{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M4NAEV5OKKVDDB4Z3U6JZLPH27","short_pith_number":"pith:M4NAEV5O","canonical_record":{"source":{"id":"2605.28863","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T21:56:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3391501e007ae9f66f7dec54814b8dca98afa14c061b8841159b260a4d648e4e","abstract_canon_sha256":"553b7c5fbb36113dd893986b1e8e909eade5b4f0abbe5b81f563f1ce5b0c4483"},"schema_version":"1.0"},"canonical_sha256":"671a0257ae52aa318799dd3c9cade7d7ea0fb88ceb7ee6f6f37a6a4f2226c584","source":{"kind":"arxiv","id":"2605.28863","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28863","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28863v1","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28863","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"M4NAEV5OKKVD","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"M4NAEV5OKKVDDB4Z","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"M4NAEV5O","created_at":"2026-05-29T00:04:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M4NAEV5OKKVDDB4Z3U6JZLPH27","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28863","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T21:56:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3391501e007ae9f66f7dec54814b8dca98afa14c061b8841159b260a4d648e4e","abstract_canon_sha256":"553b7c5fbb36113dd893986b1e8e909eade5b4f0abbe5b81f563f1ce5b0c4483"},"schema_version":"1.0"},"canonical_sha256":"671a0257ae52aa318799dd3c9cade7d7ea0fb88ceb7ee6f6f37a6a4f2226c584","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:14.627909Z","signature_b64":"BqDUS18ZDgOT2Nb4cRsizWfIyImSLhcRRbTqZtwZtwIvg8ltg+RmG0eC3C566SGx9kTkUAnWsDnVWzXKhbPUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"671a0257ae52aa318799dd3c9cade7d7ea0fb88ceb7ee6f6f37a6a4f2226c584","last_reissued_at":"2026-05-29T00:04:14.627489Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:14.627489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28863","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":"2026-05-29T00:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lUL5TqXGIQOtIi27uZ5HGTHsOg7eWHD92USejWNQXztPDBapsxjzgfD5qUr05pT2/io41j71yK5uUzxETYu7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T01:42:38.172519Z"},"content_sha256":"ac11b081d7cf6a3fbb6552f5b9a8f4cdfe795d0ac5de5d6ff14e14774803c3dd","schema_version":"1.0","event_id":"sha256:ac11b081d7cf6a3fbb6552f5b9a8f4cdfe795d0ac5de5d6ff14e14774803c3dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M4NAEV5OKKVDDB4Z3U6JZLPH27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Play Reinforcement Learning under Imperfect Information in Big 2","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aalok Patwa","submitted_at":"2026-05-21T21:56:09Z","abstract_excerpt":"Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents. We study these challenges in Big 2, a four-player imperfect-information card game. We develop a self-play RL framework for Big 2 that enables controlled comparisons between policy-gradient and value-approximating agents. Under a common environment, input representation, training budget, and evaluation protocol, PPO outperforms Monte Carlo Q approximation, SARSA, and Q-learning against random, greedy, and heuristic Big 2 opponents. We further find that mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28863","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/2605.28863/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":"2026-05-29T00:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U7QfuTmbRqV06uWP3Qm4qkz/cggDRvHXGbXtRoKqaH5Ie9+SV9+wY6WX2dUvrDqmDJFWm+FqSmY6U4W39dZRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T01:42:38.172896Z"},"content_sha256":"43d2e8e5c8701aca54701fc019b46f86f3a7abe0f176be179d032d3fc12b9d4d","schema_version":"1.0","event_id":"sha256:43d2e8e5c8701aca54701fc019b46f86f3a7abe0f176be179d032d3fc12b9d4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/bundle.json","state_url":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/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":"2026-07-01T01:42:38Z","links":{"resolver":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27","bundle":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/bundle.json","state":"https://pith.science/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M4NAEV5OKKVDDB4Z3U6JZLPH27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M4NAEV5OKKVDDB4Z3U6JZLPH27","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":"553b7c5fbb36113dd893986b1e8e909eade5b4f0abbe5b81f563f1ce5b0c4483","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T21:56:09Z","title_canon_sha256":"3391501e007ae9f66f7dec54814b8dca98afa14c061b8841159b260a4d648e4e"},"schema_version":"1.0","source":{"id":"2605.28863","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28863","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28863v1","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28863","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"M4NAEV5OKKVD","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"M4NAEV5OKKVDDB4Z","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"M4NAEV5O","created_at":"2026-05-29T00:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:43d2e8e5c8701aca54701fc019b46f86f3a7abe0f176be179d032d3fc12b9d4d","target":"graph","created_at":"2026-05-29T00:04:14Z","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/2605.28863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents. We study these challenges in Big 2, a four-player imperfect-information card game. We develop a self-play RL framework for Big 2 that enables controlled comparisons between policy-gradient and value-approximating agents. Under a common environment, input representation, training budget, and evaluation protocol, PPO outperforms Monte Carlo Q approximation, SARSA, and Q-learning against random, greedy, and heuristic Big 2 opponents. We further find that mode","authors_text":"Aalok Patwa","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T21:56:09Z","title":"Self-Play Reinforcement Learning under Imperfect Information in Big 2"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28863","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:ac11b081d7cf6a3fbb6552f5b9a8f4cdfe795d0ac5de5d6ff14e14774803c3dd","target":"record","created_at":"2026-05-29T00:04:14Z","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":"553b7c5fbb36113dd893986b1e8e909eade5b4f0abbe5b81f563f1ce5b0c4483","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T21:56:09Z","title_canon_sha256":"3391501e007ae9f66f7dec54814b8dca98afa14c061b8841159b260a4d648e4e"},"schema_version":"1.0","source":{"id":"2605.28863","kind":"arxiv","version":1}},"canonical_sha256":"671a0257ae52aa318799dd3c9cade7d7ea0fb88ceb7ee6f6f37a6a4f2226c584","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"671a0257ae52aa318799dd3c9cade7d7ea0fb88ceb7ee6f6f37a6a4f2226c584","first_computed_at":"2026-05-29T00:04:14.627489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T00:04:14.627489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BqDUS18ZDgOT2Nb4cRsizWfIyImSLhcRRbTqZtwZtwIvg8ltg+RmG0eC3C566SGx9kTkUAnWsDnVWzXKhbPUBg==","signature_status":"signed_v1","signed_at":"2026-05-29T00:04:14.627909Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28863","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac11b081d7cf6a3fbb6552f5b9a8f4cdfe795d0ac5de5d6ff14e14774803c3dd","sha256:43d2e8e5c8701aca54701fc019b46f86f3a7abe0f176be179d032d3fc12b9d4d"],"state_sha256":"fe4177962a767b3c65ebbe94922de85361e6e3d3646f67e99a4fcc2b069fc17d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m9jzTakLcl/GMDbZjjeblbnbXjB1S94XLoDu8AHYez6FjI1j0r3VsAOr337GzjKz2Db3SkS2RIXw1N4ufx6bDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T01:42:38.174930Z","bundle_sha256":"b27390f3dc201b5cdf49d2b90637354f602317ca2e0dd20e4aad5907c1acf2cc"}}