{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:S5APEEIT6UAHNRKG7LSKDENZ7T","short_pith_number":"pith:S5APEEIT","canonical_record":{"source":{"id":"2112.01328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T09:37:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2466126252030dd763157dbadba4751a9cec39e883c4af622d67c611dc24a75a","abstract_canon_sha256":"ea12a8062ff278de23eef0bfb7b66ebbae1f9aab66d59410891d3f73ac32c8d5"},"schema_version":"1.0"},"canonical_sha256":"9740f21113f50076c546fae4a191b9fcc0e5fad80eece0805115cf2decbdf717","source":{"kind":"arxiv","id":"2112.01328","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01328","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01328v1","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01328","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"pith_short_12","alias_value":"S5APEEIT6UAH","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"pith_short_16","alias_value":"S5APEEIT6UAHNRKG","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"pith_short_8","alias_value":"S5APEEIT","created_at":"2026-07-05T03:37:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:S5APEEIT6UAHNRKG7LSKDENZ7T","target":"record","payload":{"canonical_record":{"source":{"id":"2112.01328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T09:37:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2466126252030dd763157dbadba4751a9cec39e883c4af622d67c611dc24a75a","abstract_canon_sha256":"ea12a8062ff278de23eef0bfb7b66ebbae1f9aab66d59410891d3f73ac32c8d5"},"schema_version":"1.0"},"canonical_sha256":"9740f21113f50076c546fae4a191b9fcc0e5fad80eece0805115cf2decbdf717","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:08.288270Z","signature_b64":"vMVbkGhLZg7gWVqMMLTci7TrN0IZo9LKcfkb8ZeyGx7W+x3KQN4nNCsPbFTUXTl+xvqnyChrgE4kclzgCwI3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9740f21113f50076c546fae4a191b9fcc0e5fad80eece0805115cf2decbdf717","last_reissued_at":"2026-07-05T03:37:08.287906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:08.287906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.01328","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":"2026-07-05T03:37:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/YON4QBH/RlJ62XVEenKqgYNzBBtnx3s5WlpBDk/eyf4xCE7/6Pdn7Lkc2a07TstKg2ef73X95ojH9KgHx00Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:39:46.525036Z"},"content_sha256":"679262042629afe85f000ea3e4b910de1a50df7774cda13d09e1118376f4ebd4","schema_version":"1.0","event_id":"sha256:679262042629afe85f000ea3e4b910de1a50df7774cda13d09e1118376f4ebd4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:S5APEEIT6UAHNRKG7LSKDENZ7T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Homotopy Based Reinforcement Learning with Maximum Entropy for Autonomous Air Combat","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Wenya Wei, Yiwen Zhu, Yuan Zheng, Zhou Fang","submitted_at":"2021-12-01T09:37:55Z","abstract_excerpt":"The Intelligent decision of the unmanned combat aerial vehicle (UCAV) has long been a challenging problem. The conventional search method can hardly satisfy the real-time demand during high dynamics air combat scenarios. The reinforcement learning (RL) method can significantly shorten the decision time via using neural networks. However, the sparse reward problem limits its convergence speed and the artificial prior experience reward can easily deviate its optimal convergent direction of the original task, which raises great difficulties for the RL air combat application. In this paper, we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01328","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/2112.01328/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":"2026-07-05T03:37:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UON1dGaZOaFICvPWW/Kn2miwgoBrHzUMTixokgzPe18lgw5Qc1JtbZp5/1DXF6iEF/C0WpM0dm210cTaH9E0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:39:46.525574Z"},"content_sha256":"807ba277beb566777ed76a4a59a2e999e54edd62c2c0568b9625f17bd352619a","schema_version":"1.0","event_id":"sha256:807ba277beb566777ed76a4a59a2e999e54edd62c2c0568b9625f17bd352619a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S5APEEIT6UAHNRKG7LSKDENZ7T/bundle.json","state_url":"https://pith.science/pith/S5APEEIT6UAHNRKG7LSKDENZ7T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S5APEEIT6UAHNRKG7LSKDENZ7T/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":"2026-08-21T15:39:46Z","links":{"resolver":"https://pith.science/pith/S5APEEIT6UAHNRKG7LSKDENZ7T","bundle":"https://pith.science/pith/S5APEEIT6UAHNRKG7LSKDENZ7T/bundle.json","state":"https://pith.science/pith/S5APEEIT6UAHNRKG7LSKDENZ7T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S5APEEIT6UAHNRKG7LSKDENZ7T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:S5APEEIT6UAHNRKG7LSKDENZ7T","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":"ea12a8062ff278de23eef0bfb7b66ebbae1f9aab66d59410891d3f73ac32c8d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T09:37:55Z","title_canon_sha256":"2466126252030dd763157dbadba4751a9cec39e883c4af622d67c611dc24a75a"},"schema_version":"1.0","source":{"id":"2112.01328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01328","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01328v1","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01328","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"pith_short_12","alias_value":"S5APEEIT6UAH","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"pith_short_16","alias_value":"S5APEEIT6UAHNRKG","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"pith_short_8","alias_value":"S5APEEIT","created_at":"2026-07-05T03:37:08Z"}],"graph_snapshots":[{"event_id":"sha256:807ba277beb566777ed76a4a59a2e999e54edd62c2c0568b9625f17bd352619a","target":"graph","created_at":"2026-07-05T03:37:08Z","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/2112.01328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Intelligent decision of the unmanned combat aerial vehicle (UCAV) has long been a challenging problem. The conventional search method can hardly satisfy the real-time demand during high dynamics air combat scenarios. The reinforcement learning (RL) method can significantly shorten the decision time via using neural networks. However, the sparse reward problem limits its convergence speed and the artificial prior experience reward can easily deviate its optimal convergent direction of the original task, which raises great difficulties for the RL air combat application. In this paper, we pro","authors_text":"Wenya Wei, Yiwen Zhu, Yuan Zheng, Zhou Fang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T09:37:55Z","title":"Homotopy Based Reinforcement Learning with Maximum Entropy for Autonomous Air Combat"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01328","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":"sha256:679262042629afe85f000ea3e4b910de1a50df7774cda13d09e1118376f4ebd4","target":"record","created_at":"2026-07-05T03:37:08Z","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":"ea12a8062ff278de23eef0bfb7b66ebbae1f9aab66d59410891d3f73ac32c8d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T09:37:55Z","title_canon_sha256":"2466126252030dd763157dbadba4751a9cec39e883c4af622d67c611dc24a75a"},"schema_version":"1.0","source":{"id":"2112.01328","kind":"arxiv","version":1}},"canonical_sha256":"9740f21113f50076c546fae4a191b9fcc0e5fad80eece0805115cf2decbdf717","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9740f21113f50076c546fae4a191b9fcc0e5fad80eece0805115cf2decbdf717","first_computed_at":"2026-07-05T03:37:08.287906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:08.287906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vMVbkGhLZg7gWVqMMLTci7TrN0IZo9LKcfkb8ZeyGx7W+x3KQN4nNCsPbFTUXTl+xvqnyChrgE4kclzgCwI3Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:08.288270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:679262042629afe85f000ea3e4b910de1a50df7774cda13d09e1118376f4ebd4","sha256:807ba277beb566777ed76a4a59a2e999e54edd62c2c0568b9625f17bd352619a"],"state_sha256":"b9b4e215fe6d70a4a2fe760b0c05fe8fe5c98df05b04163527afe60ec0ff8de6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MlJX1uXVTWruQafKzhK6GzJpms83lRldGJZZKe+hGBYkRP/lPywel36w6lgMrl3v03t1QXxPf/IFQkjQjiqhAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:39:46.530558Z","bundle_sha256":"fcf18582d3e7a225db28095f13ba3309dad157ae0018aa0ffe677544532f68ad"}}