{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SSY2KU53DISQQ37G6YFACQTNVC","short_pith_number":"pith:SSY2KU53","canonical_record":{"source":{"id":"1705.07460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:19:20Z","cross_cats_sorted":[],"title_canon_sha256":"1b4e820932b9076f1cad13253a383174d757fb9b66088f9f5086e23b831a9335","abstract_canon_sha256":"a2dd3daf0dd0fcc16673217ef847c4db2a11118aaaa948d7d263644f652a69d3"},"schema_version":"1.0"},"canonical_sha256":"94b1a553bb1a25086fe6f60a01426da8b092a7c22e200b0464d871d42a767f9e","source":{"kind":"arxiv","id":"1705.07460","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07460","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07460v1","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07460","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"pith_short_12","alias_value":"SSY2KU53DISQ","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SSY2KU53DISQQ37G","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SSY2KU53","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SSY2KU53DISQQ37G6YFACQTNVC","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:19:20Z","cross_cats_sorted":[],"title_canon_sha256":"1b4e820932b9076f1cad13253a383174d757fb9b66088f9f5086e23b831a9335","abstract_canon_sha256":"a2dd3daf0dd0fcc16673217ef847c4db2a11118aaaa948d7d263644f652a69d3"},"schema_version":"1.0"},"canonical_sha256":"94b1a553bb1a25086fe6f60a01426da8b092a7c22e200b0464d871d42a767f9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:05.531458Z","signature_b64":"CP1IJlEx2w41JZ+MoWH1j7blVAqMuKRr2qi0AA8sgcL15WvRi/xXosXIHukJvP2DtajZpE8x3pP/Aaj0TnZbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94b1a553bb1a25086fe6f60a01426da8b092a7c22e200b0464d871d42a767f9e","last_reissued_at":"2026-05-18T00:44:05.530853Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:05.530853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07460","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":"2026-05-18T00:44:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fgHgRgXl7idED6zxq1w7hBJm5CmkLQ4vCupGXEuXPuXRVuXNjHMWRuevNQ8Tr2l+t0wjbU+yCvHaHTAisJfACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:36:11.698662Z"},"content_sha256":"622338e9af232ec425ee02d6700925fc113868279a3f41123f5e5b6d4a1eb09e","schema_version":"1.0","event_id":"sha256:622338e9af232ec425ee02d6700925fc113868279a3f41123f5e5b6d4a1eb09e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SSY2KU53DISQQ37G6YFACQTNVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Experience enrichment based task independent reward model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Min Xu","submitted_at":"2017-05-21T15:19:20Z","abstract_excerpt":"For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks. However, in real world, rewards are emergent phenomena from the complex interactions between agents and environments. In this paper, we propose an implicit generic reward model for reinforcement learning. Unlike those rewards that are manually defined for specific tasks, such implicit reward is task independent. It only comes from the deviation from the agents' previous experiences."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07460","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":"2026-05-18T00:44:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"exITsAEZOD1MNyMpP//N1GAanGy/xUI7COFfTyfRbaaZ/0Z5P9M2OegKmmZNPS63ap6zQC3aZGg9IeeCuqVHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:36:11.699352Z"},"content_sha256":"cb9bb73440154274049106a3d859c22e2d68e0a428240efd0e8c554c5eec05ac","schema_version":"1.0","event_id":"sha256:cb9bb73440154274049106a3d859c22e2d68e0a428240efd0e8c554c5eec05ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SSY2KU53DISQQ37G6YFACQTNVC/bundle.json","state_url":"https://pith.science/pith/SSY2KU53DISQQ37G6YFACQTNVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SSY2KU53DISQQ37G6YFACQTNVC/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":"2026-05-26T00:36:11Z","links":{"resolver":"https://pith.science/pith/SSY2KU53DISQQ37G6YFACQTNVC","bundle":"https://pith.science/pith/SSY2KU53DISQQ37G6YFACQTNVC/bundle.json","state":"https://pith.science/pith/SSY2KU53DISQQ37G6YFACQTNVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SSY2KU53DISQQ37G6YFACQTNVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SSY2KU53DISQQ37G6YFACQTNVC","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":"a2dd3daf0dd0fcc16673217ef847c4db2a11118aaaa948d7d263644f652a69d3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:19:20Z","title_canon_sha256":"1b4e820932b9076f1cad13253a383174d757fb9b66088f9f5086e23b831a9335"},"schema_version":"1.0","source":{"id":"1705.07460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07460","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07460v1","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07460","created_at":"2026-05-18T00:44:05Z"},{"alias_kind":"pith_short_12","alias_value":"SSY2KU53DISQ","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SSY2KU53DISQQ37G","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SSY2KU53","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:cb9bb73440154274049106a3d859c22e2d68e0a428240efd0e8c554c5eec05ac","target":"graph","created_at":"2026-05-18T00:44:05Z","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":"For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks. However, in real world, rewards are emergent phenomena from the complex interactions between agents and environments. In this paper, we propose an implicit generic reward model for reinforcement learning. Unlike those rewards that are manually defined for specific tasks, such implicit reward is task independent. It only comes from the deviation from the agents' previous experiences.","authors_text":"Min Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:19:20Z","title":"Experience enrichment based task independent reward model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07460","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":"sha256:622338e9af232ec425ee02d6700925fc113868279a3f41123f5e5b6d4a1eb09e","target":"record","created_at":"2026-05-18T00:44:05Z","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":"a2dd3daf0dd0fcc16673217ef847c4db2a11118aaaa948d7d263644f652a69d3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-21T15:19:20Z","title_canon_sha256":"1b4e820932b9076f1cad13253a383174d757fb9b66088f9f5086e23b831a9335"},"schema_version":"1.0","source":{"id":"1705.07460","kind":"arxiv","version":1}},"canonical_sha256":"94b1a553bb1a25086fe6f60a01426da8b092a7c22e200b0464d871d42a767f9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94b1a553bb1a25086fe6f60a01426da8b092a7c22e200b0464d871d42a767f9e","first_computed_at":"2026-05-18T00:44:05.530853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:05.530853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CP1IJlEx2w41JZ+MoWH1j7blVAqMuKRr2qi0AA8sgcL15WvRi/xXosXIHukJvP2DtajZpE8x3pP/Aaj0TnZbAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:05.531458Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:622338e9af232ec425ee02d6700925fc113868279a3f41123f5e5b6d4a1eb09e","sha256:cb9bb73440154274049106a3d859c22e2d68e0a428240efd0e8c554c5eec05ac"],"state_sha256":"d9e6eead0d1c8aebdb70f34e0d41bc37c452016037d313f6962d4b737f9cf7ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cb5SdY/DRcEBr3+QuXgXlS2agYZQQ3T5ZeLrptKY+rJANi5AWUh1Mw9pFYJfruR3xm05Ui6R4gIyXKEDqM8/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:36:11.703376Z","bundle_sha256":"6d72f8ae1b1f57aa2362758ab193fb4e104210586807af9c0b7dbf7263762e05"}}