{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OSBIAIFSE5TOM3OR63CZWC7VRQ","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":"e9265e18dd3b6794eda8f04169d90026b6d21f99069d81f647a276f6eb0a64f1","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T15:50:33Z","title_canon_sha256":"1c4b51475c0aed6d68be5f98781c7ff604fb9121f467003f9a419ef43e765d6f"},"schema_version":"1.0","source":{"id":"2608.02409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02409","created_at":"2026-08-04T02:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02409v1","created_at":"2026-08-04T02:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02409","created_at":"2026-08-04T02:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"OSBIAIFSE5TO","created_at":"2026-08-04T02:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"OSBIAIFSE5TOM3OR","created_at":"2026-08-04T02:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"OSBIAIFS","created_at":"2026-08-04T02:12:10Z"}],"graph_snapshots":[{"event_id":"sha256:6fbfd91fdbd617230df5fac29b12ab2220b65e5fbe9569b5e1ed395322227d72","target":"graph","created_at":"2026-08-04T02:12:10Z","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/2608.02409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark suites assess model capability on controlled tasks; large-scale conversation corpora capture naturalistic use without user feedback; and in-interface feedback mechanisms record satisfaction without task purpose. Together, they leave a critical gap in LLM evaluation: no existing infrastructure routinely links interaction trajectories to user-defined outcomes. We introduce MonitrLLM, open-source infrastructure for community-centered LLM evaluations that links full conversation transcripts to user-reported task intent and outcome assessments, treating all three as primary evaluative sig","authors_text":"Dana\\'e Metaxa, Ro Encarnaci\\'on, Suresh Venkatasubramanian, Victor Ojewale","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T15:50:33Z","title":"MonitrLLM: A Community-Centered Evaluation Infrastructure for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02409","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":"sha256:45e4d46cab405010dbfde2d7988399e30a9dd9fecb600f3f6bd87cba4f47e726","target":"record","created_at":"2026-08-04T02:12:10Z","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":"e9265e18dd3b6794eda8f04169d90026b6d21f99069d81f647a276f6eb0a64f1","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T15:50:33Z","title_canon_sha256":"1c4b51475c0aed6d68be5f98781c7ff604fb9121f467003f9a419ef43e765d6f"},"schema_version":"1.0","source":{"id":"2608.02409","kind":"arxiv","version":1}},"canonical_sha256":"74828020b22766e66dd1f6c59b0bf58c30bdbc5e855f108eda549567e58ba537","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74828020b22766e66dd1f6c59b0bf58c30bdbc5e855f108eda549567e58ba537","first_computed_at":"2026-08-04T02:12:10.359685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:12:10.359685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9VdGpZ6cbCarGrgNWEU78CZJRuyR0FaQUfowKtuX9z4EzyCCe6Kc0xnNeetpHgqHA78bqTRvvqhAoY8jYLz1Bg==","signature_status":"signed_v1","signed_at":"2026-08-04T02:12:10.361223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45e4d46cab405010dbfde2d7988399e30a9dd9fecb600f3f6bd87cba4f47e726","sha256:6fbfd91fdbd617230df5fac29b12ab2220b65e5fbe9569b5e1ed395322227d72"],"state_sha256":"6809f1e74efc80cebc5b12f9e8ca14d636171ee6e3a17ff58bcf0003d1360193"}