{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:65ATZXBWA327K2M3RFEL4JPGUL","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":"cf25e90ae513e4455aa0d3806531899bb0b8d9b359b894074675304e9f843cd2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T15:09:58Z","title_canon_sha256":"7f74de42fec1b4460fcbd587eed006a2617bab1aad4aecc138364d7c6afc36ec"},"schema_version":"1.0","source":{"id":"2607.16848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16848","created_at":"2026-07-21T01:21:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16848v1","created_at":"2026-07-21T01:21:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16848","created_at":"2026-07-21T01:21:02Z"},{"alias_kind":"pith_short_12","alias_value":"65ATZXBWA327","created_at":"2026-07-21T01:21:02Z"},{"alias_kind":"pith_short_16","alias_value":"65ATZXBWA327K2M3","created_at":"2026-07-21T01:21:02Z"},{"alias_kind":"pith_short_8","alias_value":"65ATZXBW","created_at":"2026-07-21T01:21:02Z"}],"graph_snapshots":[{"event_id":"sha256:7c67e091dbf23de4f60210349f86dea2697fec7b1cf03a35ef9c83bb6cfa0ad3","target":"graph","created_at":"2026-07-21T01:21:02Z","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/2607.16848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers. We introduce two full-text scientific-memory benchmarks, Public AI Memory (PAIM; 81 papers, 66 questions) and Public Transformers (PTr; 252 papers, 98 questions). We evaluate eight memory/retrieval systems, including our own proposed Theoria, plus a no-retrieval baseline. Our results show that memory leaderboards are not interpretable without the full protocol: ingestion granularity, raw-","authors_text":"David Finkelstein, Maksim Sheverev, Sergey Nikolenko","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T15:09:58Z","title":"Beyond Memory Leaderboards: Evaluating Scientific Memory as Budgeted Context Restoration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16848","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":"sha256:9802dd5a038a751f7460ac8e2d10a40ca49a445b5679b785d7068e06f01b9d0f","target":"record","created_at":"2026-07-21T01:21:02Z","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":"cf25e90ae513e4455aa0d3806531899bb0b8d9b359b894074675304e9f843cd2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T15:09:58Z","title_canon_sha256":"7f74de42fec1b4460fcbd587eed006a2617bab1aad4aecc138364d7c6afc36ec"},"schema_version":"1.0","source":{"id":"2607.16848","kind":"arxiv","version":1}},"canonical_sha256":"f7413cdc3606f5f5699b8948be25e6a2f8205064d2e58d1f0e1e3bcfee0a1968","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7413cdc3606f5f5699b8948be25e6a2f8205064d2e58d1f0e1e3bcfee0a1968","first_computed_at":"2026-07-21T01:21:02.058784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:02.058784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+jcFJxhjGCh2cvI110e6yomJTvE053q7220uPeEm/zXaaZsr4A0AoM7H2LVTDauGkXXL98wsHU55RRXa8AjYCA==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:02.059656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9802dd5a038a751f7460ac8e2d10a40ca49a445b5679b785d7068e06f01b9d0f","sha256:7c67e091dbf23de4f60210349f86dea2697fec7b1cf03a35ef9c83bb6cfa0ad3"],"state_sha256":"3c6a71647acf363c0d648f6b72ff3664536b2c59c276c181e138c194914c0c79"}