{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:O644I7OLWL3GAWVYUNSM2B26EO","short_pith_number":"pith:O644I7OL","canonical_record":{"source":{"id":"1806.05117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T15:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"f6b8ff83ba7d73a0826a5526254e2ff9df550752d6ee63570ea5cc769039ebf8","abstract_canon_sha256":"31d0a01e7a35c0f6cdec38f007b2cd4ca5003402b80e5e5e5bacb732b867a683"},"schema_version":"1.0"},"canonical_sha256":"77b9c47dcbb2f6605ab8a364cd075e23a30b9125fd68cce060dc748878c27796","source":{"kind":"arxiv","id":"1806.05117","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05117","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05117v1","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05117","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"O644I7OLWL3G","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"O644I7OLWL3GAWVY","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"O644I7OL","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:O644I7OLWL3GAWVYUNSM2B26EO","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T15:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"f6b8ff83ba7d73a0826a5526254e2ff9df550752d6ee63570ea5cc769039ebf8","abstract_canon_sha256":"31d0a01e7a35c0f6cdec38f007b2cd4ca5003402b80e5e5e5bacb732b867a683"},"schema_version":"1.0"},"canonical_sha256":"77b9c47dcbb2f6605ab8a364cd075e23a30b9125fd68cce060dc748878c27796","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:20.095566Z","signature_b64":"WP5J/13wBKytIDYHEAe9TtRi2iqf0NbXq6V9olM8ir+FAcCfIlMZgZU53QY5IQyGR+ChAxnUUtgv6gLc2206AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77b9c47dcbb2f6605ab8a364cd075e23a30b9125fd68cce060dc748878c27796","last_reissued_at":"2026-05-18T00:13:20.094931Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:20.094931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05117","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":"2026-05-18T00:13:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WbGfO4UAtiQBbFQ07hfGX1HhV5riASv1J4g/jN3Mju+zjrpNhp/6+8j+9GErQseeis6/9UGa/ioeNSAFRKrXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T09:36:44.909424Z"},"content_sha256":"2d9e0801ec0f1645c260e9d1d96c547c8b87e04df05cb8d507aa13f584ccfd1c","schema_version":"1.0","event_id":"sha256:2d9e0801ec0f1645c260e9d1d96c547c8b87e04df05cb8d507aa13f584ccfd1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:O644I7OLWL3GAWVYUNSM2B26EO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Shoot in First Person Shooter Games by Stabilizing Actions and Clustering Rewards for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Frank G. Glavin, Michael G. Madden","submitted_at":"2018-06-13T15:41:34Z","abstract_excerpt":"While reinforcement learning (RL) has been applied to turn-based board games for many years, more complex games involving decision-making in real-time are beginning to receive more attention. A challenge in such environments is that the time that elapses between deciding to take an action and receiving a reward based on its outcome can be longer than the interval between successive decisions. We explore this in the context of a non-player character (NPC) in a modern first-person shooter game. Such games take place in 3D environments where players, both human and computer-controlled, compete by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05117","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":""},"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":"2026-05-18T00:13:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UfaSFmiauWFlf65h+gEiNbgCEFX02huwqpDMX050I0LeC1Z0XaS+T/cB9UWQXyIAvQd0HBFCiFneJW+eNsgDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T09:36:44.909787Z"},"content_sha256":"3d6b0020da0fc11c293c801f12c0d67a6db51c9432fb02c48b296e65d4502af4","schema_version":"1.0","event_id":"sha256:3d6b0020da0fc11c293c801f12c0d67a6db51c9432fb02c48b296e65d4502af4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO/bundle.json","state_url":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O644I7OLWL3GAWVYUNSM2B26EO/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":"2026-07-25T09:36:44Z","links":{"resolver":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO","bundle":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO/bundle.json","state":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O644I7OLWL3GAWVYUNSM2B26EO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:O644I7OLWL3GAWVYUNSM2B26EO","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":"31d0a01e7a35c0f6cdec38f007b2cd4ca5003402b80e5e5e5bacb732b867a683","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T15:41:34Z","title_canon_sha256":"f6b8ff83ba7d73a0826a5526254e2ff9df550752d6ee63570ea5cc769039ebf8"},"schema_version":"1.0","source":{"id":"1806.05117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05117","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05117v1","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05117","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"O644I7OLWL3G","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"O644I7OLWL3GAWVY","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"O644I7OL","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:3d6b0020da0fc11c293c801f12c0d67a6db51c9432fb02c48b296e65d4502af4","target":"graph","created_at":"2026-05-18T00:13:20Z","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"},"paper":{"abstract_excerpt":"While reinforcement learning (RL) has been applied to turn-based board games for many years, more complex games involving decision-making in real-time are beginning to receive more attention. A challenge in such environments is that the time that elapses between deciding to take an action and receiving a reward based on its outcome can be longer than the interval between successive decisions. We explore this in the context of a non-player character (NPC) in a modern first-person shooter game. Such games take place in 3D environments where players, both human and computer-controlled, compete by","authors_text":"Frank G. Glavin, Michael G. Madden","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T15:41:34Z","title":"Learning to Shoot in First Person Shooter Games by Stabilizing Actions and Clustering Rewards for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05117","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":"sha256:2d9e0801ec0f1645c260e9d1d96c547c8b87e04df05cb8d507aa13f584ccfd1c","target":"record","created_at":"2026-05-18T00:13:20Z","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":"31d0a01e7a35c0f6cdec38f007b2cd4ca5003402b80e5e5e5bacb732b867a683","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T15:41:34Z","title_canon_sha256":"f6b8ff83ba7d73a0826a5526254e2ff9df550752d6ee63570ea5cc769039ebf8"},"schema_version":"1.0","source":{"id":"1806.05117","kind":"arxiv","version":1}},"canonical_sha256":"77b9c47dcbb2f6605ab8a364cd075e23a30b9125fd68cce060dc748878c27796","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77b9c47dcbb2f6605ab8a364cd075e23a30b9125fd68cce060dc748878c27796","first_computed_at":"2026-05-18T00:13:20.094931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:20.094931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WP5J/13wBKytIDYHEAe9TtRi2iqf0NbXq6V9olM8ir+FAcCfIlMZgZU53QY5IQyGR+ChAxnUUtgv6gLc2206AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:20.095566Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d9e0801ec0f1645c260e9d1d96c547c8b87e04df05cb8d507aa13f584ccfd1c","sha256:3d6b0020da0fc11c293c801f12c0d67a6db51c9432fb02c48b296e65d4502af4"],"state_sha256":"d69fcd326ba815db195ddcf32693fff1986320840c4f79910d31751691728cea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s84bA/yxU8u9GsgEqoZcWikHelN3XJ1jy9RJ9knds0TeIywdnsVpZT3S1xu+gS5RqfhAEqiG+IJHCDUVczaECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T09:36:44.911946Z","bundle_sha256":"b073fe30490a46db817c31c107e4940ea28384a55ce04216381ab6d5590d19cf"}}