{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XY4CFBT5TASC2RY7TNK4FFXNWZ","short_pith_number":"pith:XY4CFBT5","schema_version":"1.0","canonical_sha256":"be3822867d98242d471f9b55c296edb64950f7a736c9f529a45705ef5da6474c","source":{"kind":"arxiv","id":"2606.05749","version":1},"attestation_state":"computed","paper":{"title":"MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongtao Liu, Jian Yang, Kaifeng Chen, Qing Yang, Qiyao Peng, Xiaochen Zhang, Yongqiang Liu","submitted_at":"2026-06-04T06:23:01Z","abstract_excerpt":"Iterative retrieval-reasoning agents have recently shown promise for multimodal long-document question answering. However, most existing systems maintain a single growing context that mixes retrieval traces, observations, and intermediate reasoning. As interactions accumulate, key evidence becomes scattered and diluted, making multi-hop reasoning noisy. We propose MARDoc, a Memory-Aware Refinement Agent framework that decouples long-document QA into three specialized agents: an Explorer for multi-granularity multimodal retrieval, a Refiner for distilling interaction traces into structured evid"},"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":"2606.05749","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T06:23:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"15b6dad68a9c70c94d6c58973db23f6acf565e2192a22e36a11ee312b9076ad2","abstract_canon_sha256":"c5ebf63cc30381718ccd5edc52beb03a42c70aa63809cdc21fda4fce7f5c3537"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:01.632968Z","signature_b64":"cKWTRZYoHV6rbn0wnd6efXYdFYx3kczyNK79kcn48qd+VPewWJNmieJ0iWXIx740/R8iA4Dci1aVAxTTzlMPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be3822867d98242d471f9b55c296edb64950f7a736c9f529a45705ef5da6474c","last_reissued_at":"2026-06-05T01:15:01.632420Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:01.632420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongtao Liu, Jian Yang, Kaifeng Chen, Qing Yang, Qiyao Peng, Xiaochen Zhang, Yongqiang Liu","submitted_at":"2026-06-04T06:23:01Z","abstract_excerpt":"Iterative retrieval-reasoning agents have recently shown promise for multimodal long-document question answering. However, most existing systems maintain a single growing context that mixes retrieval traces, observations, and intermediate reasoning. As interactions accumulate, key evidence becomes scattered and diluted, making multi-hop reasoning noisy. We propose MARDoc, a Memory-Aware Refinement Agent framework that decouples long-document QA into three specialized agents: an Explorer for multi-granularity multimodal retrieval, a Refiner for distilling interaction traces into structured evid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05749","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/2606.05749/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":"2606.05749","created_at":"2026-06-05T01:15:01.632532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05749v1","created_at":"2026-06-05T01:15:01.632532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05749","created_at":"2026-06-05T01:15:01.632532+00:00"},{"alias_kind":"pith_short_12","alias_value":"XY4CFBT5TASC","created_at":"2026-06-05T01:15:01.632532+00:00"},{"alias_kind":"pith_short_16","alias_value":"XY4CFBT5TASC2RY7","created_at":"2026-06-05T01:15:01.632532+00:00"},{"alias_kind":"pith_short_8","alias_value":"XY4CFBT5","created_at":"2026-06-05T01:15:01.632532+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/XY4CFBT5TASC2RY7TNK4FFXNWZ","json":"https://pith.science/pith/XY4CFBT5TASC2RY7TNK4FFXNWZ.json","graph_json":"https://pith.science/api/pith-number/XY4CFBT5TASC2RY7TNK4FFXNWZ/graph.json","events_json":"https://pith.science/api/pith-number/XY4CFBT5TASC2RY7TNK4FFXNWZ/events.json","paper":"https://pith.science/paper/XY4CFBT5"},"agent_actions":{"view_html":"https://pith.science/pith/XY4CFBT5TASC2RY7TNK4FFXNWZ","download_json":"https://pith.science/pith/XY4CFBT5TASC2RY7TNK4FFXNWZ.json","view_paper":"https://pith.science/paper/XY4CFBT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05749&json=true","fetch_graph":"https://pith.science/api/pith-number/XY4CFBT5TASC2RY7TNK4FFXNWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XY4CFBT5TASC2RY7TNK4FFXNWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XY4CFBT5TASC2RY7TNK4FFXNWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XY4CFBT5TASC2RY7TNK4FFXNWZ/action/storage_attestation","attest_author":"https://pith.science/pith/XY4CFBT5TASC2RY7TNK4FFXNWZ/action/author_attestation","sign_citation":"https://pith.science/pith/XY4CFBT5TASC2RY7TNK4FFXNWZ/action/citation_signature","submit_replication":"https://pith.science/pith/XY4CFBT5TASC2RY7TNK4FFXNWZ/action/replication_record"}},"created_at":"2026-06-05T01:15:01.632532+00:00","updated_at":"2026-06-05T01:15:01.632532+00:00"}