{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AEDRHEWWMWQPIM62CKA3RJHS3L","short_pith_number":"pith:AEDRHEWW","schema_version":"1.0","canonical_sha256":"01071392d665a0f433da1281b8a4f2daf432e6f2c2949f4e77fe82c71821694d","source":{"kind":"arxiv","id":"2401.10529","version":2},"attestation_state":"computed","paper":{"title":"Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Feihong He, Furong Huang, Gedas Bertasius, Hongjin Lu, Huaxiu Yao, Jaehong Yoon, Mohit Bansal, Taixi Lu, Xiaoyu Liu, Xiyao Wang, Yuancheng Xu, Yuhang Zhou","submitted_at":"2024-01-19T07:10:13Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated proficiency in handling a variety of visual-language tasks. However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image, and the ability of modern MLLMs to extrapolate from image sequences, which is essential for understanding our ever-changing world, has been less investigated. To address this challenge, this paper introduces Mementos, a new benchmark designed to assess MLLMs' sequential image reasoning abilities. Mementos features 4,761 diverse image sequences wit"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.10529","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T07:10:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"94b361144c501a69002429f16448554de6ea094e33e3c9f6e90c96baab6d77d3","abstract_canon_sha256":"4f43b20b7c693593a94f9185a093023a7c766bba3eea3cb872da17b666033568"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:15.437290Z","signature_b64":"q5hfvHmolXO+/1NYHopZhF+hfx9e0NxhcRaD1CiEYJ47G7rKeclH9EbfKX3jUsGhOp/sijh32nBEpqimz620CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01071392d665a0f433da1281b8a4f2daf432e6f2c2949f4e77fe82c71821694d","last_reissued_at":"2026-07-05T07:37:15.436763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:15.436763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Feihong He, Furong Huang, Gedas Bertasius, Hongjin Lu, Huaxiu Yao, Jaehong Yoon, Mohit Bansal, Taixi Lu, Xiaoyu Liu, Xiyao Wang, Yuancheng Xu, Yuhang Zhou","submitted_at":"2024-01-19T07:10:13Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated proficiency in handling a variety of visual-language tasks. However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image, and the ability of modern MLLMs to extrapolate from image sequences, which is essential for understanding our ever-changing world, has been less investigated. To address this challenge, this paper introduces Mementos, a new benchmark designed to assess MLLMs' sequential image reasoning abilities. Mementos features 4,761 diverse image sequences wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10529","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/2401.10529/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.10529","created_at":"2026-07-05T07:37:15.436840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10529v2","created_at":"2026-07-05T07:37:15.436840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10529","created_at":"2026-07-05T07:37:15.436840+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEDRHEWWMWQP","created_at":"2026-07-05T07:37:15.436840+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEDRHEWWMWQPIM62","created_at":"2026-07-05T07:37:15.436840+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEDRHEWW","created_at":"2026-07-05T07:37:15.436840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15710","citing_title":"SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09411","citing_title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07592","citing_title":"Spatio-Temporal Grounding of Large Language Models from Perception Streams","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":255,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L","json":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L.json","graph_json":"https://pith.science/api/pith-number/AEDRHEWWMWQPIM62CKA3RJHS3L/graph.json","events_json":"https://pith.science/api/pith-number/AEDRHEWWMWQPIM62CKA3RJHS3L/events.json","paper":"https://pith.science/paper/AEDRHEWW"},"agent_actions":{"view_html":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L","download_json":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L.json","view_paper":"https://pith.science/paper/AEDRHEWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10529&json=true","fetch_graph":"https://pith.science/api/pith-number/AEDRHEWWMWQPIM62CKA3RJHS3L/graph.json","fetch_events":"https://pith.science/api/pith-number/AEDRHEWWMWQPIM62CKA3RJHS3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/action/storage_attestation","attest_author":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/action/author_attestation","sign_citation":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/action/citation_signature","submit_replication":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/action/replication_record"}},"created_at":"2026-07-05T07:37:15.436840+00:00","updated_at":"2026-07-05T07:37:15.436840+00:00"}