{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RYROPWKQ7MAQF3IU5IEZNPOYHM","short_pith_number":"pith:RYROPWKQ","canonical_record":{"source":{"id":"1805.06824","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-17T15:36:42Z","cross_cats_sorted":[],"title_canon_sha256":"0bee9700e9563a7c43e1f453cce140609b0c98aa77662a920cc5acc1c98ac6c7","abstract_canon_sha256":"dcbb771b8227d302f413ee0914e0b10fbe656ce8c3cec2ea6b3ad8cbc67e5aa6"},"schema_version":"1.0"},"canonical_sha256":"8e22e7d950fb0102ed14ea0996bdd83b1c77ad2175327ae8ed3068f0148d7035","source":{"kind":"arxiv","id":"1805.06824","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.06824","created_at":"2026-05-18T00:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"1805.06824v4","created_at":"2026-05-18T00:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06824","created_at":"2026-05-18T00:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"RYROPWKQ7MAQ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RYROPWKQ7MAQF3IU","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RYROPWKQ","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RYROPWKQ7MAQF3IU5IEZNPOYHM","target":"record","payload":{"canonical_record":{"source":{"id":"1805.06824","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-17T15:36:42Z","cross_cats_sorted":[],"title_canon_sha256":"0bee9700e9563a7c43e1f453cce140609b0c98aa77662a920cc5acc1c98ac6c7","abstract_canon_sha256":"dcbb771b8227d302f413ee0914e0b10fbe656ce8c3cec2ea6b3ad8cbc67e5aa6"},"schema_version":"1.0"},"canonical_sha256":"8e22e7d950fb0102ed14ea0996bdd83b1c77ad2175327ae8ed3068f0148d7035","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:45.507963Z","signature_b64":"VKy4Ccu3huAXc76QDWU9nfOaAbEIhi9oK4k7a32LfD+tkCr3odMS5mrKQzNR0gFes17MmbcsmjXjF/O+OH+zAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e22e7d950fb0102ed14ea0996bdd83b1c77ad2175327ae8ed3068f0148d7035","last_reissued_at":"2026-05-18T00:05:45.507278Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:45.507278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.06824","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JAOcz01oEXiZxs/ctJyMZMYC6vcRmI04Y7OgwmdjZc7hLrfauwxkvEVJECgottsFndjfu6cNPh1eG2iuoxP5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:12:24.949176Z"},"content_sha256":"f2c20e6ea3432e1d995443ce43b5aa7d3fcbb91e148e5356cd5621857dd6d2a4","schema_version":"1.0","event_id":"sha256:f2c20e6ea3432e1d995443ce43b5aa7d3fcbb91e148e5356cd5621857dd6d2a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RYROPWKQ7MAQF3IU5IEZNPOYHM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Time-Sensitive Strategies in Space Fortress","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akshat Agarwal, Katia Sycara, Ryan Hope","submitted_at":"2018-05-17T15:36:42Z","abstract_excerpt":"Although there has been remarkable progress and impressive performance on reinforcement learning (RL) on Atari games, there are many problems with challenging characteristics that have not yet been explored in Deep Learning for RL. These include reward sparsity, abrupt context-dependent reversals of strategy and time-sensitive game play. In this paper, we present Space Fortress, a game that incorporates all these characteristics and experimentally show that the presence of any of these renders state of the art Deep RL algorithms incapable of learning. Then, we present our enhancements to an ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06824","kind":"arxiv","version":4},"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":"2026-05-18T00:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++kj/KUfEhZkBplngqOGQnTYqwY/Mcwpebv4RaS/39rWeQT26CyF6P5+YDvjxUNE67I6nba/NQc8i/pEE2dRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:12:24.949837Z"},"content_sha256":"737f9b6da51a5a0b6a4884e03e1c0ade855402e6be8646abf2b7d4362ab377ff","schema_version":"1.0","event_id":"sha256:737f9b6da51a5a0b6a4884e03e1c0ade855402e6be8646abf2b7d4362ab377ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RYROPWKQ7MAQF3IU5IEZNPOYHM/bundle.json","state_url":"https://pith.science/pith/RYROPWKQ7MAQF3IU5IEZNPOYHM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RYROPWKQ7MAQF3IU5IEZNPOYHM/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":"2026-05-27T22:12:24Z","links":{"resolver":"https://pith.science/pith/RYROPWKQ7MAQF3IU5IEZNPOYHM","bundle":"https://pith.science/pith/RYROPWKQ7MAQF3IU5IEZNPOYHM/bundle.json","state":"https://pith.science/pith/RYROPWKQ7MAQF3IU5IEZNPOYHM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RYROPWKQ7MAQF3IU5IEZNPOYHM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RYROPWKQ7MAQF3IU5IEZNPOYHM","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":"dcbb771b8227d302f413ee0914e0b10fbe656ce8c3cec2ea6b3ad8cbc67e5aa6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-17T15:36:42Z","title_canon_sha256":"0bee9700e9563a7c43e1f453cce140609b0c98aa77662a920cc5acc1c98ac6c7"},"schema_version":"1.0","source":{"id":"1805.06824","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.06824","created_at":"2026-05-18T00:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"1805.06824v4","created_at":"2026-05-18T00:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06824","created_at":"2026-05-18T00:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"RYROPWKQ7MAQ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RYROPWKQ7MAQF3IU","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RYROPWKQ","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:737f9b6da51a5a0b6a4884e03e1c0ade855402e6be8646abf2b7d4362ab377ff","target":"graph","created_at":"2026-05-18T00:05:45Z","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":"Although there has been remarkable progress and impressive performance on reinforcement learning (RL) on Atari games, there are many problems with challenging characteristics that have not yet been explored in Deep Learning for RL. These include reward sparsity, abrupt context-dependent reversals of strategy and time-sensitive game play. In this paper, we present Space Fortress, a game that incorporates all these characteristics and experimentally show that the presence of any of these renders state of the art Deep RL algorithms incapable of learning. Then, we present our enhancements to an ex","authors_text":"Akshat Agarwal, Katia Sycara, Ryan Hope","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-17T15:36:42Z","title":"Learning Time-Sensitive Strategies in Space Fortress"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06824","kind":"arxiv","version":4},"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:f2c20e6ea3432e1d995443ce43b5aa7d3fcbb91e148e5356cd5621857dd6d2a4","target":"record","created_at":"2026-05-18T00:05:45Z","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":"dcbb771b8227d302f413ee0914e0b10fbe656ce8c3cec2ea6b3ad8cbc67e5aa6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-17T15:36:42Z","title_canon_sha256":"0bee9700e9563a7c43e1f453cce140609b0c98aa77662a920cc5acc1c98ac6c7"},"schema_version":"1.0","source":{"id":"1805.06824","kind":"arxiv","version":4}},"canonical_sha256":"8e22e7d950fb0102ed14ea0996bdd83b1c77ad2175327ae8ed3068f0148d7035","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e22e7d950fb0102ed14ea0996bdd83b1c77ad2175327ae8ed3068f0148d7035","first_computed_at":"2026-05-18T00:05:45.507278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:45.507278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VKy4Ccu3huAXc76QDWU9nfOaAbEIhi9oK4k7a32LfD+tkCr3odMS5mrKQzNR0gFes17MmbcsmjXjF/O+OH+zAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:45.507963Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.06824","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2c20e6ea3432e1d995443ce43b5aa7d3fcbb91e148e5356cd5621857dd6d2a4","sha256:737f9b6da51a5a0b6a4884e03e1c0ade855402e6be8646abf2b7d4362ab377ff"],"state_sha256":"c38a3271f73a164c4595494a6ba25f7aeef59e620636aa179191087dd2c52802"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ISTZjOPCzKp/xhxfitz4kT31NiiR+bHR/g/9S8wJbYCnL2FQaLEXzjLTOo+nlLMBYlmCan0/1IfjjpG18NafCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:12:24.953384Z","bundle_sha256":"5cf0ca8e53b0500cff5f9c715ef471f503734c606858572a047f899dc67defbd"}}