{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZK2JORBQ53BLLTV3N5PWKSE3PO","short_pith_number":"pith:ZK2JORBQ","canonical_record":{"source":{"id":"2607.17560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T05:09:36Z","cross_cats_sorted":[],"title_canon_sha256":"26c562a60c5dcf45510358ae5c0c3e9e8a348d78d9f8cc4b2fe081cf3cb2c4f3","abstract_canon_sha256":"6bb32ca8d04908a468c11be360b69e27c51512be426e6e679c569a94a9d83795"},"schema_version":"1.0"},"canonical_sha256":"cab4974430eec2b5cebb6f5f65489b7baf6be49f6d201157fe5fc7aaf42e9818","source":{"kind":"arxiv","id":"2607.17560","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17560","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17560v1","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17560","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"pith_short_12","alias_value":"ZK2JORBQ53BL","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZK2JORBQ53BLLTV3","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZK2JORBQ","created_at":"2026-07-21T01:21:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZK2JORBQ53BLLTV3N5PWKSE3PO","target":"record","payload":{"canonical_record":{"source":{"id":"2607.17560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T05:09:36Z","cross_cats_sorted":[],"title_canon_sha256":"26c562a60c5dcf45510358ae5c0c3e9e8a348d78d9f8cc4b2fe081cf3cb2c4f3","abstract_canon_sha256":"6bb32ca8d04908a468c11be360b69e27c51512be426e6e679c569a94a9d83795"},"schema_version":"1.0"},"canonical_sha256":"cab4974430eec2b5cebb6f5f65489b7baf6be49f6d201157fe5fc7aaf42e9818","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:52.296106Z","signature_b64":"WDogBNhXGRQpx4Nft5hvBzubSEGq0NxsiK7dgEe3MzRasmnWw0QN9/sAwkr1bT/JL4HwobbkF6MPubuT31nkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cab4974430eec2b5cebb6f5f65489b7baf6be49f6d201157fe5fc7aaf42e9818","last_reissued_at":"2026-07-21T01:21:52.295212Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:52.295212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.17560","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":"2026-07-21T01:21:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/UmoncjxQIHIFtHtm+ObhB3gPneKmfcGEn6SWV4pFKl0o5+5akjWsBz3SnhivPTVInFuSF/ESldVmN3O9h5bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T17:04:00.310551Z"},"content_sha256":"204f1f8d428bc6a42a9784e3348664447a5e6f99c792bf77f0e161bfccbf5cef","schema_version":"1.0","event_id":"sha256:204f1f8d428bc6a42a9784e3348664447a5e6f99c792bf77f0e161bfccbf5cef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZK2JORBQ53BLLTV3N5PWKSE3PO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning: From Algorithms To Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Zihan Ding","submitted_at":"2026-07-20T05:09:36Z","abstract_excerpt":"Reinforcement learning (RL) provides a framework for sequential decision making under explicit objectives. In its classical form, RL studies how an agent should act to maximise long-term reward in a dynamic environment. In richer settings, the problem extends beyond a single agent and fixed environment: intelligent behavior may require strategic interaction, adaptation to uncertainty, and reasoning over high-dimensional worlds. This thesis studies RL from two perspectives: algorithms in games and RL in the era of foundation models.\n  The first part focuses on multi-agent RL in games. It examin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17560","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/2607.17560/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":"2026-07-21T01:21:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pw/+60cX4YkaP8PFU5sTvjFXevXmcRmiYfS8ElVuW6DAAxQEQWrQKRsbUhsm+LAkgs6Bq5OdRbKCTeCjexc3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T17:04:00.311055Z"},"content_sha256":"23b2edf9fa45d2790bbc736ebdc7977c3582dc1376e589cb7aaab00fcae9c3c0","schema_version":"1.0","event_id":"sha256:23b2edf9fa45d2790bbc736ebdc7977c3582dc1376e589cb7aaab00fcae9c3c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/bundle.json","state_url":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/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":"2026-08-02T17:04:00Z","links":{"resolver":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO","bundle":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/bundle.json","state":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZK2JORBQ53BLLTV3N5PWKSE3PO","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":"6bb32ca8d04908a468c11be360b69e27c51512be426e6e679c569a94a9d83795","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T05:09:36Z","title_canon_sha256":"26c562a60c5dcf45510358ae5c0c3e9e8a348d78d9f8cc4b2fe081cf3cb2c4f3"},"schema_version":"1.0","source":{"id":"2607.17560","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17560","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17560v1","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17560","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"pith_short_12","alias_value":"ZK2JORBQ53BL","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZK2JORBQ53BLLTV3","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZK2JORBQ","created_at":"2026-07-21T01:21:52Z"}],"graph_snapshots":[{"event_id":"sha256:23b2edf9fa45d2790bbc736ebdc7977c3582dc1376e589cb7aaab00fcae9c3c0","target":"graph","created_at":"2026-07-21T01:21:52Z","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/2607.17560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) provides a framework for sequential decision making under explicit objectives. In its classical form, RL studies how an agent should act to maximise long-term reward in a dynamic environment. In richer settings, the problem extends beyond a single agent and fixed environment: intelligent behavior may require strategic interaction, adaptation to uncertainty, and reasoning over high-dimensional worlds. This thesis studies RL from two perspectives: algorithms in games and RL in the era of foundation models.\n  The first part focuses on multi-agent RL in games. It examin","authors_text":"Zihan Ding","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T05:09:36Z","title":"Reinforcement Learning: From Algorithms To Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17560","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":"sha256:204f1f8d428bc6a42a9784e3348664447a5e6f99c792bf77f0e161bfccbf5cef","target":"record","created_at":"2026-07-21T01:21:52Z","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":"6bb32ca8d04908a468c11be360b69e27c51512be426e6e679c569a94a9d83795","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T05:09:36Z","title_canon_sha256":"26c562a60c5dcf45510358ae5c0c3e9e8a348d78d9f8cc4b2fe081cf3cb2c4f3"},"schema_version":"1.0","source":{"id":"2607.17560","kind":"arxiv","version":1}},"canonical_sha256":"cab4974430eec2b5cebb6f5f65489b7baf6be49f6d201157fe5fc7aaf42e9818","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cab4974430eec2b5cebb6f5f65489b7baf6be49f6d201157fe5fc7aaf42e9818","first_computed_at":"2026-07-21T01:21:52.295212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:52.295212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WDogBNhXGRQpx4Nft5hvBzubSEGq0NxsiK7dgEe3MzRasmnWw0QN9/sAwkr1bT/JL4HwobbkF6MPubuT31nkBQ==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:52.296106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17560","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:204f1f8d428bc6a42a9784e3348664447a5e6f99c792bf77f0e161bfccbf5cef","sha256:23b2edf9fa45d2790bbc736ebdc7977c3582dc1376e589cb7aaab00fcae9c3c0"],"state_sha256":"c2bc5ba8b9a0f1d436a82dccccfefd7747dd2f1e80cf905655ca5a3dce4100db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l3E6QvZF0p93py63zgxuoAD9qM74pGna/6biCvCc9TLwckBCDWAzC54a5U+yS4wUkcFUpNSGPriSuGa1NeitAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T17:04:00.314742Z","bundle_sha256":"52674de34a4214ad954a653d58334c30e2da56e066282c6a589c3c08a6e8f44f"}}