{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z6OBPZHYS5NPEH2H4PL2J5Q6UY","short_pith_number":"pith:Z6OBPZHY","canonical_record":{"source":{"id":"2508.21365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T07:13:39Z","cross_cats_sorted":[],"title_canon_sha256":"c7329eb808fb0366a3efdcb41aeb93c8a469c4a1c7ea11030b4b8cbdccfbe45d","abstract_canon_sha256":"96eaa6f4593030936709b2d3909cebf60c49c8a4d2aaa07158ec6a929a5804a8"},"schema_version":"1.0"},"canonical_sha256":"cf9c17e4f8975af21f47e3d7a4f61ea6310251741f66d4d47dbc76bd5cfe2419","source":{"kind":"arxiv","id":"2508.21365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21365","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21365v1","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21365","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"Z6OBPZHYS5NP","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"Z6OBPZHYS5NPEH2H","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"Z6OBPZHY","created_at":"2026-07-05T12:01:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z6OBPZHYS5NPEH2H4PL2J5Q6UY","target":"record","payload":{"canonical_record":{"source":{"id":"2508.21365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T07:13:39Z","cross_cats_sorted":[],"title_canon_sha256":"c7329eb808fb0366a3efdcb41aeb93c8a469c4a1c7ea11030b4b8cbdccfbe45d","abstract_canon_sha256":"96eaa6f4593030936709b2d3909cebf60c49c8a4d2aaa07158ec6a929a5804a8"},"schema_version":"1.0"},"canonical_sha256":"cf9c17e4f8975af21f47e3d7a4f61ea6310251741f66d4d47dbc76bd5cfe2419","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:33.582201Z","signature_b64":"5yfAqNB5xK9EE+NVHwxVTZdo61C5kye0w5V0n9+ZywxWfBTGEB8NrPofOCFHsh19Wqjyvd9Z78gzKeLYhXD/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf9c17e4f8975af21f47e3d7a4f61ea6310251741f66d4d47dbc76bd5cfe2419","last_reissued_at":"2026-07-05T12:01:33.581662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:33.581662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.21365","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":"2026-07-05T12:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+/IDxi32SCT6D/r1ZGgayRfRTOlof2rHXNT37EzcG9rRhi6I8x11wB2lvBpFjQfHlo1FfLx4qS9ChsWP3oaAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:58:06.602336Z"},"content_sha256":"3cf034d13087037db7e46b96104b8fee580ad9e75f30d9cc12e22937950bfd6b","schema_version":"1.0","event_id":"sha256:3cf034d13087037db7e46b96104b8fee580ad9e75f30d9cc12e22937950bfd6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z6OBPZHYS5NPEH2H4PL2J5Q6UY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guohua Tang, Wei Yang, Yifan Lu, Yi Liao, Yuan Sui, Yu Gu, Zhongqian Sun, Zining Zhu","submitted_at":"2025-08-29T07:13:39Z","abstract_excerpt":"Large language models (LLMs) excel at complex reasoning tasks such as mathematics and coding, yet they frequently struggle with simple interactive tasks that young children perform effortlessly. This discrepancy highlights a critical gap between declarative knowledge (knowing about something) and procedural knowledge (knowing how to do something). Although traditional reinforcement learning (RL) agents can acquire procedural knowledge through environmental interaction, they often operate as black boxes and require substantial training data. In contrast, LLMs possess extensive world knowledge a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21365","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/2508.21365/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":"2026-07-05T12:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4IdoICm9Og0yHSd59gWmE2IacsG20eszvm+f7IlVG7vtLgyzxXTy4X2KBS68SSy/gdHufYjIL7bmSor5aFxxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:58:06.602646Z"},"content_sha256":"a99b37353b1c1e78ad4b81ecd9701fe89bdc4906c727c8cb8b15f2511ed552df","schema_version":"1.0","event_id":"sha256:a99b37353b1c1e78ad4b81ecd9701fe89bdc4906c727c8cb8b15f2511ed552df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z6OBPZHYS5NPEH2H4PL2J5Q6UY/bundle.json","state_url":"https://pith.science/pith/Z6OBPZHYS5NPEH2H4PL2J5Q6UY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z6OBPZHYS5NPEH2H4PL2J5Q6UY/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":"2026-08-06T01:58:06Z","links":{"resolver":"https://pith.science/pith/Z6OBPZHYS5NPEH2H4PL2J5Q6UY","bundle":"https://pith.science/pith/Z6OBPZHYS5NPEH2H4PL2J5Q6UY/bundle.json","state":"https://pith.science/pith/Z6OBPZHYS5NPEH2H4PL2J5Q6UY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z6OBPZHYS5NPEH2H4PL2J5Q6UY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z6OBPZHYS5NPEH2H4PL2J5Q6UY","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":"96eaa6f4593030936709b2d3909cebf60c49c8a4d2aaa07158ec6a929a5804a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T07:13:39Z","title_canon_sha256":"c7329eb808fb0366a3efdcb41aeb93c8a469c4a1c7ea11030b4b8cbdccfbe45d"},"schema_version":"1.0","source":{"id":"2508.21365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21365","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21365v1","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21365","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"Z6OBPZHYS5NP","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"Z6OBPZHYS5NPEH2H","created_at":"2026-07-05T12:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"Z6OBPZHY","created_at":"2026-07-05T12:01:33Z"}],"graph_snapshots":[{"event_id":"sha256:a99b37353b1c1e78ad4b81ecd9701fe89bdc4906c727c8cb8b15f2511ed552df","target":"graph","created_at":"2026-07-05T12:01:33Z","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/2508.21365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel at complex reasoning tasks such as mathematics and coding, yet they frequently struggle with simple interactive tasks that young children perform effortlessly. This discrepancy highlights a critical gap between declarative knowledge (knowing about something) and procedural knowledge (knowing how to do something). Although traditional reinforcement learning (RL) agents can acquire procedural knowledge through environmental interaction, they often operate as black boxes and require substantial training data. In contrast, LLMs possess extensive world knowledge a","authors_text":"Guohua Tang, Wei Yang, Yifan Lu, Yi Liao, Yuan Sui, Yu Gu, Zhongqian Sun, Zining Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T07:13:39Z","title":"Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21365","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":"sha256:3cf034d13087037db7e46b96104b8fee580ad9e75f30d9cc12e22937950bfd6b","target":"record","created_at":"2026-07-05T12:01:33Z","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":"96eaa6f4593030936709b2d3909cebf60c49c8a4d2aaa07158ec6a929a5804a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T07:13:39Z","title_canon_sha256":"c7329eb808fb0366a3efdcb41aeb93c8a469c4a1c7ea11030b4b8cbdccfbe45d"},"schema_version":"1.0","source":{"id":"2508.21365","kind":"arxiv","version":1}},"canonical_sha256":"cf9c17e4f8975af21f47e3d7a4f61ea6310251741f66d4d47dbc76bd5cfe2419","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf9c17e4f8975af21f47e3d7a4f61ea6310251741f66d4d47dbc76bd5cfe2419","first_computed_at":"2026-07-05T12:01:33.581662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:33.581662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5yfAqNB5xK9EE+NVHwxVTZdo61C5kye0w5V0n9+ZywxWfBTGEB8NrPofOCFHsh19Wqjyvd9Z78gzKeLYhXD/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:33.582201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cf034d13087037db7e46b96104b8fee580ad9e75f30d9cc12e22937950bfd6b","sha256:a99b37353b1c1e78ad4b81ecd9701fe89bdc4906c727c8cb8b15f2511ed552df"],"state_sha256":"11a0e80abf96ea36eaaf976c125cd35380df8f6ebec9cc0fee690abed9bad7d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X5XYCqH/d7HXujOl4wlkz2mwmOIBAvKo2+XKWFT2BWJGAKJoysoULvTpB6pRFvqQH7Fpe8RH/PKwGhARL7OXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:58:06.605959Z","bundle_sha256":"07e69ecac8511e340c4b7ac168fed942ec97f2503e18841849f571ef844fcc14"}}