{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3GMEITB4M7PCWYVJ7LBWZNEMWY","short_pith_number":"pith:3GMEITB4","canonical_record":{"source":{"id":"2508.19506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T01:30:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3916256f0961aa655eaa0ca8eb549b249f67d759eefe87af9e6c662da0f917c6","abstract_canon_sha256":"a22fe36e2b9c2a29c66b776555f6dd8399badc937633b4c8cd488ebb31581d10"},"schema_version":"1.0"},"canonical_sha256":"d998444c3c67de2b62a9fac36cb48cb61a3f54c37f8d944e3c979d769d8dbca3","source":{"kind":"arxiv","id":"2508.19506","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19506","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19506v1","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19506","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"pith_short_12","alias_value":"3GMEITB4M7PC","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"pith_short_16","alias_value":"3GMEITB4M7PCWYVJ","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"pith_short_8","alias_value":"3GMEITB4","created_at":"2026-07-05T12:00:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3GMEITB4M7PCWYVJ7LBWZNEMWY","target":"record","payload":{"canonical_record":{"source":{"id":"2508.19506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T01:30:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3916256f0961aa655eaa0ca8eb549b249f67d759eefe87af9e6c662da0f917c6","abstract_canon_sha256":"a22fe36e2b9c2a29c66b776555f6dd8399badc937633b4c8cd488ebb31581d10"},"schema_version":"1.0"},"canonical_sha256":"d998444c3c67de2b62a9fac36cb48cb61a3f54c37f8d944e3c979d769d8dbca3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:12.798009Z","signature_b64":"20aXdTE00MTN8VDghHGgr5x/mvoIrtRMdkxePywLL+PK4v8O/Ieo7AdBh7XvehJIVPdjdEYpshiXgVl/12xkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d998444c3c67de2b62a9fac36cb48cb61a3f54c37f8d944e3c979d769d8dbca3","last_reissued_at":"2026-07-05T12:00:12.797595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:12.797595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.19506","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":"2026-07-05T12:00:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p1XAPpZuOLH4Yz/66BT3Fn+KWpAVv49/+ahdH00tisc49DU/wlqMobrg9+R2/JnicmgYb0b4PpGO6HeDE3qfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:56:44.916736Z"},"content_sha256":"3b74652da7172b552d0aa8faa230d67e2fd7ae940e605964611c0174ed80c2ed","schema_version":"1.0","event_id":"sha256:3b74652da7172b552d0aa8faa230d67e2fd7ae940e605964611c0174ed80c2ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3GMEITB4M7PCWYVJ7LBWZNEMWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Game-Playing Agents with Generative Code Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Allen Nie, Ryan Rong, YuCheng Yuan, Zhiyi Kuang","submitted_at":"2025-08-27T01:30:20Z","abstract_excerpt":"We present a generative optimization approach for learning game-playing agents, where policies are represented as Python programs and refined using large language models (LLMs). Our method treats decision-making policies as self-evolving code, with current observation as input and an in-game action as output, enabling agents to self-improve through execution traces and natural language feedback with minimal human intervention. Applied to Atari games, our game-playing Python program achieves performance competitive with deep reinforcement learning (RL) baselines while using significantly less t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19506","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/2508.19506/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":"2026-07-05T12:00:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lxR3X0r7CkAQkK/K8OqaMYFy9dmOoggi1EEjs+RQgB4oK8hzc5XlCH/WEUfqnHkmEObl8mPbw2Kf8SIU+mT1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:56:44.917695Z"},"content_sha256":"0680cb91280beb0e867096eb957535df54fc3151559033ba5a14d2dd4f4fd92c","schema_version":"1.0","event_id":"sha256:0680cb91280beb0e867096eb957535df54fc3151559033ba5a14d2dd4f4fd92c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/bundle.json","state_url":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/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":"2026-08-04T03:56:44Z","links":{"resolver":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY","bundle":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/bundle.json","state":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3GMEITB4M7PCWYVJ7LBWZNEMWY","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":"a22fe36e2b9c2a29c66b776555f6dd8399badc937633b4c8cd488ebb31581d10","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T01:30:20Z","title_canon_sha256":"3916256f0961aa655eaa0ca8eb549b249f67d759eefe87af9e6c662da0f917c6"},"schema_version":"1.0","source":{"id":"2508.19506","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19506","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19506v1","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19506","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"pith_short_12","alias_value":"3GMEITB4M7PC","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"pith_short_16","alias_value":"3GMEITB4M7PCWYVJ","created_at":"2026-07-05T12:00:12Z"},{"alias_kind":"pith_short_8","alias_value":"3GMEITB4","created_at":"2026-07-05T12:00:12Z"}],"graph_snapshots":[{"event_id":"sha256:0680cb91280beb0e867096eb957535df54fc3151559033ba5a14d2dd4f4fd92c","target":"graph","created_at":"2026-07-05T12:00:12Z","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/2508.19506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a generative optimization approach for learning game-playing agents, where policies are represented as Python programs and refined using large language models (LLMs). Our method treats decision-making policies as self-evolving code, with current observation as input and an in-game action as output, enabling agents to self-improve through execution traces and natural language feedback with minimal human intervention. Applied to Atari games, our game-playing Python program achieves performance competitive with deep reinforcement learning (RL) baselines while using significantly less t","authors_text":"Allen Nie, Ryan Rong, YuCheng Yuan, Zhiyi Kuang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T01:30:20Z","title":"Learning Game-Playing Agents with Generative Code Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19506","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":"sha256:3b74652da7172b552d0aa8faa230d67e2fd7ae940e605964611c0174ed80c2ed","target":"record","created_at":"2026-07-05T12:00:12Z","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":"a22fe36e2b9c2a29c66b776555f6dd8399badc937633b4c8cd488ebb31581d10","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T01:30:20Z","title_canon_sha256":"3916256f0961aa655eaa0ca8eb549b249f67d759eefe87af9e6c662da0f917c6"},"schema_version":"1.0","source":{"id":"2508.19506","kind":"arxiv","version":1}},"canonical_sha256":"d998444c3c67de2b62a9fac36cb48cb61a3f54c37f8d944e3c979d769d8dbca3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d998444c3c67de2b62a9fac36cb48cb61a3f54c37f8d944e3c979d769d8dbca3","first_computed_at":"2026-07-05T12:00:12.797595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:12.797595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"20aXdTE00MTN8VDghHGgr5x/mvoIrtRMdkxePywLL+PK4v8O/Ieo7AdBh7XvehJIVPdjdEYpshiXgVl/12xkCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:12.798009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.19506","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b74652da7172b552d0aa8faa230d67e2fd7ae940e605964611c0174ed80c2ed","sha256:0680cb91280beb0e867096eb957535df54fc3151559033ba5a14d2dd4f4fd92c"],"state_sha256":"a27ac65e8b70e3234bb447182072fa9f8db5a813e580a56f26b792b878cbd6d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"57ulNWoY+nvH4UbqMTh8Fmw2g4OfdBlRUsE2OZen6qntgsMnNO11b5CLbe9cCSFIyjGQ5pEgWvU0Jp1boAnlCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:56:44.924332Z","bundle_sha256":"e28b729287285aaa549198e3fe63d58f6ef41a62c834158e00bbe30de595a74a"}}