{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MTYMJ57F2X4GLXD7IMNMC4YWHL","short_pith_number":"pith:MTYMJ57F","schema_version":"1.0","canonical_sha256":"64f0c4f7e5d5f865dc7f431ac173163ac912f75ef506edd9fb5327c1641525b3","source":{"kind":"arxiv","id":"2605.30087","version":1},"attestation_state":"computed","paper":{"title":"Selective QA over Conflicting Multi-Source Personal Memory: A Diagnostic Testbed and Method Comparison","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ilia Sucholutsky, Matthias Schonlau, Tiancheng Yang","submitted_at":"2026-05-28T15:33:39Z","abstract_excerpt":"Emerging personal AI agents are moving toward persistent, multi-source memory. This creates an evaluation problem: systems must decide how to use conflicting or incomplete evidence; they cannot just retrieve facts from one clean history. Existing benchmarks rarely show whether an error came from the evidence given to a method or from the method's conflict-resolution step. We study this as selective QA over conflicting multi-source personal memory: systems answer based on conflicting, sometimes incomplete sources, or abstain when evidence is insufficient. We develop a benchmark containing 18 qu"},"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":"2605.30087","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T15:33:39Z","cross_cats_sorted":[],"title_canon_sha256":"2872edee6a9ab8942ebbc7ee28a784c5eb1d73b41bf8f871ef6ff6c2673a78c6","abstract_canon_sha256":"466ceadfcb0984626a1156090ce66eb1b59864f7ed2b9b58157180a25506ce3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:09.598965Z","signature_b64":"UCVwucOxO/1YmbHq4uU5yal+HlSgZD3k9ym8MkoQ+OIg+YU12wsVy7jVXBN//AiPGFXjrv6vaWhqzDHy7hdPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64f0c4f7e5d5f865dc7f431ac173163ac912f75ef506edd9fb5327c1641525b3","last_reissued_at":"2026-05-29T02:06:09.598637Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:09.598637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selective QA over Conflicting Multi-Source Personal Memory: A Diagnostic Testbed and Method Comparison","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ilia Sucholutsky, Matthias Schonlau, Tiancheng Yang","submitted_at":"2026-05-28T15:33:39Z","abstract_excerpt":"Emerging personal AI agents are moving toward persistent, multi-source memory. This creates an evaluation problem: systems must decide how to use conflicting or incomplete evidence; they cannot just retrieve facts from one clean history. Existing benchmarks rarely show whether an error came from the evidence given to a method or from the method's conflict-resolution step. We study this as selective QA over conflicting multi-source personal memory: systems answer based on conflicting, sometimes incomplete sources, or abstain when evidence is insufficient. We develop a benchmark containing 18 qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30087","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/2605.30087/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":"2605.30087","created_at":"2026-05-29T02:06:09.598691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30087v1","created_at":"2026-05-29T02:06:09.598691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30087","created_at":"2026-05-29T02:06:09.598691+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTYMJ57F2X4G","created_at":"2026-05-29T02:06:09.598691+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTYMJ57F2X4GLXD7","created_at":"2026-05-29T02:06:09.598691+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTYMJ57F","created_at":"2026-05-29T02:06:09.598691+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/MTYMJ57F2X4GLXD7IMNMC4YWHL","json":"https://pith.science/pith/MTYMJ57F2X4GLXD7IMNMC4YWHL.json","graph_json":"https://pith.science/api/pith-number/MTYMJ57F2X4GLXD7IMNMC4YWHL/graph.json","events_json":"https://pith.science/api/pith-number/MTYMJ57F2X4GLXD7IMNMC4YWHL/events.json","paper":"https://pith.science/paper/MTYMJ57F"},"agent_actions":{"view_html":"https://pith.science/pith/MTYMJ57F2X4GLXD7IMNMC4YWHL","download_json":"https://pith.science/pith/MTYMJ57F2X4GLXD7IMNMC4YWHL.json","view_paper":"https://pith.science/paper/MTYMJ57F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30087&json=true","fetch_graph":"https://pith.science/api/pith-number/MTYMJ57F2X4GLXD7IMNMC4YWHL/graph.json","fetch_events":"https://pith.science/api/pith-number/MTYMJ57F2X4GLXD7IMNMC4YWHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTYMJ57F2X4GLXD7IMNMC4YWHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTYMJ57F2X4GLXD7IMNMC4YWHL/action/storage_attestation","attest_author":"https://pith.science/pith/MTYMJ57F2X4GLXD7IMNMC4YWHL/action/author_attestation","sign_citation":"https://pith.science/pith/MTYMJ57F2X4GLXD7IMNMC4YWHL/action/citation_signature","submit_replication":"https://pith.science/pith/MTYMJ57F2X4GLXD7IMNMC4YWHL/action/replication_record"}},"created_at":"2026-05-29T02:06:09.598691+00:00","updated_at":"2026-05-29T02:06:09.598691+00:00"}