{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BDK5HC7OFU22BBJNWPIT2KGR3Y","short_pith_number":"pith:BDK5HC7O","canonical_record":{"source":{"id":"2605.16312","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T14:05:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80ecfccb5f2452e33b84923566c22da2265a873fbaf68f5a9f4f66ec5ad7c8b1","abstract_canon_sha256":"f4d3f5e8ff05fcd72738ba0511ce9713a8fb3f88e12bb7a888c4b657e3553db0"},"schema_version":"1.0"},"canonical_sha256":"08d5d38bee2d35a0852db3d13d28d1de399483807b9b6f9b03d9dddee605f561","source":{"kind":"arxiv","id":"2605.16312","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16312","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16312v1","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16312","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"BDK5HC7OFU22","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"BDK5HC7OFU22BBJN","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"BDK5HC7O","created_at":"2026-05-20T00:02:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BDK5HC7OFU22BBJNWPIT2KGR3Y","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16312","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T14:05:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80ecfccb5f2452e33b84923566c22da2265a873fbaf68f5a9f4f66ec5ad7c8b1","abstract_canon_sha256":"f4d3f5e8ff05fcd72738ba0511ce9713a8fb3f88e12bb7a888c4b657e3553db0"},"schema_version":"1.0"},"canonical_sha256":"08d5d38bee2d35a0852db3d13d28d1de399483807b9b6f9b03d9dddee605f561","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:16.531727Z","signature_b64":"oD/vOMd6B0Av1yCXpmIlFsf4YRi3KFQKVIGCydXtkDDlR5xPg+oo3xkk7Zf0WHoE368e+kOu1IOgfP3gXWC6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08d5d38bee2d35a0852db3d13d28d1de399483807b9b6f9b03d9dddee605f561","last_reissued_at":"2026-05-20T00:02:16.531146Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:16.531146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16312","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":"2026-05-20T00:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"13PwZ+D27uHnKWh4Zk286MJF2KN+XHB+EMzYMOGSsyi1hamLShepeaHgK63Fc5ywZTWu8eCKIGl/+o+W980NCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:47:09.800720Z"},"content_sha256":"06e4a431e3c052e97292dc4fb76d3cc0d96f91a0e9f22e5ef3c5a89d0d75ff5b","schema_version":"1.0","event_id":"sha256:06e4a431e3c052e97292dc4fb76d3cc0d96f91a0e9f22e5ef3c5a89d0d75ff5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BDK5HC7OFU22BBJNWPIT2KGR3Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arahan Kujur","submitted_at":"2026-05-04T14:05:39Z","abstract_excerpt":"We study adversarial action masking in self-play reinforcement learning: an attacker selectively removes legal actions from a victim's action set. Unlike observation or action perturbations, removal eliminates decision options before the agent acts. Across poker games scaling from 6 to 5,531 information states and two non-poker domains, learned masking causes substantially more damage than random masking and learned perturbation baselines. The attack persists across Q-learning, PPO, NFSP, neural NFSP, and DQN victims; transfers across agents; is amplified by self-play; and shows no recovery un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16312","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/2605.16312/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":"2026-05-20T00:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x2BgwktCM+rZczyjSa0+jridRuJ1hz7l6cXslgniWNS13nZTjeIiOs9wJUwhOW6Slkb7ZdwYEJjgU4XcfjHSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:47:09.801479Z"},"content_sha256":"7d9f7865a8749b9b3bba87fd2bcdb79cc5d21501b6f61e319fd0ccd4f5410901","schema_version":"1.0","event_id":"sha256:7d9f7865a8749b9b3bba87fd2bcdb79cc5d21501b6f61e319fd0ccd4f5410901"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BDK5HC7OFU22BBJNWPIT2KGR3Y/bundle.json","state_url":"https://pith.science/pith/BDK5HC7OFU22BBJNWPIT2KGR3Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BDK5HC7OFU22BBJNWPIT2KGR3Y/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":"2026-05-25T22:47:09Z","links":{"resolver":"https://pith.science/pith/BDK5HC7OFU22BBJNWPIT2KGR3Y","bundle":"https://pith.science/pith/BDK5HC7OFU22BBJNWPIT2KGR3Y/bundle.json","state":"https://pith.science/pith/BDK5HC7OFU22BBJNWPIT2KGR3Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BDK5HC7OFU22BBJNWPIT2KGR3Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BDK5HC7OFU22BBJNWPIT2KGR3Y","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":"f4d3f5e8ff05fcd72738ba0511ce9713a8fb3f88e12bb7a888c4b657e3553db0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T14:05:39Z","title_canon_sha256":"80ecfccb5f2452e33b84923566c22da2265a873fbaf68f5a9f4f66ec5ad7c8b1"},"schema_version":"1.0","source":{"id":"2605.16312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16312","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16312v1","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16312","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"BDK5HC7OFU22","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"BDK5HC7OFU22BBJN","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"BDK5HC7O","created_at":"2026-05-20T00:02:16Z"}],"graph_snapshots":[{"event_id":"sha256:7d9f7865a8749b9b3bba87fd2bcdb79cc5d21501b6f61e319fd0ccd4f5410901","target":"graph","created_at":"2026-05-20T00:02:16Z","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/2605.16312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study adversarial action masking in self-play reinforcement learning: an attacker selectively removes legal actions from a victim's action set. Unlike observation or action perturbations, removal eliminates decision options before the agent acts. Across poker games scaling from 6 to 5,531 information states and two non-poker domains, learned masking causes substantially more damage than random masking and learned perturbation baselines. The attack persists across Q-learning, PPO, NFSP, neural NFSP, and DQN victims; transfers across agents; is amplified by self-play; and shows no recovery un","authors_text":"Arahan Kujur","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T14:05:39Z","title":"When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16312","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":"sha256:06e4a431e3c052e97292dc4fb76d3cc0d96f91a0e9f22e5ef3c5a89d0d75ff5b","target":"record","created_at":"2026-05-20T00:02:16Z","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":"f4d3f5e8ff05fcd72738ba0511ce9713a8fb3f88e12bb7a888c4b657e3553db0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T14:05:39Z","title_canon_sha256":"80ecfccb5f2452e33b84923566c22da2265a873fbaf68f5a9f4f66ec5ad7c8b1"},"schema_version":"1.0","source":{"id":"2605.16312","kind":"arxiv","version":1}},"canonical_sha256":"08d5d38bee2d35a0852db3d13d28d1de399483807b9b6f9b03d9dddee605f561","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08d5d38bee2d35a0852db3d13d28d1de399483807b9b6f9b03d9dddee605f561","first_computed_at":"2026-05-20T00:02:16.531146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:16.531146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oD/vOMd6B0Av1yCXpmIlFsf4YRi3KFQKVIGCydXtkDDlR5xPg+oo3xkk7Zf0WHoE368e+kOu1IOgfP3gXWC6CQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:16.531727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06e4a431e3c052e97292dc4fb76d3cc0d96f91a0e9f22e5ef3c5a89d0d75ff5b","sha256:7d9f7865a8749b9b3bba87fd2bcdb79cc5d21501b6f61e319fd0ccd4f5410901"],"state_sha256":"d4c3843a26708a483d2cfd468c2698fb92fa0bc5ea1511ed5bbe3b75de16b0f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H8MtRPxU7FOPuPpzWu+Hh+rNtdqrmzmsL6R6zG3TgBEHlYEYYOtFAZvpaYk2UotinS+Ng5pr3Vu1pIaa4bgsDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:47:09.805253Z","bundle_sha256":"5a6e5c670b76dd4b5f0d4000b0bbfe98c548ab42e6b9942ebe74b7e26bc60c18"}}