{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V3SDGG3IROB2VFJDHGRC6SSA6L","short_pith_number":"pith:V3SDGG3I","canonical_record":{"source":{"id":"2505.15616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T15:06:59Z","cross_cats_sorted":[],"title_canon_sha256":"224c7a8cc983291ae548fdc92d98aba4b63552a3ff5a56d54132ffcfbe9f5e9c","abstract_canon_sha256":"52afcd89ec74b77d64c60679e41748abd98d46856e9eabb689927e693e886493"},"schema_version":"1.0"},"canonical_sha256":"aee4331b688b83aa952339a22f4a40f2c003aab69aee2b5058e1488c88d6d984","source":{"kind":"arxiv","id":"2505.15616","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15616","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15616v2","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15616","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"pith_short_12","alias_value":"V3SDGG3IROB2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"V3SDGG3IROB2VFJD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"V3SDGG3I","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V3SDGG3IROB2VFJDHGRC6SSA6L","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T15:06:59Z","cross_cats_sorted":[],"title_canon_sha256":"224c7a8cc983291ae548fdc92d98aba4b63552a3ff5a56d54132ffcfbe9f5e9c","abstract_canon_sha256":"52afcd89ec74b77d64c60679e41748abd98d46856e9eabb689927e693e886493"},"schema_version":"1.0"},"canonical_sha256":"aee4331b688b83aa952339a22f4a40f2c003aab69aee2b5058e1488c88d6d984","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:13.903773Z","signature_b64":"Q1W+HVGHsPali+/e81R1OEsKTuvJOJSnEYoAhgcVvMJlZwB58H/2XyhUIKiLAg5sY6Ea/H22mo68CTNrXO1wAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aee4331b688b83aa952339a22f4a40f2c003aab69aee2b5058e1488c88d6d984","last_reissued_at":"2026-05-18T02:45:13.903024Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:13.903024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15616","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":"2026-05-18T02:45:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/L2gepACSFdC4NCxop2UV90dDcGm0QsfmBV7IeJwH1Zr5ypGL7Mk3+liAo/ouUD4L6Qq6iMibwzlZz9tGX7VCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:33:09.116968Z"},"content_sha256":"6bbc96acf5aab15d8141dde37ea6a9af1f76cb5c0be088686d46b0341372d8fe","schema_version":"1.0","event_id":"sha256:6bbc96acf5aab15d8141dde37ea6a9af1f76cb5c0be088686d46b0341372d8fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V3SDGG3IROB2VFJDHGRC6SSA6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Zhou, Bo Zhang, David Clifton, Guoyou Li, Jiajun Zhang, Jirui Huang, Luc Van Gool, Peng Xu, Ruilin Yao, Shengwu Xiong, Shichao Su, Shilan Zhang, Tianyu Zou, Wenxi Zeng, Xinwei Long, Yaxiong Chen, Yifang Zhang, Yifan Xu, Yufei Wu, Zhaoyu Yang, Zichan Li","submitted_at":"2025-05-21T15:06:59Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are usually constructed in the task-oriented manner without guarantee that different task samples come from the same data distribution, thus they often fall short in evaluating the synergistic effects of lower-level perceptual capabilities on higher-order reasoning. To lift this limitation, we contribute Lens, a multi-level benchmark with 3.4K contemporary images "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15616","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":""},"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":"2026-05-18T02:45:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsqFhloHHrE6K8oK0FLcGDTl8wiB8IZb15OPuo5+GgyGphd3W0piVs70qyi9MqZ2OOaJRwv6dO2mCks7Jrs9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:33:09.117343Z"},"content_sha256":"dbccca8f553807c39c2ba940a031291e6f5123e35ef67eca3135efe82e6611ab","schema_version":"1.0","event_id":"sha256:dbccca8f553807c39c2ba940a031291e6f5123e35ef67eca3135efe82e6611ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V3SDGG3IROB2VFJDHGRC6SSA6L/bundle.json","state_url":"https://pith.science/pith/V3SDGG3IROB2VFJDHGRC6SSA6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V3SDGG3IROB2VFJDHGRC6SSA6L/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":"2026-05-28T13:33:09Z","links":{"resolver":"https://pith.science/pith/V3SDGG3IROB2VFJDHGRC6SSA6L","bundle":"https://pith.science/pith/V3SDGG3IROB2VFJDHGRC6SSA6L/bundle.json","state":"https://pith.science/pith/V3SDGG3IROB2VFJDHGRC6SSA6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V3SDGG3IROB2VFJDHGRC6SSA6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V3SDGG3IROB2VFJDHGRC6SSA6L","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":"52afcd89ec74b77d64c60679e41748abd98d46856e9eabb689927e693e886493","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T15:06:59Z","title_canon_sha256":"224c7a8cc983291ae548fdc92d98aba4b63552a3ff5a56d54132ffcfbe9f5e9c"},"schema_version":"1.0","source":{"id":"2505.15616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15616","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15616v2","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15616","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"pith_short_12","alias_value":"V3SDGG3IROB2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"V3SDGG3IROB2VFJD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"V3SDGG3I","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:dbccca8f553807c39c2ba940a031291e6f5123e35ef67eca3135efe82e6611ab","target":"graph","created_at":"2026-05-18T02:45:13Z","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"},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are usually constructed in the task-oriented manner without guarantee that different task samples come from the same data distribution, thus they often fall short in evaluating the synergistic effects of lower-level perceptual capabilities on higher-order reasoning. To lift this limitation, we contribute Lens, a multi-level benchmark with 3.4K contemporary images ","authors_text":"Bowen Zhou, Bo Zhang, David Clifton, Guoyou Li, Jiajun Zhang, Jirui Huang, Luc Van Gool, Peng Xu, Ruilin Yao, Shengwu Xiong, Shichao Su, Shilan Zhang, Tianyu Zou, Wenxi Zeng, Xinwei Long, Yaxiong Chen, Yifang Zhang, Yifan Xu, Yufei Wu, Zhaoyu Yang, Zichan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T15:06:59Z","title":"LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15616","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":"sha256:6bbc96acf5aab15d8141dde37ea6a9af1f76cb5c0be088686d46b0341372d8fe","target":"record","created_at":"2026-05-18T02:45:13Z","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":"52afcd89ec74b77d64c60679e41748abd98d46856e9eabb689927e693e886493","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T15:06:59Z","title_canon_sha256":"224c7a8cc983291ae548fdc92d98aba4b63552a3ff5a56d54132ffcfbe9f5e9c"},"schema_version":"1.0","source":{"id":"2505.15616","kind":"arxiv","version":2}},"canonical_sha256":"aee4331b688b83aa952339a22f4a40f2c003aab69aee2b5058e1488c88d6d984","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aee4331b688b83aa952339a22f4a40f2c003aab69aee2b5058e1488c88d6d984","first_computed_at":"2026-05-18T02:45:13.903024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:45:13.903024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q1W+HVGHsPali+/e81R1OEsKTuvJOJSnEYoAhgcVvMJlZwB58H/2XyhUIKiLAg5sY6Ea/H22mo68CTNrXO1wAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:45:13.903773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bbc96acf5aab15d8141dde37ea6a9af1f76cb5c0be088686d46b0341372d8fe","sha256:dbccca8f553807c39c2ba940a031291e6f5123e35ef67eca3135efe82e6611ab"],"state_sha256":"c6061fee2d1a8ce9f315b598c73ad81ddf9c6d505be0e9242b7ffbbe3a6c568f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKsN+zSZkVGBPhbboUxTe7QH9tSVDEi+6LdjeIjJgeiN2FW2khdyLen/dZQ6rmCCdwqoWg0r3GX/xQPFY4nxBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:33:09.120227Z","bundle_sha256":"890cbab16fbb6352bad16b5e05e55a4a28eab4d8520803e0a66fff5532804ae4"}}