{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VBDEKFGIPQZ3KTG5R5HRC6EEAF","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":"4a6c67fe779bb1e3557481fd3a8327ba5f8a1d26a34218e36ec9e71a4f43bec4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T17:59:34Z","title_canon_sha256":"e18201ec970b1f64db9fb11604695442b62e5f6ee795672af977079575ebdb21"},"schema_version":"1.0","source":{"id":"2606.19338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19338","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19338v1","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19338","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"VBDEKFGIPQZ3","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"VBDEKFGIPQZ3KTG5","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"VBDEKFGI","created_at":"2026-06-19T16:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:f5d095982c06a4c9baff24498974a5208b5ad5f4e8f52146a3861a49efb1a2dc","target":"graph","created_at":"2026-06-19T16:12:11Z","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/2606.19338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deploying multimodal foundation models as closed-loop policies increasingly requires conditioning actions on observations that are no longer visible. However, existing benchmarks either expose the full state, conflate hidden-state reconstruction with other agent skills, or test recall only after an episode has ended. We introduce RNG-Bench (Reconstructive Non-Markov Games), a benchmark suite designed to isolate a base model's ability to reconstruct past observations and act on them during multi-step interaction. RNG-Bench includes two complementary games: Matching Pairs, where card identities ","authors_text":"Dahua Lin, Haodong Duan, Jiaqi Wang, Shengyuan Ding, Xilin Wei, Xinyu Fang, Yuhang Zang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T17:59:34Z","title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19338","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":"sha256:2b529e8b1853593d0fc7a73c390884874ad1694cccaf8873edf10a3ae733fab9","target":"record","created_at":"2026-06-19T16:12:11Z","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":"4a6c67fe779bb1e3557481fd3a8327ba5f8a1d26a34218e36ec9e71a4f43bec4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T17:59:34Z","title_canon_sha256":"e18201ec970b1f64db9fb11604695442b62e5f6ee795672af977079575ebdb21"},"schema_version":"1.0","source":{"id":"2606.19338","kind":"arxiv","version":1}},"canonical_sha256":"a8464514c87c33b54cdd8f4f117884014b7ea6d354a6a5a5f3ecd8d14501d111","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8464514c87c33b54cdd8f4f117884014b7ea6d354a6a5a5f3ecd8d14501d111","first_computed_at":"2026-06-19T16:12:11.582975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:11.582975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3bULaYouhPLcxL1H8k4DX6g3uCIB6e/PeuRAOj0unpdAo3ev+ziljxgDZijJFJKlfh1l1pNDWBROSPE5lJaAAA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:11.583334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b529e8b1853593d0fc7a73c390884874ad1694cccaf8873edf10a3ae733fab9","sha256:f5d095982c06a4c9baff24498974a5208b5ad5f4e8f52146a3861a49efb1a2dc"],"state_sha256":"8099c36fc6576a53d03b63fe7a23cf2f720150018f6130ddd6406061aa80ac53"}