{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E43VPQLL6FFE6IDIIZJVRHO2VV","short_pith_number":"pith:E43VPQLL","canonical_record":{"source":{"id":"2411.14725","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T04:41:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"16f328a284ae778bbcb982c368c0d4d8660a04e116f420b5eb3bb8a755c38308","abstract_canon_sha256":"296bbdbc13db5f0ff0d280552e6f024c5065186de24adf084ea6626889b54adb"},"schema_version":"1.0"},"canonical_sha256":"273757c16bf14a4f20684653589ddaad5a7c69f6e63ae76e4c762d975fd34280","source":{"kind":"arxiv","id":"2411.14725","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14725","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14725v2","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14725","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"pith_short_12","alias_value":"E43VPQLL6FFE","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"pith_short_16","alias_value":"E43VPQLL6FFE6IDI","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"pith_short_8","alias_value":"E43VPQLL","created_at":"2026-07-05T11:14:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E43VPQLL6FFE6IDIIZJVRHO2VV","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14725","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T04:41:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"16f328a284ae778bbcb982c368c0d4d8660a04e116f420b5eb3bb8a755c38308","abstract_canon_sha256":"296bbdbc13db5f0ff0d280552e6f024c5065186de24adf084ea6626889b54adb"},"schema_version":"1.0"},"canonical_sha256":"273757c16bf14a4f20684653589ddaad5a7c69f6e63ae76e4c762d975fd34280","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:50.942682Z","signature_b64":"z5qdGkPwoAHUw8XcpGMA+Mv8n/rFSPlvjawIUW0wziHRy9Bpj4veg5DLa4Lium2t2a/Ufi524l/CuPdbqRXKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"273757c16bf14a4f20684653589ddaad5a7c69f6e63ae76e4c762d975fd34280","last_reissued_at":"2026-07-05T11:14:50.942217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:50.942217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14725","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":"2026-07-05T11:14:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXVy0TsiqlrAkP8w3wmAPVECnvu9SS9jmN+Haz8kJYMmgu86t+YjooIlWcxnmWbf0IJNNVJfFngamr4YzB7xAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T14:02:01.261521Z"},"content_sha256":"9e4dc859f29cde1fb5bff490694fc69fc9a395fc40fa42de4f165e86ae7b76d8","schema_version":"1.0","event_id":"sha256:9e4dc859f29cde1fb5bff490694fc69fc9a395fc40fa42de4f165e86ae7b76d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E43VPQLL6FFE6IDIIZJVRHO2VV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Chenhui Gou, Feng Chen, Jing Liu, Jiyuan Zhang, Qi Wu, Yang Yang, Zhaoyang Li, Zhenbang Sun","submitted_at":"2024-11-22T04:41:20Z","abstract_excerpt":"As multimodal large language models (MLLMs) advance rapidly, rigorous evaluation has become essential, providing further guidance for their development. In this work, we focus on a unified and robust evaluation of \\textbf{vision perception} abilities, the foundational skill of MLLMs. We find that existing perception benchmarks, each focusing on different question types, domains, and evaluation metrics, introduce significant evaluation variance, complicating comprehensive assessments of perception abilities when relying on any single benchmark. To address this, we introduce \\textbf{AbilityLens}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14725","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/2411.14725/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":"2026-07-05T11:14:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OyyOORtbvptNTjVyz14VcLzGMf/NEXkgFFGjIeytNsCj3JfGBRSJGhUxWIIhUbrhx+tT5AeWOVWNpE7VinWKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T14:02:01.261912Z"},"content_sha256":"cd9ec9e91689dfcb7b07798732748c145d21a12ac3e563b9be758a0c5f05480f","schema_version":"1.0","event_id":"sha256:cd9ec9e91689dfcb7b07798732748c145d21a12ac3e563b9be758a0c5f05480f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E43VPQLL6FFE6IDIIZJVRHO2VV/bundle.json","state_url":"https://pith.science/pith/E43VPQLL6FFE6IDIIZJVRHO2VV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E43VPQLL6FFE6IDIIZJVRHO2VV/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":"2026-08-13T14:02:01Z","links":{"resolver":"https://pith.science/pith/E43VPQLL6FFE6IDIIZJVRHO2VV","bundle":"https://pith.science/pith/E43VPQLL6FFE6IDIIZJVRHO2VV/bundle.json","state":"https://pith.science/pith/E43VPQLL6FFE6IDIIZJVRHO2VV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E43VPQLL6FFE6IDIIZJVRHO2VV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E43VPQLL6FFE6IDIIZJVRHO2VV","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":"296bbdbc13db5f0ff0d280552e6f024c5065186de24adf084ea6626889b54adb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T04:41:20Z","title_canon_sha256":"16f328a284ae778bbcb982c368c0d4d8660a04e116f420b5eb3bb8a755c38308"},"schema_version":"1.0","source":{"id":"2411.14725","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14725","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14725v2","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14725","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"pith_short_12","alias_value":"E43VPQLL6FFE","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"pith_short_16","alias_value":"E43VPQLL6FFE6IDI","created_at":"2026-07-05T11:14:50Z"},{"alias_kind":"pith_short_8","alias_value":"E43VPQLL","created_at":"2026-07-05T11:14:50Z"}],"graph_snapshots":[{"event_id":"sha256:cd9ec9e91689dfcb7b07798732748c145d21a12ac3e563b9be758a0c5f05480f","target":"graph","created_at":"2026-07-05T11:14:50Z","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/2411.14725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As multimodal large language models (MLLMs) advance rapidly, rigorous evaluation has become essential, providing further guidance for their development. In this work, we focus on a unified and robust evaluation of \\textbf{vision perception} abilities, the foundational skill of MLLMs. We find that existing perception benchmarks, each focusing on different question types, domains, and evaluation metrics, introduce significant evaluation variance, complicating comprehensive assessments of perception abilities when relying on any single benchmark. To address this, we introduce \\textbf{AbilityLens}","authors_text":"Bohan Zhuang, Chenhui Gou, Feng Chen, Jing Liu, Jiyuan Zhang, Qi Wu, Yang Yang, Zhaoyang Li, Zhenbang Sun","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T04:41:20Z","title":"Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14725","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":"sha256:9e4dc859f29cde1fb5bff490694fc69fc9a395fc40fa42de4f165e86ae7b76d8","target":"record","created_at":"2026-07-05T11:14:50Z","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":"296bbdbc13db5f0ff0d280552e6f024c5065186de24adf084ea6626889b54adb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T04:41:20Z","title_canon_sha256":"16f328a284ae778bbcb982c368c0d4d8660a04e116f420b5eb3bb8a755c38308"},"schema_version":"1.0","source":{"id":"2411.14725","kind":"arxiv","version":2}},"canonical_sha256":"273757c16bf14a4f20684653589ddaad5a7c69f6e63ae76e4c762d975fd34280","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"273757c16bf14a4f20684653589ddaad5a7c69f6e63ae76e4c762d975fd34280","first_computed_at":"2026-07-05T11:14:50.942217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:50.942217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5qdGkPwoAHUw8XcpGMA+Mv8n/rFSPlvjawIUW0wziHRy9Bpj4veg5DLa4Lium2t2a/Ufi524l/CuPdbqRXKCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:50.942682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14725","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e4dc859f29cde1fb5bff490694fc69fc9a395fc40fa42de4f165e86ae7b76d8","sha256:cd9ec9e91689dfcb7b07798732748c145d21a12ac3e563b9be758a0c5f05480f"],"state_sha256":"68895f46012d65b6c2da04f0b0b067bd326bac293acc17defbef8bef28f65bdc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OjxoW4ktdYYjohxUG3somShir6BGF3LmjATo7An8Uu7mudUrNHuV++GXj1FjEncV0haiLX9mj3pIrsLl0iYCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T14:02:01.265075Z","bundle_sha256":"ad83dff6f2be356aa68e2ba4319222ac5bec97638b4ece743a4d734ff3fc9f40"}}