{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VBDEKFGIPQZ3KTG5R5HRC6EEAF","short_pith_number":"pith:VBDEKFGI","schema_version":"1.0","canonical_sha256":"a8464514c87c33b54cdd8f4f117884014b7ea6d354a6a5a5f3ecd8d14501d111","source":{"kind":"arxiv","id":"2606.19338","version":1},"attestation_state":"computed","paper":{"title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Haodong Duan, Jiaqi Wang, Shengyuan Ding, Xilin Wei, Xinyu Fang, Yuhang Zang","submitted_at":"2026-06-17T17:59:34Z","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 "},"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":"2606.19338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T17:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"e18201ec970b1f64db9fb11604695442b62e5f6ee795672af977079575ebdb21","abstract_canon_sha256":"4a6c67fe779bb1e3557481fd3a8327ba5f8a1d26a34218e36ec9e71a4f43bec4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:11.583334Z","signature_b64":"3bULaYouhPLcxL1H8k4DX6g3uCIB6e/PeuRAOj0unpdAo3ev+ziljxgDZijJFJKlfh1l1pNDWBROSPE5lJaAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8464514c87c33b54cdd8f4f117884014b7ea6d354a6a5a5f3ecd8d14501d111","last_reissued_at":"2026-06-19T16:12:11.582975Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:11.582975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Haodong Duan, Jiaqi Wang, Shengyuan Ding, Xilin Wei, Xinyu Fang, Yuhang Zang","submitted_at":"2026-06-17T17:59:34Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19338","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/2606.19338/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":"2606.19338","created_at":"2026-06-19T16:12:11.583027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19338v1","created_at":"2026-06-19T16:12:11.583027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19338","created_at":"2026-06-19T16:12:11.583027+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBDEKFGIPQZ3","created_at":"2026-06-19T16:12:11.583027+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBDEKFGIPQZ3KTG5","created_at":"2026-06-19T16:12:11.583027+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBDEKFGI","created_at":"2026-06-19T16:12:11.583027+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/VBDEKFGIPQZ3KTG5R5HRC6EEAF","json":"https://pith.science/pith/VBDEKFGIPQZ3KTG5R5HRC6EEAF.json","graph_json":"https://pith.science/api/pith-number/VBDEKFGIPQZ3KTG5R5HRC6EEAF/graph.json","events_json":"https://pith.science/api/pith-number/VBDEKFGIPQZ3KTG5R5HRC6EEAF/events.json","paper":"https://pith.science/paper/VBDEKFGI"},"agent_actions":{"view_html":"https://pith.science/pith/VBDEKFGIPQZ3KTG5R5HRC6EEAF","download_json":"https://pith.science/pith/VBDEKFGIPQZ3KTG5R5HRC6EEAF.json","view_paper":"https://pith.science/paper/VBDEKFGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19338&json=true","fetch_graph":"https://pith.science/api/pith-number/VBDEKFGIPQZ3KTG5R5HRC6EEAF/graph.json","fetch_events":"https://pith.science/api/pith-number/VBDEKFGIPQZ3KTG5R5HRC6EEAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBDEKFGIPQZ3KTG5R5HRC6EEAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBDEKFGIPQZ3KTG5R5HRC6EEAF/action/storage_attestation","attest_author":"https://pith.science/pith/VBDEKFGIPQZ3KTG5R5HRC6EEAF/action/author_attestation","sign_citation":"https://pith.science/pith/VBDEKFGIPQZ3KTG5R5HRC6EEAF/action/citation_signature","submit_replication":"https://pith.science/pith/VBDEKFGIPQZ3KTG5R5HRC6EEAF/action/replication_record"}},"created_at":"2026-06-19T16:12:11.583027+00:00","updated_at":"2026-06-19T16:12:11.583027+00:00"}