{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QTPDFMRPCKMGFYFNXU5FSFY6HK","short_pith_number":"pith:QTPDFMRP","schema_version":"1.0","canonical_sha256":"84de32b22f129862e0adbd3a59171e3ab1ef317adb318cf7f18ed6b1b02a753a","source":{"kind":"arxiv","id":"2606.01223","version":1},"attestation_state":"computed","paper":{"title":"Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bingbing Wang, Jingjie Lin, Jing Li, Ruifeng Xu, Weiming Qiao, Zhengda Jin, Zihan Wang","submitted_at":"2026-05-31T13:16:02Z","abstract_excerpt":"Despite substantial progress in long-context modeling, existing benchmarks remain confined to factual memory for explicit recall, failing to measure the reflective memory required to synthesize fragmented, multimodal cues into high-level interpretations. To address this gap, we introduce RefMem-Bench, a benchmark for reflective memory in long-horizon dialogue. RefMem-Bench contains 26K annotated QA instances with eight reflective-memory dimensions and three task formats, requiring models to move beyond surface-level retrieval and infer latent meanings from evidence distributed across interacti"},"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":"2606.01223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T13:16:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17e55404d64f95b54ecdbf5a04a89c3d060eb1b92171edeaefa09953a87b85b9","abstract_canon_sha256":"bf589129b3d9f427829b88b2316d8ab6e033798fa995b8c475b22a77dc087210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:27.205704Z","signature_b64":"bPYy65MJRlYDo/Fwup93JWsve3CN99cPaNg0ziMK+iOLHvvk9OjfPW8akVfTo74wOF3yS/9yQjx1gdgI+DnABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84de32b22f129862e0adbd3a59171e3ab1ef317adb318cf7f18ed6b1b02a753a","last_reissued_at":"2026-06-02T02:04:27.205284Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:27.205284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bingbing Wang, Jingjie Lin, Jing Li, Ruifeng Xu, Weiming Qiao, Zhengda Jin, Zihan Wang","submitted_at":"2026-05-31T13:16:02Z","abstract_excerpt":"Despite substantial progress in long-context modeling, existing benchmarks remain confined to factual memory for explicit recall, failing to measure the reflective memory required to synthesize fragmented, multimodal cues into high-level interpretations. To address this gap, we introduce RefMem-Bench, a benchmark for reflective memory in long-horizon dialogue. RefMem-Bench contains 26K annotated QA instances with eight reflective-memory dimensions and three task formats, requiring models to move beyond surface-level retrieval and infer latent meanings from evidence distributed across interacti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01223","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/2606.01223/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":"2606.01223","created_at":"2026-06-02T02:04:27.205356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01223v1","created_at":"2026-06-02T02:04:27.205356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01223","created_at":"2026-06-02T02:04:27.205356+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTPDFMRPCKMG","created_at":"2026-06-02T02:04:27.205356+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTPDFMRPCKMGFYFN","created_at":"2026-06-02T02:04:27.205356+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTPDFMRP","created_at":"2026-06-02T02:04:27.205356+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/QTPDFMRPCKMGFYFNXU5FSFY6HK","json":"https://pith.science/pith/QTPDFMRPCKMGFYFNXU5FSFY6HK.json","graph_json":"https://pith.science/api/pith-number/QTPDFMRPCKMGFYFNXU5FSFY6HK/graph.json","events_json":"https://pith.science/api/pith-number/QTPDFMRPCKMGFYFNXU5FSFY6HK/events.json","paper":"https://pith.science/paper/QTPDFMRP"},"agent_actions":{"view_html":"https://pith.science/pith/QTPDFMRPCKMGFYFNXU5FSFY6HK","download_json":"https://pith.science/pith/QTPDFMRPCKMGFYFNXU5FSFY6HK.json","view_paper":"https://pith.science/paper/QTPDFMRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01223&json=true","fetch_graph":"https://pith.science/api/pith-number/QTPDFMRPCKMGFYFNXU5FSFY6HK/graph.json","fetch_events":"https://pith.science/api/pith-number/QTPDFMRPCKMGFYFNXU5FSFY6HK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTPDFMRPCKMGFYFNXU5FSFY6HK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTPDFMRPCKMGFYFNXU5FSFY6HK/action/storage_attestation","attest_author":"https://pith.science/pith/QTPDFMRPCKMGFYFNXU5FSFY6HK/action/author_attestation","sign_citation":"https://pith.science/pith/QTPDFMRPCKMGFYFNXU5FSFY6HK/action/citation_signature","submit_replication":"https://pith.science/pith/QTPDFMRPCKMGFYFNXU5FSFY6HK/action/replication_record"}},"created_at":"2026-06-02T02:04:27.205356+00:00","updated_at":"2026-06-02T02:04:27.205356+00:00"}