{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RBZIEWN5CEBN5SNVGD7ODP2FKM","short_pith_number":"pith:RBZIEWN5","canonical_record":{"source":{"id":"2104.04004","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-08T18:40:20Z","cross_cats_sorted":[],"title_canon_sha256":"0e5bf4cb5f044236df2eceaa129ec700f5cb9cca621196de1b051d7e0c673736","abstract_canon_sha256":"47339d95d83d29a7eb88e3be55e79d086a558dd0b754ac6fc0f71699722f6738"},"schema_version":"1.0"},"canonical_sha256":"88728259bd1102dec9b530fee1bf45532f220b30cc2b167cf8562acc257bb675","source":{"kind":"arxiv","id":"2104.04004","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04004","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04004v4","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04004","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_12","alias_value":"RBZIEWN5CEBN","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_16","alias_value":"RBZIEWN5CEBN5SNV","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_8","alias_value":"RBZIEWN5","created_at":"2026-07-05T04:38:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RBZIEWN5CEBN5SNVGD7ODP2FKM","target":"record","payload":{"canonical_record":{"source":{"id":"2104.04004","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-08T18:40:20Z","cross_cats_sorted":[],"title_canon_sha256":"0e5bf4cb5f044236df2eceaa129ec700f5cb9cca621196de1b051d7e0c673736","abstract_canon_sha256":"47339d95d83d29a7eb88e3be55e79d086a558dd0b754ac6fc0f71699722f6738"},"schema_version":"1.0"},"canonical_sha256":"88728259bd1102dec9b530fee1bf45532f220b30cc2b167cf8562acc257bb675","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:42.377888Z","signature_b64":"KPUn02H3nSVuhJhEdFnTWJXG16zURf7G7jROp9VjNJGZCdUwI+hQkSXZW9Xk6O7Ctg3pHx6g3ixqnt35q5R+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88728259bd1102dec9b530fee1bf45532f220b30cc2b167cf8562acc257bb675","last_reissued_at":"2026-07-05T04:38:42.377436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:42.377436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.04004","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":"2026-07-05T04:38:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NohNzRxCj4DP5d7RK9+st3916DMZT9nmtpNGi7HupLJYf3JVBaWxXCcfkcelAK55ddUknHsvPxW06TwRV2TfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:32.981584Z"},"content_sha256":"8fdcbbedfba8800577c6960d46611cef6c2754656046b3507d0415a14537f331","schema_version":"1.0","event_id":"sha256:8fdcbbedfba8800577c6960d46611cef6c2754656046b3507d0415a14537f331"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RBZIEWN5CEBN5SNVGD7ODP2FKM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ACERAC: Efficient reinforcement learning in fine time discretization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jakub {\\L}yskawa, Pawe{\\l} Wawrzy\\'nski","submitted_at":"2021-04-08T18:40:20Z","abstract_excerpt":"One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of the machines usually requires fine time discretization. The most common RL methods apply independent random elements to each action, which is not suitable in that setting. It is not feasible because it causes the controlled system to jerk, and does not ensure sufficient exploration since a~single action is not long enough to create a~significant experience that could be translated into policy improvement. In our view"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04004","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.04004/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":"2026-07-05T04:38:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iIRHVJlyq8maOEYiinSFaKp0uS1/Ef9QEIXYGyekfIY9dOqcmuibwfsRW4NqEZRc0Uaufy5OA3ZHHb9lSriLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:32.981968Z"},"content_sha256":"a218d645166065053f1094c8f31f111a974e3bc798c3d7542d924e5ef11f25a6","schema_version":"1.0","event_id":"sha256:a218d645166065053f1094c8f31f111a974e3bc798c3d7542d924e5ef11f25a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/bundle.json","state_url":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/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":"2026-07-09T05:56:32Z","links":{"resolver":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM","bundle":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/bundle.json","state":"https://pith.science/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RBZIEWN5CEBN5SNVGD7ODP2FKM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RBZIEWN5CEBN5SNVGD7ODP2FKM","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":"47339d95d83d29a7eb88e3be55e79d086a558dd0b754ac6fc0f71699722f6738","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-08T18:40:20Z","title_canon_sha256":"0e5bf4cb5f044236df2eceaa129ec700f5cb9cca621196de1b051d7e0c673736"},"schema_version":"1.0","source":{"id":"2104.04004","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04004","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04004v4","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04004","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_12","alias_value":"RBZIEWN5CEBN","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_16","alias_value":"RBZIEWN5CEBN5SNV","created_at":"2026-07-05T04:38:42Z"},{"alias_kind":"pith_short_8","alias_value":"RBZIEWN5","created_at":"2026-07-05T04:38:42Z"}],"graph_snapshots":[{"event_id":"sha256:a218d645166065053f1094c8f31f111a974e3bc798c3d7542d924e5ef11f25a6","target":"graph","created_at":"2026-07-05T04:38:42Z","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/2104.04004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of the machines usually requires fine time discretization. The most common RL methods apply independent random elements to each action, which is not suitable in that setting. It is not feasible because it causes the controlled system to jerk, and does not ensure sufficient exploration since a~single action is not long enough to create a~significant experience that could be translated into policy improvement. In our view","authors_text":"Jakub {\\L}yskawa, Pawe{\\l} Wawrzy\\'nski","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-08T18:40:20Z","title":"ACERAC: Efficient reinforcement learning in fine time discretization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04004","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":"sha256:8fdcbbedfba8800577c6960d46611cef6c2754656046b3507d0415a14537f331","target":"record","created_at":"2026-07-05T04:38:42Z","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":"47339d95d83d29a7eb88e3be55e79d086a558dd0b754ac6fc0f71699722f6738","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-08T18:40:20Z","title_canon_sha256":"0e5bf4cb5f044236df2eceaa129ec700f5cb9cca621196de1b051d7e0c673736"},"schema_version":"1.0","source":{"id":"2104.04004","kind":"arxiv","version":4}},"canonical_sha256":"88728259bd1102dec9b530fee1bf45532f220b30cc2b167cf8562acc257bb675","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88728259bd1102dec9b530fee1bf45532f220b30cc2b167cf8562acc257bb675","first_computed_at":"2026-07-05T04:38:42.377436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:42.377436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KPUn02H3nSVuhJhEdFnTWJXG16zURf7G7jROp9VjNJGZCdUwI+hQkSXZW9Xk6O7Ctg3pHx6g3ixqnt35q5R+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:42.377888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.04004","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fdcbbedfba8800577c6960d46611cef6c2754656046b3507d0415a14537f331","sha256:a218d645166065053f1094c8f31f111a974e3bc798c3d7542d924e5ef11f25a6"],"state_sha256":"64a5850190b2f643a7cf764a9442ec05ddf5c90ccc47e296258d7865e58ba3f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xCM6Ly92Y88bONtfR43HSTEa+jmoTb3P7LQyKRgziJb+FQ442aWtSyQODDVztp8OU5zj3rX4MoGQB7yncTijBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:56:32.984385Z","bundle_sha256":"0930b7f898172e6e1a96f0a1c670a416c2c7e1878cded27a313c33dbd73df024"}}