{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KFUVCQD4T5A2X6AU4U6PLICPVF","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":"7a87e9db5e0038ff315f516a2451f634741e4c35ce8eed238036704e227f760b","cross_cats_sorted":["cs.IR","cs.MA"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-29T23:33:38Z","title_canon_sha256":"4a7bc3656528399f40d0b72e65405a660ea43955f81a482b1eae6781af50425b"},"schema_version":"1.0","source":{"id":"2603.27910","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.27910","created_at":"2026-05-18T02:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"2603.27910v2","created_at":"2026-05-18T02:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27910","created_at":"2026-05-18T02:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"KFUVCQD4T5A2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KFUVCQD4T5A2X6AU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KFUVCQD4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:468844762d2b13bdcf8c59a1d23890bb913f2a8f8fec53e805b167f8b093a047","target":"graph","created_at":"2026-05-18T02:44:30Z","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":"On LoCoMo-10 (1,540 questions, 10 multi-session conversations), GAAMA achieves 79.1% mean reward, a +4.2 pp improvement over a tuned RAG baseline, the strongest comparator. On MemoryArena, GAAMA outperforms full-context baselines across three tasks with advantages growing monotonically with dialogue length."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The LLM-based extraction of atomic facts and topic-level concept nodes, together with the synthesis of higher-order reflections, accurately preserves structural relationships and avoids introducing errors that would degrade retrieval quality."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GAAMA constructs a four-node-type knowledge graph with concept-mediated edges and Personalized PageRank retrieval to improve multi-session agent memory, reporting 79.1% mean reward on LoCoMo-10 (+4.2 pp over tuned RAG) and gains on MemoryArena tasks that grow with dialogue length."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GAAMA builds a concept-mediated knowledge graph to improve memory retrieval for AI agents across multi-session conversations."}],"snapshot_sha256":"ed2cf21661f166bb9ef33f2e95666a544138f023be098b992ed47951423294b5"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"8f4e7ec69ecc6e9d92bdae211d3d6299bc4727e98aae8c020c1ef1e6da55f6bc"},"paper":{"abstract_excerpt":"AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current approaches either rely on flat retrieval-augmented generation (RAG), which loses structural relationships among memories, or use entity-centric knowledge graphs that suffer from mega-hub effects in conversational data, diluting graph-based relevance propagation. We propose GAAMA, a graph-augmented associative memory for agents that constructs a concept-mediated knowledge graph through a three-step pipeline: (1)verbatim episode preservation, (2)LLM","authors_text":"Nitin Sareen, Shubhendu Sharma, Swarna Kamal Paul","cross_cats":["cs.IR","cs.MA"],"headline":"GAAMA builds a concept-mediated knowledge graph to improve memory retrieval for AI agents across multi-session conversations.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-29T23:33:38Z","title":"GAAMA: Graph Augmented Associative Memory for Agents"},"references":{"count":18,"internal_anchors":0,"resolved_work":18,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"User’s birthday is March 15, 1990","work_id":"d34d6a0c-e7d9-404f-86f2-1b2e08599e7e","year":1990},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"**Do NOT duplicate existing facts.** If an existing fact already captures the information, skip it","work_id":"ac3a60e3-57cf-47e6-8902-6c8116edf459","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"**Resolve relative dates to absolute dates** using the conversation timestamp. For example, if the conversation date is \"2023-06-15\" and the user says \"last week\", resolve to approximately \"2023-06-08","work_id":"94176a33-6f0e-46d5-a8aa-5c19cd43f5ac","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Derive general knowledge from episodes by doing multi-step reasoning where possible","work_id":"bc599878-56e6-4c5f-bb0e-eee6ea174fd8","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Only extract general knowledge, preferences, attributes, or relationships that can be applied broadly","work_id":"95439836-326d-4358-af3d-bbdb7b121a72","year":null}],"snapshot_sha256":"022c26f9294501f88cb1b4555bcf515c63557b3f425746e11972461a05162c1c"},"source":{"id":"2603.27910","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-14T21:05:32.860871Z","id":"3ae038c2-cef8-4ef9-858e-77f11a442878","model_set":{"reader":"grok-4.3"},"one_line_summary":"GAAMA constructs a four-node-type knowledge graph with concept-mediated edges and Personalized PageRank retrieval to improve multi-session agent memory, reporting 79.1% mean reward on LoCoMo-10 (+4.2 pp over tuned RAG) and gains on MemoryArena tasks that grow with dialogue length.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GAAMA builds a concept-mediated knowledge graph to improve memory retrieval for AI agents across multi-session conversations.","strongest_claim":"On LoCoMo-10 (1,540 questions, 10 multi-session conversations), GAAMA achieves 79.1% mean reward, a +4.2 pp improvement over a tuned RAG baseline, the strongest comparator. On MemoryArena, GAAMA outperforms full-context baselines across three tasks with advantages growing monotonically with dialogue length.","weakest_assumption":"The LLM-based extraction of atomic facts and topic-level concept nodes, together with the synthesis of higher-order reflections, accurately preserves structural relationships and avoids introducing errors that would degrade retrieval quality."}},"verdict_id":"3ae038c2-cef8-4ef9-858e-77f11a442878"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55256d7fe4b5de77ba9dd5b6e725b96900c14bd7011f17f6f8e5c9fbf4417c78","target":"record","created_at":"2026-05-18T02:44:30Z","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":"7a87e9db5e0038ff315f516a2451f634741e4c35ce8eed238036704e227f760b","cross_cats_sorted":["cs.IR","cs.MA"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-29T23:33:38Z","title_canon_sha256":"4a7bc3656528399f40d0b72e65405a660ea43955f81a482b1eae6781af50425b"},"schema_version":"1.0","source":{"id":"2603.27910","kind":"arxiv","version":2}},"canonical_sha256":"516951407c9f41abf814e53cf5a04fa95947a9b17daa696ac557231819815809","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"516951407c9f41abf814e53cf5a04fa95947a9b17daa696ac557231819815809","first_computed_at":"2026-05-18T02:44:30.605980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:30.605980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SsikiwaptQjo8fsAuPT3Uc1v42Vjqhyy8syCz/MAV2/lHrtrl9dWvD2W+bAzLiJRlkciySt+ucQPE38JREb9DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:30.606585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.27910","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55256d7fe4b5de77ba9dd5b6e725b96900c14bd7011f17f6f8e5c9fbf4417c78","sha256:468844762d2b13bdcf8c59a1d23890bb913f2a8f8fec53e805b167f8b093a047"],"state_sha256":"25eb51d5df3a497e565cfe2d1b8a0b8266dc2423f6f373a2d49e8d492d3aa59f"}