{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DEHDMZ4CMUAL5SMWDWTG4J6Y5O","short_pith_number":"pith:DEHDMZ4C","canonical_record":{"source":{"id":"2606.00103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T09:12:30Z","cross_cats_sorted":[],"title_canon_sha256":"b60dc8cd3f333bd9cec11c46f6d1c958ad25b8ed1912097b6df3d1215648d582","abstract_canon_sha256":"22af889be59868517983350a43ff9d8540b07fc8e7e2adb2cc70cc9024eb9b6b"},"schema_version":"1.0"},"canonical_sha256":"190e3667826500bec9961da66e27d8eb8c4925aec145d376116ac9c58240e918","source":{"kind":"arxiv","id":"2606.00103","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00103","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00103v1","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00103","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"pith_short_12","alias_value":"DEHDMZ4CMUAL","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"pith_short_16","alias_value":"DEHDMZ4CMUAL5SMW","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"pith_short_8","alias_value":"DEHDMZ4C","created_at":"2026-06-02T00:03:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DEHDMZ4CMUAL5SMWDWTG4J6Y5O","target":"record","payload":{"canonical_record":{"source":{"id":"2606.00103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T09:12:30Z","cross_cats_sorted":[],"title_canon_sha256":"b60dc8cd3f333bd9cec11c46f6d1c958ad25b8ed1912097b6df3d1215648d582","abstract_canon_sha256":"22af889be59868517983350a43ff9d8540b07fc8e7e2adb2cc70cc9024eb9b6b"},"schema_version":"1.0"},"canonical_sha256":"190e3667826500bec9961da66e27d8eb8c4925aec145d376116ac9c58240e918","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T00:03:15.125481Z","signature_b64":"bnHBUPd9uK47qP4HE5Bj9WoDdPVotvyffQSdNbNFbgfiR8LNSDULDs2x27kFBf9dDFuFJ6lEFE6yaH2jzdDbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"190e3667826500bec9961da66e27d8eb8c4925aec145d376116ac9c58240e918","last_reissued_at":"2026-06-02T00:03:15.124867Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T00:03:15.124867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.00103","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T00:03:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ApTt5IzdA1n1PKJZqsrKk2qHi0D34cyhHnkP74hTAGKNigLustP+u2TNk4KTLZun88v2lbMd3l/I+PaU0BJoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T04:59:57.084631Z"},"content_sha256":"d4a46548a4634b3cbf1f72647cd908ec371869f249f18475df302781575629ec","schema_version":"1.0","event_id":"sha256:d4a46548a4634b3cbf1f72647cd908ec371869f249f18475df302781575629ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DEHDMZ4CMUAL5SMWDWTG4J6Y5O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cen Chen, Daixin Wang, Jun Zhou, Mingyuan Fan, Weiguang Han, Zhiqiang Zhang","submitted_at":"2026-05-26T09:12:30Z","abstract_excerpt":"We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating. Wherein, LLMs receive only the task rules, must issue targeted queries to a hidden environment, integrate partial observations over time, and decide when to submit a final answer. Beyond standard success rate and interaction efficiency, we evaluate contextual robustness under controlled contextual perturbations, and metacognitive adaptation through counterfactual revision and necessity judgment. We instantiate the framework as a benchmark of 474 exe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00103","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/2606.00103/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T00:03:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pww6ukh/6USwyF5FJnHYLAK1WLA8zATfBgGN+YG/YkqnhVO7DPR0FKNz7a/AWV1tQckITokMPn88PjPYlJlXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T04:59:57.085326Z"},"content_sha256":"72c3f7300a853a50c08f5739377c05f18f6511785fe6473b77592e8d7e72f291","schema_version":"1.0","event_id":"sha256:72c3f7300a853a50c08f5739377c05f18f6511785fe6473b77592e8d7e72f291"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DEHDMZ4CMUAL5SMWDWTG4J6Y5O/bundle.json","state_url":"https://pith.science/pith/DEHDMZ4CMUAL5SMWDWTG4J6Y5O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DEHDMZ4CMUAL5SMWDWTG4J6Y5O/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T04:59:57Z","links":{"resolver":"https://pith.science/pith/DEHDMZ4CMUAL5SMWDWTG4J6Y5O","bundle":"https://pith.science/pith/DEHDMZ4CMUAL5SMWDWTG4J6Y5O/bundle.json","state":"https://pith.science/pith/DEHDMZ4CMUAL5SMWDWTG4J6Y5O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DEHDMZ4CMUAL5SMWDWTG4J6Y5O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DEHDMZ4CMUAL5SMWDWTG4J6Y5O","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":"22af889be59868517983350a43ff9d8540b07fc8e7e2adb2cc70cc9024eb9b6b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T09:12:30Z","title_canon_sha256":"b60dc8cd3f333bd9cec11c46f6d1c958ad25b8ed1912097b6df3d1215648d582"},"schema_version":"1.0","source":{"id":"2606.00103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00103","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00103v1","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00103","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"pith_short_12","alias_value":"DEHDMZ4CMUAL","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"pith_short_16","alias_value":"DEHDMZ4CMUAL5SMW","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"pith_short_8","alias_value":"DEHDMZ4C","created_at":"2026-06-02T00:03:15Z"}],"graph_snapshots":[{"event_id":"sha256:72c3f7300a853a50c08f5739377c05f18f6511785fe6473b77592e8d7e72f291","target":"graph","created_at":"2026-06-02T00:03:15Z","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/2606.00103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating. Wherein, LLMs receive only the task rules, must issue targeted queries to a hidden environment, integrate partial observations over time, and decide when to submit a final answer. Beyond standard success rate and interaction efficiency, we evaluate contextual robustness under controlled contextual perturbations, and metacognitive adaptation through counterfactual revision and necessity judgment. We instantiate the framework as a benchmark of 474 exe","authors_text":"Cen Chen, Daixin Wang, Jun Zhou, Mingyuan Fan, Weiguang Han, Zhiqiang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T09:12:30Z","title":"Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00103","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:d4a46548a4634b3cbf1f72647cd908ec371869f249f18475df302781575629ec","target":"record","created_at":"2026-06-02T00:03:15Z","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":"22af889be59868517983350a43ff9d8540b07fc8e7e2adb2cc70cc9024eb9b6b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T09:12:30Z","title_canon_sha256":"b60dc8cd3f333bd9cec11c46f6d1c958ad25b8ed1912097b6df3d1215648d582"},"schema_version":"1.0","source":{"id":"2606.00103","kind":"arxiv","version":1}},"canonical_sha256":"190e3667826500bec9961da66e27d8eb8c4925aec145d376116ac9c58240e918","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"190e3667826500bec9961da66e27d8eb8c4925aec145d376116ac9c58240e918","first_computed_at":"2026-06-02T00:03:15.124867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T00:03:15.124867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bnHBUPd9uK47qP4HE5Bj9WoDdPVotvyffQSdNbNFbgfiR8LNSDULDs2x27kFBf9dDFuFJ6lEFE6yaH2jzdDbDQ==","signature_status":"signed_v1","signed_at":"2026-06-02T00:03:15.125481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4a46548a4634b3cbf1f72647cd908ec371869f249f18475df302781575629ec","sha256:72c3f7300a853a50c08f5739377c05f18f6511785fe6473b77592e8d7e72f291"],"state_sha256":"8234a3f67cd237c7fbad915edbf482f885c6bfaadd1c199787a4d8f58650a142"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xk7r9mPDLsoiz11fsdmkthoACCTfZDtLwh/w7iHnGUnx/HfTaRU0qBgrWel/ENzd0i9FPUB/3Gx03m68762fAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T04:59:57.088688Z","bundle_sha256":"c842e04ee6d9408583629094dc0799b218402f0737cee346e83966c574538aa0"}}