{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VEZXXSFKDO7JHC76AL4HEWS4HC","short_pith_number":"pith:VEZXXSFK","schema_version":"1.0","canonical_sha256":"a9337bc8aa1bbe938bfe02f8725a5c389162bbbead4eb325258292b35afe53a2","source":{"kind":"arxiv","id":"2503.18533","version":1},"attestation_state":"computed","paper":{"title":"MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunhua Shen, Dawei Yan, Haokui Zhang, Peng Wang, Qing-Guo Chen, Weihua Luo, Yang Li","submitted_at":"2025-03-24T10:40:33Z","abstract_excerpt":"Compared to single-turn dialogue, multi-turn dialogue involving multiple images better aligns with the needs of real-world human-AI interactions. Additionally, as training data, it provides richer contextual reasoning information, thereby guiding the model to achieve better performance. However, existing vision-language models (VLMs) primarily rely on single-turn dialogue training and evaluation benchmarks. In this paper, following the characteristics of human dialogue, such as focused topics and concise, clear content, we present MMCR (Multimodal Multi-turn Contextual Reasoning), a novel data"},"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":"2503.18533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-24T10:40:33Z","cross_cats_sorted":[],"title_canon_sha256":"a1db4b9bcd10299b54321d4391cd42d8cd7e3d0f429c81859bdb4908705f3813","abstract_canon_sha256":"0f4d655965787d559516686fb693362628add7889d639d71a85dca1543b85405"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:12.511568Z","signature_b64":"2JmOBnQM6xg0eOPy//MzdaUKcdFxGDoUJcNBIBuFdyvWWjeKinL3adwcydXFKaGK3fdToPg7TETd5yuEzxKwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9337bc8aa1bbe938bfe02f8725a5c389162bbbead4eb325258292b35afe53a2","last_reissued_at":"2026-07-05T10:38:12.511062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:12.511062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunhua Shen, Dawei Yan, Haokui Zhang, Peng Wang, Qing-Guo Chen, Weihua Luo, Yang Li","submitted_at":"2025-03-24T10:40:33Z","abstract_excerpt":"Compared to single-turn dialogue, multi-turn dialogue involving multiple images better aligns with the needs of real-world human-AI interactions. Additionally, as training data, it provides richer contextual reasoning information, thereby guiding the model to achieve better performance. However, existing vision-language models (VLMs) primarily rely on single-turn dialogue training and evaluation benchmarks. In this paper, following the characteristics of human dialogue, such as focused topics and concise, clear content, we present MMCR (Multimodal Multi-turn Contextual Reasoning), a novel data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18533","kind":"arxiv","version":1},"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/2503.18533/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":"2503.18533","created_at":"2026-07-05T10:38:12.511123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18533v1","created_at":"2026-07-05T10:38:12.511123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18533","created_at":"2026-07-05T10:38:12.511123+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEZXXSFKDO7J","created_at":"2026-07-05T10:38:12.511123+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEZXXSFKDO7JHC76","created_at":"2026-07-05T10:38:12.511123+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEZXXSFK","created_at":"2026-07-05T10:38:12.511123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00465","citing_title":"StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16301","citing_title":"MANTA: Multi-turn Assessment for Nonhuman Thinking & Alignment","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05557","citing_title":"EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEZXXSFKDO7JHC76AL4HEWS4HC","json":"https://pith.science/pith/VEZXXSFKDO7JHC76AL4HEWS4HC.json","graph_json":"https://pith.science/api/pith-number/VEZXXSFKDO7JHC76AL4HEWS4HC/graph.json","events_json":"https://pith.science/api/pith-number/VEZXXSFKDO7JHC76AL4HEWS4HC/events.json","paper":"https://pith.science/paper/VEZXXSFK"},"agent_actions":{"view_html":"https://pith.science/pith/VEZXXSFKDO7JHC76AL4HEWS4HC","download_json":"https://pith.science/pith/VEZXXSFKDO7JHC76AL4HEWS4HC.json","view_paper":"https://pith.science/paper/VEZXXSFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18533&json=true","fetch_graph":"https://pith.science/api/pith-number/VEZXXSFKDO7JHC76AL4HEWS4HC/graph.json","fetch_events":"https://pith.science/api/pith-number/VEZXXSFKDO7JHC76AL4HEWS4HC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEZXXSFKDO7JHC76AL4HEWS4HC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEZXXSFKDO7JHC76AL4HEWS4HC/action/storage_attestation","attest_author":"https://pith.science/pith/VEZXXSFKDO7JHC76AL4HEWS4HC/action/author_attestation","sign_citation":"https://pith.science/pith/VEZXXSFKDO7JHC76AL4HEWS4HC/action/citation_signature","submit_replication":"https://pith.science/pith/VEZXXSFKDO7JHC76AL4HEWS4HC/action/replication_record"}},"created_at":"2026-07-05T10:38:12.511123+00:00","updated_at":"2026-07-05T10:38:12.511123+00:00"}