.science/pith/NCVUURDFKNQYQGWFSFJK2OMHQ4","bundle":"https://pith.science/pith/NCVUURDFKNQYQGWFSFJK2OMHQ4/bundle.json","state":"https://pith.science/pith/NCVUURDFKNQYQGWFSFJK2OMHQ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCVUURDFKNQYQGWFSFJK2OMHQ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NCVUURDFKNQYQGWFSFJK2OMHQ4","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":"19fe163bad4fd265f850c5aa50e57578ca7ae373cdb10d4838e6f3bcf1363055","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T22:05:21Z","title_canon_sha256":"a36cc468cebae109a4973e776762580c668b6d66d8fea29b90e66bf8b881463a"},"schema_version":"1.0","source":{"id":"2507.00045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00045","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00045v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00045","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"NCVUURDFKNQY","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"NCVUURDFKNQYQGWF","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"NCVUURDF","created_at":"2026-07-05T11:29:35Z"}],"graph_snapshots":[{"event_id":"sha256:e21656acfff7a287790ee3840151194979f4205a4cc5fd90051b668f5c2910f8","target":"graph","created_at":"2026-07-05T11:29:35Z","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/2507.00045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent agentic Multi-Modal Large Language Models (MLLMs) such as GPT-o3 have achieved near-ceiling scores on various existing benchmarks, motivating a demand for more challenging test tasks. These MLLMs have been reported to excel in a few expert-level tasks for humans, e.g., GeoGuesser, reflecting their potential as a detective who can notice minuscule cues in an image and weave them into coherent, situational explanations, leading to a reliable answer. But can they match the performance of excellent human detectives? To answer this question, we investigate some hard scenarios where GPT-o3 ca","authors_text":"Chenguang Wang, Ming Li, Ruiyi Zhang, Tianyi Zhou, Xiyang Wu, Xiyao Wang, Yijun Liang, Yuhang Zhou, Yuqing Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T22:05:21Z","title":"CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00045","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":"sha256:9473135e10af7f05bf5633f8344bcfc7e7eb797fa03800e4a234e43a20924c10","target":"record","created_at":"2026-07-05T11:29:35Z","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":"19fe163bad4fd265f850c5aa50e57578ca7ae373cdb10d4838e6f3bcf1363055","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T22:05:21Z","title_canon_sha256":"a36cc468cebae109a4973e776762580c668b6d66d8fea29b90e66bf8b881463a"},"schema_version":"1.0","source":{"id":"2507.00045","kind":"arxiv","version":1}},"canonical_sha256":"68ab4a44655361881ac59152ad39878711a6dc4d5506fcedc6e6711da39b0518","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68ab4a44655361881ac59152ad39878711a6dc4d5506fcedc6e6711da39b0518","first_computed_at":"2026-07-05T11:29:35.643601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:35.643601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ICPGu/Gcl6gN6eKTUbcz2RbPWHiZjXuAdVgQAsiAj/ICy1TL2HMg9dJeJGGj3LMJZMubi/A1MIvsyeOoJVx8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:35.644261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9473135e10af7f05bf5633f8344bcfc7e7eb797fa03800e4a234e43a20924c10","sha256:e21656acfff7a287790ee3840151194979f4205a4cc5fd90051b668f5c2910f8"],"state_sha256":"ee79a4c90fec46e1a206b9bd3330181f1ff82958b39999b433e3c5a5db7b0b5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I0qIUu09du8Cqqz9W5rjdGZBW4Uz94YL8WtCic3DmbfLmPO8sF6BXx/tp2yvfZqQh1vgHz32OVB2iexro5/MBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:22:45.594774Z","bundle_sha256":"024f817242c20efaacd775422beedd73fc7ea567506594c237b063b11d77278b"}}