{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K2DYVBFYHBTTE7DKRNZ3ZVH2SX","short_pith_number":"pith:K2DYVBFY","canonical_record":{"source":{"id":"2410.04345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T03:47:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"754a5bc6d6ff6047a9010123129408b6e7bc587a8ed714ca50940b5d477d641d","abstract_canon_sha256":"b1f976f4af37c91174e68512f4e5ca07b5d6aed3951ebe41735d6a06dded6059"},"schema_version":"1.0"},"canonical_sha256":"56878a84b83867327c6a8b73bcd4fa95f870918b6b4bd1ef357e3ae4ac87e540","source":{"kind":"arxiv","id":"2410.04345","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04345","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04345v1","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04345","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"pith_short_12","alias_value":"K2DYVBFYHBTT","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"pith_short_16","alias_value":"K2DYVBFYHBTTE7DK","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"pith_short_8","alias_value":"K2DYVBFY","created_at":"2026-07-05T09:16:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K2DYVBFYHBTTE7DKRNZ3ZVH2SX","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T03:47:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"754a5bc6d6ff6047a9010123129408b6e7bc587a8ed714ca50940b5d477d641d","abstract_canon_sha256":"b1f976f4af37c91174e68512f4e5ca07b5d6aed3951ebe41735d6a06dded6059"},"schema_version":"1.0"},"canonical_sha256":"56878a84b83867327c6a8b73bcd4fa95f870918b6b4bd1ef357e3ae4ac87e540","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:33.055038Z","signature_b64":"v2JOnCeLhQqWSk3OzLZkyCgoUwuNKhCo4qpsgDmXEz4k7zm1/PyZ5WvsW2aLHxQXWI2k3FW4C2mso85enIJAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56878a84b83867327c6a8b73bcd4fa95f870918b6b4bd1ef357e3ae4ac87e540","last_reissued_at":"2026-07-05T09:16:33.054627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:33.054627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04345","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":"2026-07-05T09:16:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"imC8FuHgTI011EV3g2dy/yrsPtC6Igarj7xpM4FzF3IYN1hzOQze5Fdqw/Nxrx/L5OHLBWGuON20Eoyx+iqHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:02:45.552617Z"},"content_sha256":"3252968e6872887be7a2167e2198fc2321fd4eb568fb3704558f3a0e4ed6af24","schema_version":"1.0","event_id":"sha256:3252968e6872887be7a2167e2198fc2321fd4eb568fb3704558f3a0e4ed6af24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K2DYVBFYHBTTE7DKRNZ3ZVH2SX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanzhen Li, Min-Yen Kan, Yuxi Xie","submitted_at":"2024-10-06T03:47:57Z","abstract_excerpt":"Humans perform visual perception at multiple levels, including low-level object recognition and high-level semantic interpretation such as behavior understanding. Subtle differences in low-level details can lead to substantial changes in high-level perception. For example, substituting the shopping bag held by a person with a gun suggests violent behavior, implying criminal or violent activity. Despite significant advancements in various multimodal tasks, Large Visual-Language Models (LVLMs) remain unexplored in their capabilities to conduct such multi-level visual perceptions.\n  To investigat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04345","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/2410.04345/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":"2026-07-05T09:16:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E9QNPgn7B9XsqLZkm63e5RCKmIwjgXCOFM36+YEwPkIZFfkyIYBlr1nxl5Eu292n6WBPOuguV3TXYNjh11HaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:02:45.553132Z"},"content_sha256":"335b9529fde11e3177cf51af4097b12cca7e17a841ce1bf4432b26216c7c9715","schema_version":"1.0","event_id":"sha256:335b9529fde11e3177cf51af4097b12cca7e17a841ce1bf4432b26216c7c9715"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2DYVBFYHBTTE7DKRNZ3ZVH2SX/bundle.json","state_url":"https://pith.science/pith/K2DYVBFYHBTTE7DKRNZ3ZVH2SX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2DYVBFYHBTTE7DKRNZ3ZVH2SX/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":"2026-08-19T02:02:45Z","links":{"resolver":"https://pith.science/pith/K2DYVBFYHBTTE7DKRNZ3ZVH2SX","bundle":"https://pith.science/pith/K2DYVBFYHBTTE7DKRNZ3ZVH2SX/bundle.json","state":"https://pith.science/pith/K2DYVBFYHBTTE7DKRNZ3ZVH2SX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2DYVBFYHBTTE7DKRNZ3ZVH2SX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K2DYVBFYHBTTE7DKRNZ3ZVH2SX","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":"b1f976f4af37c91174e68512f4e5ca07b5d6aed3951ebe41735d6a06dded6059","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T03:47:57Z","title_canon_sha256":"754a5bc6d6ff6047a9010123129408b6e7bc587a8ed714ca50940b5d477d641d"},"schema_version":"1.0","source":{"id":"2410.04345","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04345","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04345v1","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04345","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"pith_short_12","alias_value":"K2DYVBFYHBTT","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"pith_short_16","alias_value":"K2DYVBFYHBTTE7DK","created_at":"2026-07-05T09:16:33Z"},{"alias_kind":"pith_short_8","alias_value":"K2DYVBFY","created_at":"2026-07-05T09:16:33Z"}],"graph_snapshots":[{"event_id":"sha256:335b9529fde11e3177cf51af4097b12cca7e17a841ce1bf4432b26216c7c9715","target":"graph","created_at":"2026-07-05T09:16:33Z","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/2410.04345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans perform visual perception at multiple levels, including low-level object recognition and high-level semantic interpretation such as behavior understanding. Subtle differences in low-level details can lead to substantial changes in high-level perception. For example, substituting the shopping bag held by a person with a gun suggests violent behavior, implying criminal or violent activity. Despite significant advancements in various multimodal tasks, Large Visual-Language Models (LVLMs) remain unexplored in their capabilities to conduct such multi-level visual perceptions.\n  To investigat","authors_text":"Guanzhen Li, Min-Yen Kan, Yuxi Xie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T03:47:57Z","title":"MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04345","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":"sha256:3252968e6872887be7a2167e2198fc2321fd4eb568fb3704558f3a0e4ed6af24","target":"record","created_at":"2026-07-05T09:16:33Z","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":"b1f976f4af37c91174e68512f4e5ca07b5d6aed3951ebe41735d6a06dded6059","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-06T03:47:57Z","title_canon_sha256":"754a5bc6d6ff6047a9010123129408b6e7bc587a8ed714ca50940b5d477d641d"},"schema_version":"1.0","source":{"id":"2410.04345","kind":"arxiv","version":1}},"canonical_sha256":"56878a84b83867327c6a8b73bcd4fa95f870918b6b4bd1ef357e3ae4ac87e540","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56878a84b83867327c6a8b73bcd4fa95f870918b6b4bd1ef357e3ae4ac87e540","first_computed_at":"2026-07-05T09:16:33.054627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:33.054627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v2JOnCeLhQqWSk3OzLZkyCgoUwuNKhCo4qpsgDmXEz4k7zm1/PyZ5WvsW2aLHxQXWI2k3FW4C2mso85enIJAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:33.055038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04345","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3252968e6872887be7a2167e2198fc2321fd4eb568fb3704558f3a0e4ed6af24","sha256:335b9529fde11e3177cf51af4097b12cca7e17a841ce1bf4432b26216c7c9715"],"state_sha256":"fa7abbea549a2353b8a49e8a505f5dd0244415d6672a645bad355a9dd77619fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EhhAXS44f3UVx8zjuxSj8bdCFfSK1NjyLdR8wyDulS9JKUKDkC6/t4LowlbC3+bRyNftxikgRjtkfwc6F1shCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:02:45.556972Z","bundle_sha256":"039f2cdd953da9de4c842a4306fb331843acd0345201c75ef147f53d937165c4"}}