{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZHKPO4UTDBCN3TFKMH6I2GJKZC","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":"530e35cbf262ec1568daf45573dbf48ec0d0f9d86c0b7bd60570fd5198ad690a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T09:08:27Z","title_canon_sha256":"c50edfd336d29687079b61bcaf5024653278fe84acc4a0018eff4f3b9d98d786"},"schema_version":"1.0","source":{"id":"2607.13618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13618","created_at":"2026-07-16T01:22:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13618v1","created_at":"2026-07-16T01:22:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13618","created_at":"2026-07-16T01:22:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZHKPO4UTDBCN","created_at":"2026-07-16T01:22:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZHKPO4UTDBCN3TFK","created_at":"2026-07-16T01:22:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZHKPO4UT","created_at":"2026-07-16T01:22:57Z"}],"graph_snapshots":[{"event_id":"sha256:fe7266fce27f7b8671b3e6bff786178eee72c65ecdf4bab04e8dd7746d3c5e0d","target":"graph","created_at":"2026-07-16T01:22:57Z","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/2607.13618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed. On such tasks the final cost cannot say why an agent failed: it may have misread the world, or read it correctly and still failed to act (the knowing-doing gap). Existing evaluations cannot separate these two failures; their reference policies either read privileged information the agent never sees, or are missing altogether. We introduce STOCKTAKE, a 26-week supply-chain replenishment benchmark built as a factored partially observable Markov decision process with ","authors_text":"Ashwanth Krishnan, Sagar Deb","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T09:08:27Z","title":"STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13618","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":"sha256:54ed013eec01cdf7487a2c3fee5ab5289c6ac39b83a9465f0310687c298aa20a","target":"record","created_at":"2026-07-16T01:22:57Z","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":"530e35cbf262ec1568daf45573dbf48ec0d0f9d86c0b7bd60570fd5198ad690a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T09:08:27Z","title_canon_sha256":"c50edfd336d29687079b61bcaf5024653278fe84acc4a0018eff4f3b9d98d786"},"schema_version":"1.0","source":{"id":"2607.13618","kind":"arxiv","version":1}},"canonical_sha256":"c9d4f772931844ddccaa61fc8d192ac8a97c28d19dee0ae4be42f8b1937b46c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9d4f772931844ddccaa61fc8d192ac8a97c28d19dee0ae4be42f8b1937b46c6","first_computed_at":"2026-07-16T01:22:57.182538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:22:57.182538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ck4dYRBCpQdZSsO6bjS3wGTqMhHgMHdbPbF8azIGl4utwXVN0QBAR7Y7/TNIs+8vUTfXQEUPoKdpzGiIRb2eCg==","signature_status":"signed_v1","signed_at":"2026-07-16T01:22:57.183382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54ed013eec01cdf7487a2c3fee5ab5289c6ac39b83a9465f0310687c298aa20a","sha256:fe7266fce27f7b8671b3e6bff786178eee72c65ecdf4bab04e8dd7746d3c5e0d"],"state_sha256":"d66e316a2f6bd26174961d8cbe5994142256ec406539ef922c9b1d0763580ae7"}