{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QTPDFMRPCKMGFYFNXU5FSFY6HK","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":"bf589129b3d9f427829b88b2316d8ab6e033798fa995b8c475b22a77dc087210","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T13:16:02Z","title_canon_sha256":"17e55404d64f95b54ecdbf5a04a89c3d060eb1b92171edeaefa09953a87b85b9"},"schema_version":"1.0","source":{"id":"2606.01223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01223","created_at":"2026-06-02T02:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01223v1","created_at":"2026-06-02T02:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01223","created_at":"2026-06-02T02:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"QTPDFMRPCKMG","created_at":"2026-06-02T02:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"QTPDFMRPCKMGFYFN","created_at":"2026-06-02T02:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"QTPDFMRP","created_at":"2026-06-02T02:04:27Z"}],"graph_snapshots":[{"event_id":"sha256:d76eee6f91cfbb05da9629c0f75c59c3abe60797391ab87c680e7c0b256ead10","target":"graph","created_at":"2026-06-02T02:04:27Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.01223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bingbing Wang, Jingjie Lin, Jing Li, Ruifeng Xu, Weiming Qiao, Zhengda Jin, Zihan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T13:16:02Z","title":"Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01223","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55108f1abf09f2d008c5caaec426539e168c8723178c84c0f00776ed9e93059c","target":"record","created_at":"2026-06-02T02:04:27Z","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":"bf589129b3d9f427829b88b2316d8ab6e033798fa995b8c475b22a77dc087210","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T13:16:02Z","title_canon_sha256":"17e55404d64f95b54ecdbf5a04a89c3d060eb1b92171edeaefa09953a87b85b9"},"schema_version":"1.0","source":{"id":"2606.01223","kind":"arxiv","version":1}},"canonical_sha256":"84de32b22f129862e0adbd3a59171e3ab1ef317adb318cf7f18ed6b1b02a753a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84de32b22f129862e0adbd3a59171e3ab1ef317adb318cf7f18ed6b1b02a753a","first_computed_at":"2026-06-02T02:04:27.205284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:27.205284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bPYy65MJRlYDo/Fwup93JWsve3CN99cPaNg0ziMK+iOLHvvk9OjfPW8akVfTo74wOF3yS/9yQjx1gdgI+DnABA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:27.205704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55108f1abf09f2d008c5caaec426539e168c8723178c84c0f00776ed9e93059c","sha256:d76eee6f91cfbb05da9629c0f75c59c3abe60797391ab87c680e7c0b256ead10"],"state_sha256":"65c2046e808326475fa73e6a684824808de62d330d1b2f63ff230ee0d1c45e0a"}