{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RTQGP7BP4LMGQEVOYJLLX5NVJT","short_pith_number":"pith:RTQGP7BP","schema_version":"1.0","canonical_sha256":"8ce067fc2fe2d86812aec256bbf5b54ceb75bb201f921243cb2addeb7842f823","source":{"kind":"arxiv","id":"2601.05488","version":4},"attestation_state":"computed","paper":{"title":"MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MemBuilder trains a 4B model with dense rewards to outperform closed-source LLMs on long-term dialogue memory.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fuming Lai, Shaobing Lian, Yanghui Rao, Zhiyu Shen, Ziming Wu","submitted_at":"2026-01-09T02:44:37Z","abstract_excerpt":"Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical states. While memory-augmented frameworks offer a structured alternative, current systems rely on static prompting of closed-source models or suffer from ineffective training paradigms with sparse rewards. We introduce MemBuilder, a reinforcement learning framework that trains models to orchestrate multi-dimensional memory construction with attributed dense rewards. MemBuilder addresses two key challenges: (1) Spars"},"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":true},"canonical_record":{"source":{"id":"2601.05488","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T02:44:37Z","cross_cats_sorted":[],"title_canon_sha256":"c178304caa6aaa1b902a468ea4ee41cc68c2669cb31e2b34459160bab673c3cb","abstract_canon_sha256":"e5a186dec8385e48b46cebc9616f85230615985ba34d607dc23fbbfe0d0e4a56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:19.896643Z","signature_b64":"UfgWRVT80O/mZchGVuw4OL+x33hVowqaW9lWWS6wLQsoDkBejU0utmSQ6nb/HJSV5qiCIjmUyHiWzrq37EfRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ce067fc2fe2d86812aec256bbf5b54ceb75bb201f921243cb2addeb7842f823","last_reissued_at":"2026-06-23T02:13:19.896189Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:19.896189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MemBuilder trains a 4B model with dense rewards to outperform closed-source LLMs on long-term dialogue memory.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fuming Lai, Shaobing Lian, Yanghui Rao, Zhiyu Shen, Ziming Wu","submitted_at":"2026-01-09T02:44:37Z","abstract_excerpt":"Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical states. While memory-augmented frameworks offer a structured alternative, current systems rely on static prompting of closed-source models or suffer from ineffective training paradigms with sparse rewards. We introduce MemBuilder, a reinforcement learning framework that trains models to orchestrate multi-dimensional memory construction with attributed dense rewards. MemBuilder addresses two key challenges: (1) Spars"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results show that MemBuilder enables a 4B-parameter model to outperform state-of-the-art closed-source baselines, exhibiting strong generalization across long-term dialogue benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That synthetic session-level question generation produces unbiased, representative dense rewards that accurately measure and improve real-world memory construction quality without introducing artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MemBuilder trains 4B-parameter models with attributed dense rewards to outperform closed-source baselines on long-term dialogue memory tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MemBuilder trains a 4B model with dense rewards to outperform closed-source LLMs on long-term dialogue memory.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ccfbef3e30dbb23547d333e01a49c691f8be3498c592a377ffa851f87fa0fcca"},"source":{"id":"2601.05488","kind":"arxiv","version":4},"verdict":{"id":"0838669c-3178-4531-b8bf-c0848244cc2f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T16:53:01.591957Z","strongest_claim":"Experimental results show that MemBuilder enables a 4B-parameter model to outperform state-of-the-art closed-source baselines, exhibiting strong generalization across long-term dialogue benchmarks.","one_line_summary":"MemBuilder trains 4B-parameter models with attributed dense rewards to outperform closed-source baselines on long-term dialogue memory tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That synthetic session-level question generation produces unbiased, representative dense rewards that accurately measure and improve real-world memory construction quality without introducing artifacts.","pith_extraction_headline":"MemBuilder trains a 4B model with dense rewards to outperform closed-source LLMs on long-term dialogue memory."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.05488/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":2,"snapshot_sha256":"05d0f612b60166ebd6c38efa8142ad949ea10fca898c3dcf954e947f08f7fc1b"},"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":"2601.05488","created_at":"2026-06-23T02:13:19.896246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.05488v4","created_at":"2026-06-23T02:13:19.896246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05488","created_at":"2026-06-23T02:13:19.896246+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTQGP7BP4LMG","created_at":"2026-06-23T02:13:19.896246+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTQGP7BP4LMGQEVO","created_at":"2026-06-23T02:13:19.896246+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTQGP7BP","created_at":"2026-06-23T02:13:19.896246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTQGP7BP4LMGQEVOYJLLX5NVJT","json":"https://pith.science/pith/RTQGP7BP4LMGQEVOYJLLX5NVJT.json","graph_json":"https://pith.science/api/pith-number/RTQGP7BP4LMGQEVOYJLLX5NVJT/graph.json","events_json":"https://pith.science/api/pith-number/RTQGP7BP4LMGQEVOYJLLX5NVJT/events.json","paper":"https://pith.science/paper/RTQGP7BP"},"agent_actions":{"view_html":"https://pith.science/pith/RTQGP7BP4LMGQEVOYJLLX5NVJT","download_json":"https://pith.science/pith/RTQGP7BP4LMGQEVOYJLLX5NVJT.json","view_paper":"https://pith.science/paper/RTQGP7BP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.05488&json=true","fetch_graph":"https://pith.science/api/pith-number/RTQGP7BP4LMGQEVOYJLLX5NVJT/graph.json","fetch_events":"https://pith.science/api/pith-number/RTQGP7BP4LMGQEVOYJLLX5NVJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTQGP7BP4LMGQEVOYJLLX5NVJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTQGP7BP4LMGQEVOYJLLX5NVJT/action/storage_attestation","attest_author":"https://pith.science/pith/RTQGP7BP4LMGQEVOYJLLX5NVJT/action/author_attestation","sign_citation":"https://pith.science/pith/RTQGP7BP4LMGQEVOYJLLX5NVJT/action/citation_signature","submit_replication":"https://pith.science/pith/RTQGP7BP4LMGQEVOYJLLX5NVJT/action/replication_record"}},"created_at":"2026-06-23T02:13:19.896246+00:00","updated_at":"2026-06-23T02:13:19.896246+00:00"}