{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZXPSAPNH7KNNTLVY6IMZZ5JQ57","short_pith_number":"pith:ZXPSAPNH","canonical_record":{"source":{"id":"2012.02671","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-12-04T15:41:07Z","cross_cats_sorted":["cs.GT","cs.LG"],"title_canon_sha256":"71ee596f876bd7900d09138ae6b0b51b4b66c370106ebe0cdac1e4a1644be587","abstract_canon_sha256":"b3a27a53b94afbd4ac1ea7a250c218474d0fe55706561c96f1ca22092dd129c5"},"schema_version":"1.0"},"canonical_sha256":"cddf203da7fa9ad9aeb8f2199cf530efe0303d72546a72c2537eb2254767d9aa","source":{"kind":"arxiv","id":"2012.02671","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02671","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02671v2","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02671","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZXPSAPNH7KNN","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZXPSAPNH7KNNTLVY","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZXPSAPNH","created_at":"2026-07-05T03:07:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZXPSAPNH7KNNTLVY6IMZZ5JQ57","target":"record","payload":{"canonical_record":{"source":{"id":"2012.02671","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-12-04T15:41:07Z","cross_cats_sorted":["cs.GT","cs.LG"],"title_canon_sha256":"71ee596f876bd7900d09138ae6b0b51b4b66c370106ebe0cdac1e4a1644be587","abstract_canon_sha256":"b3a27a53b94afbd4ac1ea7a250c218474d0fe55706561c96f1ca22092dd129c5"},"schema_version":"1.0"},"canonical_sha256":"cddf203da7fa9ad9aeb8f2199cf530efe0303d72546a72c2537eb2254767d9aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:26.613828Z","signature_b64":"Z6BMD6IEpfd84Di/JAf4AaihsVnTKZISfjrKiEGEvtxMpPJd1zFvz9vOuNXG5mGx/CERzMOKXUqUqXzDsWz2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cddf203da7fa9ad9aeb8f2199cf530efe0303d72546a72c2537eb2254767d9aa","last_reissued_at":"2026-07-05T03:07:26.613418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:26.613418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.02671","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:07:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dyCCUEXc/c3xJPwy3P2AiEtKcVd8D/+IuzxbE/LFqZS4eOyiQWBDZyJOwSUD28ZjQqgeXTBQhOUwyYCCvZroBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:04:42.312743Z"},"content_sha256":"aeb77ee4303461fcb5389a93a3eada18149fc60d9ede0fc4af7e99965e4e7ee5","schema_version":"1.0","event_id":"sha256:aeb77ee4303461fcb5389a93a3eada18149fc60d9ede0fc4af7e99965e4e7ee5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZXPSAPNH7KNNTLVY6IMZZ5JQ57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning in two-player games between transparent opponents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"cs.AI","authors_text":"Adrian Hutter","submitted_at":"2020-12-04T15:41:07Z","abstract_excerpt":"We consider a scenario in which two reinforcement learning agents repeatedly play a matrix game against each other and update their parameters after each round. The agents' decision-making is transparent to each other, which allows each agent to predict how their opponent will play against them. To prevent an infinite regress of both agents recursively predicting each other indefinitely, each agent is required to give an opponent-independent response with some probability at least epsilon. Transparency also allows each agent to anticipate and shape the other agent's gradient step, i.e. to move"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02671","kind":"arxiv","version":2},"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/2012.02671/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":"2026-07-05T03:07:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"umy79rCTrQc6zmhMQ2HvmexxVftLv/VXHYDm+totiXPHUA2nLqOM7wcr8dTwLBapwMsMCpBQ2AWtEbGN845WAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:04:42.313264Z"},"content_sha256":"293df9b8f748f2024e735a63add6b070ec62c62f73da57a2c101865ca932b9c4","schema_version":"1.0","event_id":"sha256:293df9b8f748f2024e735a63add6b070ec62c62f73da57a2c101865ca932b9c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZXPSAPNH7KNNTLVY6IMZZ5JQ57/bundle.json","state_url":"https://pith.science/pith/ZXPSAPNH7KNNTLVY6IMZZ5JQ57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZXPSAPNH7KNNTLVY6IMZZ5JQ57/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":"2026-08-03T22:04:42Z","links":{"resolver":"https://pith.science/pith/ZXPSAPNH7KNNTLVY6IMZZ5JQ57","bundle":"https://pith.science/pith/ZXPSAPNH7KNNTLVY6IMZZ5JQ57/bundle.json","state":"https://pith.science/pith/ZXPSAPNH7KNNTLVY6IMZZ5JQ57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZXPSAPNH7KNNTLVY6IMZZ5JQ57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZXPSAPNH7KNNTLVY6IMZZ5JQ57","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":"b3a27a53b94afbd4ac1ea7a250c218474d0fe55706561c96f1ca22092dd129c5","cross_cats_sorted":["cs.GT","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-12-04T15:41:07Z","title_canon_sha256":"71ee596f876bd7900d09138ae6b0b51b4b66c370106ebe0cdac1e4a1644be587"},"schema_version":"1.0","source":{"id":"2012.02671","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02671","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02671v2","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02671","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZXPSAPNH7KNN","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZXPSAPNH7KNNTLVY","created_at":"2026-07-05T03:07:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZXPSAPNH","created_at":"2026-07-05T03:07:26Z"}],"graph_snapshots":[{"event_id":"sha256:293df9b8f748f2024e735a63add6b070ec62c62f73da57a2c101865ca932b9c4","target":"graph","created_at":"2026-07-05T03:07:26Z","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/2012.02671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a scenario in which two reinforcement learning agents repeatedly play a matrix game against each other and update their parameters after each round. The agents' decision-making is transparent to each other, which allows each agent to predict how their opponent will play against them. To prevent an infinite regress of both agents recursively predicting each other indefinitely, each agent is required to give an opponent-independent response with some probability at least epsilon. Transparency also allows each agent to anticipate and shape the other agent's gradient step, i.e. to move","authors_text":"Adrian Hutter","cross_cats":["cs.GT","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-12-04T15:41:07Z","title":"Learning in two-player games between transparent opponents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02671","kind":"arxiv","version":2},"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:aeb77ee4303461fcb5389a93a3eada18149fc60d9ede0fc4af7e99965e4e7ee5","target":"record","created_at":"2026-07-05T03:07:26Z","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":"b3a27a53b94afbd4ac1ea7a250c218474d0fe55706561c96f1ca22092dd129c5","cross_cats_sorted":["cs.GT","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-12-04T15:41:07Z","title_canon_sha256":"71ee596f876bd7900d09138ae6b0b51b4b66c370106ebe0cdac1e4a1644be587"},"schema_version":"1.0","source":{"id":"2012.02671","kind":"arxiv","version":2}},"canonical_sha256":"cddf203da7fa9ad9aeb8f2199cf530efe0303d72546a72c2537eb2254767d9aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cddf203da7fa9ad9aeb8f2199cf530efe0303d72546a72c2537eb2254767d9aa","first_computed_at":"2026-07-05T03:07:26.613418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:07:26.613418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z6BMD6IEpfd84Di/JAf4AaihsVnTKZISfjrKiEGEvtxMpPJd1zFvz9vOuNXG5mGx/CERzMOKXUqUqXzDsWz2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:07:26.613828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02671","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aeb77ee4303461fcb5389a93a3eada18149fc60d9ede0fc4af7e99965e4e7ee5","sha256:293df9b8f748f2024e735a63add6b070ec62c62f73da57a2c101865ca932b9c4"],"state_sha256":"fb22e385993a55f93a868de3a21884171f74e83ad4c14e15740cd99e58f2b3e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nQxFFQ2IPwFDuQ8M8xGueRZrIaTUxbfu7wBFd+NTp7dE0HuNmhWGZitM14x7fZVORrHlPuvh5yaFVKha3iuMBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:04:42.318410Z","bundle_sha256":"1529766add36888fb8eb2c610ab57dc4a159e6f2a8c2d481c68e98b5a69325b7"}}