{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W6LXFWZSBPEO3LDGK5XPVYJ4X7","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":"4d33836d1f2a2d1df2195fdccc19c2e56b95e489c85cd597d7aff64c807acc91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-02T11:20:34Z","title_canon_sha256":"4086ccdd6cb62d12a8ec69483f72670afecedc9404b1dac9161e22f6eaf9f6fc"},"schema_version":"1.0","source":{"id":"2605.01386","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01386","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01386v2","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01386","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"W6LXFWZSBPEO","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"W6LXFWZSBPEO3LDG","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"W6LXFWZS","created_at":"2026-06-03T01:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:cd9531b3f4305e84275dacdd5a17762b9f01cc5685ba2d3e616d9a6c7773566c","target":"graph","created_at":"2026-06-03T01:05:14Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Evaluated on LOCOMO and LongMemEval benchmarks, MemORAI achieves state-of-the-art performance in memory retrieval and personalized response generation, demonstrating that selective storage, enriched representation, and adaptive retrieval are essential for coherent, personalized LLM agents."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the three proposed components (dual-layer compression with selective filtering, turn-level provenance in the multi-relational graph, and query-conditioned edge weighting in Dynamic Weighted PageRank) will reliably solve information dilution and uniform retrieval problems without introducing new overhead or retrieval biases that could degrade performance on unseen conversation styles or domains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MemORAI combines selective filtering, provenance tracking in multi-relational graphs, and dynamic weighted PageRank retrieval to achieve state-of-the-art memory retrieval and personalized responses in LLM agents on LOCOMO and LongMemEval benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MemORAI equips LLMs with selective memory filtering, provenance tracking, and adaptive retrieval to enable coherent long-term personalized conversations."}],"snapshot_sha256":"1d644e17ddae88d7996e7a4ca3d40ea03677feefd30e038fe917ca66de4676f9"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T18:34:19.197971Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T17:18:50.790739Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.01386/integrity.json","findings":[],"snapshot_sha256":"3dde0c0ee762b74f0fe509ef200366e8c152a2b5aa8167d2211de06ce2429497","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from information dilution, absent provenance tracking, and uniform retrieval that ignores query context. We introduce MemORAI (Memory Organization and Retrieval via Adaptive Graph Intelligence), a framework that integrates three innovations: selective memory filtering with dual-layer compression to retain user-persona-relevant content, a provenance-enriched multi-relational graph tracking factual origins at the turn level, and query-adaptive subgraph retrieva","authors_text":"Hung Pham Van, Khang Pham Tran Tuan, Linh Ngo Van, Nam Le Hai, Nguyen Manh Hieu, Nguyen Thi Ngoc Diep, Trung Le","cross_cats":[],"headline":"MemORAI equips LLMs with selective memory filtering, provenance tracking, and adaptive retrieval to enable coherent long-term personalized conversations.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-02T11:20:34Z","title":"MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.01386","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T14:41:09.671302Z","id":"1e9bff85-7869-4b8b-9b0f-5da8d17ee017","model_set":{"reader":"grok-4.3"},"one_line_summary":"MemORAI combines selective filtering, provenance tracking in multi-relational graphs, and dynamic weighted PageRank retrieval to achieve state-of-the-art memory retrieval and personalized responses in LLM agents on LOCOMO and LongMemEval benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MemORAI equips LLMs with selective memory filtering, provenance tracking, and adaptive retrieval to enable coherent long-term personalized conversations.","strongest_claim":"Evaluated on LOCOMO and LongMemEval benchmarks, MemORAI achieves state-of-the-art performance in memory retrieval and personalized response generation, demonstrating that selective storage, enriched representation, and adaptive retrieval are essential for coherent, personalized LLM agents.","weakest_assumption":"The assumption that the three proposed components (dual-layer compression with selective filtering, turn-level provenance in the multi-relational graph, and query-conditioned edge weighting in Dynamic Weighted PageRank) will reliably solve information dilution and uniform retrieval problems without introducing new overhead or retrieval biases that could degrade performance on unseen conversation styles or domains."}},"verdict_id":"1e9bff85-7869-4b8b-9b0f-5da8d17ee017"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:241be621d99ee37527c0690e04b956d85a4bd184ec60f5825814c5d6ef30caa4","target":"record","created_at":"2026-06-03T01:05:14Z","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":"4d33836d1f2a2d1df2195fdccc19c2e56b95e489c85cd597d7aff64c807acc91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-02T11:20:34Z","title_canon_sha256":"4086ccdd6cb62d12a8ec69483f72670afecedc9404b1dac9161e22f6eaf9f6fc"},"schema_version":"1.0","source":{"id":"2605.01386","kind":"arxiv","version":2}},"canonical_sha256":"b79772db320bc8edac66576efae13cbfd1f050446c828b9e30319a0783b7dee7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b79772db320bc8edac66576efae13cbfd1f050446c828b9e30319a0783b7dee7","first_computed_at":"2026-06-03T01:05:14.332464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:14.332464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ohMgkDS/dE1Xy9i8Pw3vJ8kYuVuUSZT7gBFKnNZmtZN7F2UybuObB0PzrriQUgpzthrnoyGy9wNEbr77AncmAQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:14.332872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.01386","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:241be621d99ee37527c0690e04b956d85a4bd184ec60f5825814c5d6ef30caa4","sha256:cd9531b3f4305e84275dacdd5a17762b9f01cc5685ba2d3e616d9a6c7773566c"],"state_sha256":"724f9cbae2c9ba2162dee5541d7ec4cb6a13e2c80d012c3e4de6a666c8f3fc2d"}