{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UDMJCIN4Z722GCME7ZEGYXWLZY","short_pith_number":"pith:UDMJCIN4","schema_version":"1.0","canonical_sha256":"a0d89121bccff5a30984fe486c5ecbce2be3b774d8a1e49aef975b6a40944abb","source":{"kind":"arxiv","id":"2509.05669","version":1},"attestation_state":"computed","paper":{"title":"Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Apiradee Boonmee, Weijie Shen, Xinrui Wang, Yuanqi Nie","submitted_at":"2025-09-06T10:14:49Z","abstract_excerpt":"Current Large Language Models (LLMs) and Vision-Language Large Models (LVLMs) excel in single-turn tasks but face significant challenges in multi-turn interactions requiring deep contextual understanding and complex visual reasoning, often leading to fragmented reasoning, context loss, and hallucinations. To address these limitations, we propose Context-Aware Multi-Turn Visual Reasoning (CAMVR), a novel framework designed to empower LVLMs with robust and coherent multi-turn visual-textual inference capabilities. CAMVR introduces two key innovations: a Visual-Textual Context Memory Unit (VCMU),"},"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":"2509.05669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-06T10:14:49Z","cross_cats_sorted":[],"title_canon_sha256":"13b2070e555fd1746b0a0bf87b750b2e90c2909b4b672cd5c3b0bca72a6cb116","abstract_canon_sha256":"024bfdd8c0c0b5f64aef0699fbd09504402cb9bff70f24bf753b9aacf14c1576"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:22.129288Z","signature_b64":"j9qdI/ViGIpoyuYtc7eIPmRaUH8/t2ECuC15kd/bDofQYB9o0sIl2CSvM3zN+Rpa+CflH+wvdghWD2UbO8WLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0d89121bccff5a30984fe486c5ecbce2be3b774d8a1e49aef975b6a40944abb","last_reissued_at":"2026-07-05T12:06:22.128818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:22.128818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Apiradee Boonmee, Weijie Shen, Xinrui Wang, Yuanqi Nie","submitted_at":"2025-09-06T10:14:49Z","abstract_excerpt":"Current Large Language Models (LLMs) and Vision-Language Large Models (LVLMs) excel in single-turn tasks but face significant challenges in multi-turn interactions requiring deep contextual understanding and complex visual reasoning, often leading to fragmented reasoning, context loss, and hallucinations. To address these limitations, we propose Context-Aware Multi-Turn Visual Reasoning (CAMVR), a novel framework designed to empower LVLMs with robust and coherent multi-turn visual-textual inference capabilities. CAMVR introduces two key innovations: a Visual-Textual Context Memory Unit (VCMU),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05669","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/2509.05669/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":"2509.05669","created_at":"2026-07-05T12:06:22.128869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05669v1","created_at":"2026-07-05T12:06:22.128869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05669","created_at":"2026-07-05T12:06:22.128869+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDMJCIN4Z722","created_at":"2026-07-05T12:06:22.128869+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDMJCIN4Z722GCME","created_at":"2026-07-05T12:06:22.128869+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDMJCIN4","created_at":"2026-07-05T12:06:22.128869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00814","citing_title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00814","citing_title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDMJCIN4Z722GCME7ZEGYXWLZY","json":"https://pith.science/pith/UDMJCIN4Z722GCME7ZEGYXWLZY.json","graph_json":"https://pith.science/api/pith-number/UDMJCIN4Z722GCME7ZEGYXWLZY/graph.json","events_json":"https://pith.science/api/pith-number/UDMJCIN4Z722GCME7ZEGYXWLZY/events.json","paper":"https://pith.science/paper/UDMJCIN4"},"agent_actions":{"view_html":"https://pith.science/pith/UDMJCIN4Z722GCME7ZEGYXWLZY","download_json":"https://pith.science/pith/UDMJCIN4Z722GCME7ZEGYXWLZY.json","view_paper":"https://pith.science/paper/UDMJCIN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05669&json=true","fetch_graph":"https://pith.science/api/pith-number/UDMJCIN4Z722GCME7ZEGYXWLZY/graph.json","fetch_events":"https://pith.science/api/pith-number/UDMJCIN4Z722GCME7ZEGYXWLZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDMJCIN4Z722GCME7ZEGYXWLZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDMJCIN4Z722GCME7ZEGYXWLZY/action/storage_attestation","attest_author":"https://pith.science/pith/UDMJCIN4Z722GCME7ZEGYXWLZY/action/author_attestation","sign_citation":"https://pith.science/pith/UDMJCIN4Z722GCME7ZEGYXWLZY/action/citation_signature","submit_replication":"https://pith.science/pith/UDMJCIN4Z722GCME7ZEGYXWLZY/action/replication_record"}},"created_at":"2026-07-05T12:06:22.128869+00:00","updated_at":"2026-07-05T12:06:22.128869+00:00"}