{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RDGM2JEDLGAJ3W7D5IWXMIDBNO","short_pith_number":"pith:RDGM2JED","schema_version":"1.0","canonical_sha256":"88cccd248359809ddbe3ea2d7620616b9bf3ea6c39fa7ffcb30f27fc2b18b516","source":{"kind":"arxiv","id":"2601.07298","version":2},"attestation_state":"computed","paper":{"title":"Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqing Li, Cheng Ding, Jianghao Yin, Jian Xu, Jie Wang, Jie Zhou, Kun Sun, Liang He, Nan Wang, Pei Wu, Qin Chen, Qingbin Li, Zheming Yang","submitted_at":"2026-01-12T08:15:36Z","abstract_excerpt":"While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose a Cognition-Inspired Meta-Action Framework (CINEMA), which decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer, explicitly modeling the sequential cognitive steps hum"},"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":"2601.07298","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-12T08:15:36Z","cross_cats_sorted":[],"title_canon_sha256":"ae7565c4f08bc1210da6d7e091535ce53290ae62529d13ee19d8f064936987ea","abstract_canon_sha256":"0335c5278353b750a19f05613834a9e457eea823945573f91312decffb2fafc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:20.059719Z","signature_b64":"ZLinnHNIxlPeFaclrEfUmymPotDAzmAOazcB2KDuoxpsu2+FlNQ5EfNx3R7l5IfUlZbE9fuzwrNqItxPUtPKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88cccd248359809ddbe3ea2d7620616b9bf3ea6c39fa7ffcb30f27fc2b18b516","last_reissued_at":"2026-06-23T02:13:20.059331Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:20.059331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqing Li, Cheng Ding, Jianghao Yin, Jian Xu, Jie Wang, Jie Zhou, Kun Sun, Liang He, Nan Wang, Pei Wu, Qin Chen, Qingbin Li, Zheming Yang","submitted_at":"2026-01-12T08:15:36Z","abstract_excerpt":"While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose a Cognition-Inspired Meta-Action Framework (CINEMA), which decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer, explicitly modeling the sequential cognitive steps hum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.07298","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/2601.07298/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":"2601.07298","created_at":"2026-06-23T02:13:20.059388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.07298v2","created_at":"2026-06-23T02:13:20.059388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.07298","created_at":"2026-06-23T02:13:20.059388+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDGM2JEDLGAJ","created_at":"2026-06-23T02:13:20.059388+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDGM2JEDLGAJ3W7D","created_at":"2026-06-23T02:13:20.059388+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDGM2JED","created_at":"2026-06-23T02:13:20.059388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RDGM2JEDLGAJ3W7D5IWXMIDBNO","json":"https://pith.science/pith/RDGM2JEDLGAJ3W7D5IWXMIDBNO.json","graph_json":"https://pith.science/api/pith-number/RDGM2JEDLGAJ3W7D5IWXMIDBNO/graph.json","events_json":"https://pith.science/api/pith-number/RDGM2JEDLGAJ3W7D5IWXMIDBNO/events.json","paper":"https://pith.science/paper/RDGM2JED"},"agent_actions":{"view_html":"https://pith.science/pith/RDGM2JEDLGAJ3W7D5IWXMIDBNO","download_json":"https://pith.science/pith/RDGM2JEDLGAJ3W7D5IWXMIDBNO.json","view_paper":"https://pith.science/paper/RDGM2JED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.07298&json=true","fetch_graph":"https://pith.science/api/pith-number/RDGM2JEDLGAJ3W7D5IWXMIDBNO/graph.json","fetch_events":"https://pith.science/api/pith-number/RDGM2JEDLGAJ3W7D5IWXMIDBNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDGM2JEDLGAJ3W7D5IWXMIDBNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDGM2JEDLGAJ3W7D5IWXMIDBNO/action/storage_attestation","attest_author":"https://pith.science/pith/RDGM2JEDLGAJ3W7D5IWXMIDBNO/action/author_attestation","sign_citation":"https://pith.science/pith/RDGM2JEDLGAJ3W7D5IWXMIDBNO/action/citation_signature","submit_replication":"https://pith.science/pith/RDGM2JEDLGAJ3W7D5IWXMIDBNO/action/replication_record"}},"created_at":"2026-06-23T02:13:20.059388+00:00","updated_at":"2026-06-23T02:13:20.059388+00:00"}