{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CNNQSMGEXMUS4CGQLJ6UQBU5PZ","short_pith_number":"pith:CNNQSMGE","canonical_record":{"source":{"id":"2204.02785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-04-04T16:18:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a3d9280045b655b40b4acccdda655762b688c359d1365644aa5c556e851f205f","abstract_canon_sha256":"03c19b14a35b2331afb901a5bd05ac72dbcc0385fe2ea4a8280afa2220730cf9"},"schema_version":"1.0"},"canonical_sha256":"135b0930c4bb292e08d05a7d48069d7e64b27c7c8e0a55ba8a9c764a9de38d58","source":{"kind":"arxiv","id":"2204.02785","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02785","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02785v1","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02785","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"pith_short_12","alias_value":"CNNQSMGEXMUS","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"pith_short_16","alias_value":"CNNQSMGEXMUS4CGQ","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"pith_short_8","alias_value":"CNNQSMGE","created_at":"2026-07-05T04:12:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CNNQSMGEXMUS4CGQLJ6UQBU5PZ","target":"record","payload":{"canonical_record":{"source":{"id":"2204.02785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-04-04T16:18:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a3d9280045b655b40b4acccdda655762b688c359d1365644aa5c556e851f205f","abstract_canon_sha256":"03c19b14a35b2331afb901a5bd05ac72dbcc0385fe2ea4a8280afa2220730cf9"},"schema_version":"1.0"},"canonical_sha256":"135b0930c4bb292e08d05a7d48069d7e64b27c7c8e0a55ba8a9c764a9de38d58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:12.316132Z","signature_b64":"b5sVUI+sZOYar6ULhVkiMZzKYK/QC5nPclw6ZR1L8NobXYA9nfAZKenk9ZWzd/R9pes8VQUDDP3vEJAySbIDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"135b0930c4bb292e08d05a7d48069d7e64b27c7c8e0a55ba8a9c764a9de38d58","last_reissued_at":"2026-07-05T04:12:12.315630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:12.315630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.02785","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":"2026-07-05T04:12:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/Usr2+93NUpqEm2V6YD0Q9mLD/hiGNPVQE60AijEIND8lH87h30ocbGSI9oOjGCEEC7pZE0SvKMF6hGxA05Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:00:16.604789Z"},"content_sha256":"b970c00ef6bffe196aa7e81e20cdf985a4bfcaeb229a936cada2963be044c829","schema_version":"1.0","event_id":"sha256:b970c00ef6bffe196aa7e81e20cdf985a4bfcaeb229a936cada2963be044c829"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CNNQSMGEXMUS4CGQLJ6UQBU5PZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning Agents in Colonel Blotto","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Joseph Christian G. Noel","submitted_at":"2022-04-04T16:18:01Z","abstract_excerpt":"Models and games are simplified representations of the world. There are many different kinds of models, all differing in complexity and which aspect of the world they allow us to further our understanding of. In this paper we focus on a specific instance of agent-based models, which uses reinforcement learning (RL) to train the agent how to act in its environment. Reinforcement learning agents are usually also Markov processes, which is another type of model that can be used. We test this reinforcement learning agent in a Colonel Blotto environment1, and measure its performance against Random "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02785","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/2204.02785/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":"2026-07-05T04:12:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hb6u5U5fL7XkTOx0+Rz5+4IQ2/6dmYVBDRN7m/6JIiAtThzkbjzPaP+6T3DCN+eUwpQuafg5d9fD1tRleiLDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:00:16.605309Z"},"content_sha256":"f71e12231aeb632ac4b619ad1b4c17507335b2a0c50c6b3d7aa3982ec6e38025","schema_version":"1.0","event_id":"sha256:f71e12231aeb632ac4b619ad1b4c17507335b2a0c50c6b3d7aa3982ec6e38025"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNNQSMGEXMUS4CGQLJ6UQBU5PZ/bundle.json","state_url":"https://pith.science/pith/CNNQSMGEXMUS4CGQLJ6UQBU5PZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNNQSMGEXMUS4CGQLJ6UQBU5PZ/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":"2026-08-08T04:00:16Z","links":{"resolver":"https://pith.science/pith/CNNQSMGEXMUS4CGQLJ6UQBU5PZ","bundle":"https://pith.science/pith/CNNQSMGEXMUS4CGQLJ6UQBU5PZ/bundle.json","state":"https://pith.science/pith/CNNQSMGEXMUS4CGQLJ6UQBU5PZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNNQSMGEXMUS4CGQLJ6UQBU5PZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CNNQSMGEXMUS4CGQLJ6UQBU5PZ","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":"03c19b14a35b2331afb901a5bd05ac72dbcc0385fe2ea4a8280afa2220730cf9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-04-04T16:18:01Z","title_canon_sha256":"a3d9280045b655b40b4acccdda655762b688c359d1365644aa5c556e851f205f"},"schema_version":"1.0","source":{"id":"2204.02785","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02785","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02785v1","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02785","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"pith_short_12","alias_value":"CNNQSMGEXMUS","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"pith_short_16","alias_value":"CNNQSMGEXMUS4CGQ","created_at":"2026-07-05T04:12:12Z"},{"alias_kind":"pith_short_8","alias_value":"CNNQSMGE","created_at":"2026-07-05T04:12:12Z"}],"graph_snapshots":[{"event_id":"sha256:f71e12231aeb632ac4b619ad1b4c17507335b2a0c50c6b3d7aa3982ec6e38025","target":"graph","created_at":"2026-07-05T04:12:12Z","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/2204.02785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Models and games are simplified representations of the world. There are many different kinds of models, all differing in complexity and which aspect of the world they allow us to further our understanding of. In this paper we focus on a specific instance of agent-based models, which uses reinforcement learning (RL) to train the agent how to act in its environment. Reinforcement learning agents are usually also Markov processes, which is another type of model that can be used. We test this reinforcement learning agent in a Colonel Blotto environment1, and measure its performance against Random ","authors_text":"Joseph Christian G. Noel","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-04-04T16:18:01Z","title":"Reinforcement Learning Agents in Colonel Blotto"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02785","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:b970c00ef6bffe196aa7e81e20cdf985a4bfcaeb229a936cada2963be044c829","target":"record","created_at":"2026-07-05T04:12:12Z","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":"03c19b14a35b2331afb901a5bd05ac72dbcc0385fe2ea4a8280afa2220730cf9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-04-04T16:18:01Z","title_canon_sha256":"a3d9280045b655b40b4acccdda655762b688c359d1365644aa5c556e851f205f"},"schema_version":"1.0","source":{"id":"2204.02785","kind":"arxiv","version":1}},"canonical_sha256":"135b0930c4bb292e08d05a7d48069d7e64b27c7c8e0a55ba8a9c764a9de38d58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"135b0930c4bb292e08d05a7d48069d7e64b27c7c8e0a55ba8a9c764a9de38d58","first_computed_at":"2026-07-05T04:12:12.315630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:12.315630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b5sVUI+sZOYar6ULhVkiMZzKYK/QC5nPclw6ZR1L8NobXYA9nfAZKenk9ZWzd/R9pes8VQUDDP3vEJAySbIDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:12.316132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.02785","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b970c00ef6bffe196aa7e81e20cdf985a4bfcaeb229a936cada2963be044c829","sha256:f71e12231aeb632ac4b619ad1b4c17507335b2a0c50c6b3d7aa3982ec6e38025"],"state_sha256":"b7651eb4703cf6f62e3b090a210aee2629ed251ed7c49fedd08ce226a3141bba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8oE4mzomdbqbOQQvGVP8USIw6BYApG55aNUVvvOFS/NpZmUAQd3+1MLDd3gPFWABxvKs1AswfHed0NUw45dAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:00:16.610232Z","bundle_sha256":"e44ed73890896de2c4f02e487408b0f66f1c375a86626c8e1fe842b30dbb1fa3"}}