{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VEZXXSFKDO7JHC76AL4HEWS4HC","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":"0f4d655965787d559516686fb693362628add7889d639d71a85dca1543b85405","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-24T10:40:33Z","title_canon_sha256":"a1db4b9bcd10299b54321d4391cd42d8cd7e3d0f429c81859bdb4908705f3813"},"schema_version":"1.0","source":{"id":"2503.18533","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18533","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18533v1","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18533","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"pith_short_12","alias_value":"VEZXXSFKDO7J","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"pith_short_16","alias_value":"VEZXXSFKDO7JHC76","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"pith_short_8","alias_value":"VEZXXSFK","created_at":"2026-07-05T10:38:12Z"}],"graph_snapshots":[{"event_id":"sha256:08fabd777cb27dc95461e6edc4f44d08a80a86301b81ea9505fa0fe60536a9cc","target":"graph","created_at":"2026-07-05T10:38:12Z","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/2503.18533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chunhua Shen, Dawei Yan, Haokui Zhang, Peng Wang, Qing-Guo Chen, Weihua Luo, Yang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-24T10:40:33Z","title":"MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18533","kind":"arxiv","version":1},"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":"sha256:24e9471c927efa5177c8872945c2f3b6a10d51ff2b93af974ec94bbd162a9684","target":"record","created_at":"2026-07-05T10:38:12Z","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":"0f4d655965787d559516686fb693362628add7889d639d71a85dca1543b85405","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-24T10:40:33Z","title_canon_sha256":"a1db4b9bcd10299b54321d4391cd42d8cd7e3d0f429c81859bdb4908705f3813"},"schema_version":"1.0","source":{"id":"2503.18533","kind":"arxiv","version":1}},"canonical_sha256":"a9337bc8aa1bbe938bfe02f8725a5c389162bbbead4eb325258292b35afe53a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9337bc8aa1bbe938bfe02f8725a5c389162bbbead4eb325258292b35afe53a2","first_computed_at":"2026-07-05T10:38:12.511062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:12.511062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2JmOBnQM6xg0eOPy//MzdaUKcdFxGDoUJcNBIBuFdyvWWjeKinL3adwcydXFKaGK3fdToPg7TETd5yuEzxKwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:12.511568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.18533","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24e9471c927efa5177c8872945c2f3b6a10d51ff2b93af974ec94bbd162a9684","sha256:08fabd777cb27dc95461e6edc4f44d08a80a86301b81ea9505fa0fe60536a9cc"],"state_sha256":"56b1ab241a1ca08404640491dc240f9401f228f207eb3f43d582407098b92a2c"}