{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AEDRHEWWMWQPIM62CKA3RJHS3L","short_pith_number":"pith:AEDRHEWW","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"},"canonical_sha256":"01071392d665a0f433da1281b8a4f2daf432e6f2c2949f4e77fe82c71821694d","source":{"kind":"arxiv","id":"2401.10529","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10529","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10529v2","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10529","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"AEDRHEWWMWQP","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"AEDRHEWWMWQPIM62","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"AEDRHEWW","created_at":"2026-07-05T07:37:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AEDRHEWWMWQPIM62CKA3RJHS3L","target":"record","payload":{"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"},"canonical_sha256":"01071392d665a0f433da1281b8a4f2daf432e6f2c2949f4e77fe82c71821694d","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"},"source_kind":"arxiv","source_id":"2401.10529","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":"2026-07-05T07:37:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xEkVCyUzJWWN+gAw/pjKvaKAO2W4VF1tTY+PjjDCurDJv9eaZEaw+cA5U7tKtALd7YNC7+kBKt4YSsG21B/vAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:25:59.422760Z"},"content_sha256":"acb3ce6d5fc0676d9b773f8208c4d734fc58c12d39da97bb0fede5590543665a","schema_version":"1.0","event_id":"sha256:acb3ce6d5fc0676d9b773f8208c4d734fc58c12d39da97bb0fede5590543665a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AEDRHEWWMWQPIM62CKA3RJHS3L","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:37:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s4OnN7cn1faCuBDG27M5pZ1z2WIBnHIeI6N7CGzIa8MtVqOYIBDbTpt370Kx5cuj4ew23uAdz+8NBEym3A0ADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:25:59.423318Z"},"content_sha256":"a1c76823ef38f62f2c6deba19ec4e8614fb94f2d9dc6dd3dd97a161b3bef5f09","schema_version":"1.0","event_id":"sha256:a1c76823ef38f62f2c6deba19ec4e8614fb94f2d9dc6dd3dd97a161b3bef5f09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/bundle.json","state_url":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/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":"2026-08-04T06:25:59Z","links":{"resolver":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L","bundle":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/bundle.json","state":"https://pith.science/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AEDRHEWWMWQPIM62CKA3RJHS3L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AEDRHEWWMWQPIM62CKA3RJHS3L","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":"4f43b20b7c693593a94f9185a093023a7c766bba3eea3cb872da17b666033568","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T07:10:13Z","title_canon_sha256":"94b361144c501a69002429f16448554de6ea094e33e3c9f6e90c96baab6d77d3"},"schema_version":"1.0","source":{"id":"2401.10529","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10529","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10529v2","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10529","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"AEDRHEWWMWQP","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"AEDRHEWWMWQPIM62","created_at":"2026-07-05T07:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"AEDRHEWW","created_at":"2026-07-05T07:37:15Z"}],"graph_snapshots":[{"event_id":"sha256:a1c76823ef38f62f2c6deba19ec4e8614fb94f2d9dc6dd3dd97a161b3bef5f09","target":"graph","created_at":"2026-07-05T07:37:15Z","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/2401.10529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T07:10:13Z","title":"Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10529","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:acb3ce6d5fc0676d9b773f8208c4d734fc58c12d39da97bb0fede5590543665a","target":"record","created_at":"2026-07-05T07:37:15Z","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":"4f43b20b7c693593a94f9185a093023a7c766bba3eea3cb872da17b666033568","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T07:10:13Z","title_canon_sha256":"94b361144c501a69002429f16448554de6ea094e33e3c9f6e90c96baab6d77d3"},"schema_version":"1.0","source":{"id":"2401.10529","kind":"arxiv","version":2}},"canonical_sha256":"01071392d665a0f433da1281b8a4f2daf432e6f2c2949f4e77fe82c71821694d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01071392d665a0f433da1281b8a4f2daf432e6f2c2949f4e77fe82c71821694d","first_computed_at":"2026-07-05T07:37:15.436763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:15.436763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q5hfvHmolXO+/1NYHopZhF+hfx9e0NxhcRaD1CiEYJ47G7rKeclH9EbfKX3jUsGhOp/sijh32nBEpqimz620CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:15.437290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.10529","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acb3ce6d5fc0676d9b773f8208c4d734fc58c12d39da97bb0fede5590543665a","sha256:a1c76823ef38f62f2c6deba19ec4e8614fb94f2d9dc6dd3dd97a161b3bef5f09"],"state_sha256":"6a89f7a86eaeacdf1d47dd165b134f3e03d651f9fb3ade76e4a3638720c6ddd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X8dqlMiGynFzDhrDUZYvQ7A3woO56TPenRzvJYBW46+EyOEjbZMwIoXpA8skg3ukyFNtSDUXQmiarBaLfzMrAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:25:59.429030Z","bundle_sha256":"f7291a77f98cfc4ae9802ba2a1a62334220a18ef9a985abc3de9546bd4534217"}}