{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2Q3THMXYH5FPWWE6BHODSLPI52","short_pith_number":"pith:2Q3THMXY","canonical_record":{"source":{"id":"2107.00703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T19:02:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7896afc2371c2b550eb4aada9818d2522cbd64c0bd5a5be2539a537ca4f7631e","abstract_canon_sha256":"39b1f822a7b175fbc105e22149d02d8397e6543ca243aa51ac44a01a1ad940c6"},"schema_version":"1.0"},"canonical_sha256":"d43733b2f83f4afb589e09dc392de8eeb98641db5326051af4ad63b9797d59dd","source":{"kind":"arxiv","id":"2107.00703","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.00703","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2107.00703v1","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00703","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"2Q3THMXYH5FP","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"2Q3THMXYH5FPWWE6","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"2Q3THMXY","created_at":"2026-07-05T02:54:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2Q3THMXYH5FPWWE6BHODSLPI52","target":"record","payload":{"canonical_record":{"source":{"id":"2107.00703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T19:02:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7896afc2371c2b550eb4aada9818d2522cbd64c0bd5a5be2539a537ca4f7631e","abstract_canon_sha256":"39b1f822a7b175fbc105e22149d02d8397e6543ca243aa51ac44a01a1ad940c6"},"schema_version":"1.0"},"canonical_sha256":"d43733b2f83f4afb589e09dc392de8eeb98641db5326051af4ad63b9797d59dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:32.719091Z","signature_b64":"5p7YwqvZSzTujzMbFFaOIqL3wSMPjmQ3LZKSgkzuI63yK2a4EtTFQ0uGQGGc1yXnNidxG39NuQ/YiHMOFhK5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d43733b2f83f4afb589e09dc392de8eeb98641db5326051af4ad63b9797d59dd","last_reissued_at":"2026-07-05T02:54:32.718595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:32.718595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.00703","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":"2026-07-05T02:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJU4V+NoMB94NsjeNKAtPJkPnudgDyakRodkUy0NJL3UQ+4zr1jfHvnTDnWuz/8kK6HVJz5DvK6e7fOFzkkiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T15:36:16.226796Z"},"content_sha256":"282b778ab30a66ee752e434b7957be88abec0f3c36314cadfeb5b58cb12f60a6","schema_version":"1.0","event_id":"sha256:282b778ab30a66ee752e434b7957be88abec0f3c36314cadfeb5b58cb12f60a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2Q3THMXYH5FPWWE6BHODSLPI52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Reinforcement Learning Tricks for Video Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anssi Kanervisto, Christian Scheller, Ville Hautam\\\"aki, Yanick Schraner","submitted_at":"2021-07-01T19:02:38Z","abstract_excerpt":"Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering steps (\"tricks\") which may be needed to effectively use RL, such as reward shaping, curriculum learning, and splitting a large task into smaller chunks. Such tricks are common, if not necessary, to achieve state-of-the-art results and win RL competitions. To ease the engineering efforts, we distill descriptions of tricks from state-of-the-art results and stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00703","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/2107.00703/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":"2026-07-05T02:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pk4VULXKeAaEoPDeMA0QSFQgJIo9WvmWVVXze60b50MbliDDL/xGToh6CSt3H8qSWneuV4HkeV26uXlgTwfeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T15:36:16.227180Z"},"content_sha256":"f60c25b86a25f5baf7c56d7965c3ac3407f34194d4008e612416d64a71bb68a9","schema_version":"1.0","event_id":"sha256:f60c25b86a25f5baf7c56d7965c3ac3407f34194d4008e612416d64a71bb68a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2Q3THMXYH5FPWWE6BHODSLPI52/bundle.json","state_url":"https://pith.science/pith/2Q3THMXYH5FPWWE6BHODSLPI52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2Q3THMXYH5FPWWE6BHODSLPI52/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":"2026-07-16T15:36:16Z","links":{"resolver":"https://pith.science/pith/2Q3THMXYH5FPWWE6BHODSLPI52","bundle":"https://pith.science/pith/2Q3THMXYH5FPWWE6BHODSLPI52/bundle.json","state":"https://pith.science/pith/2Q3THMXYH5FPWWE6BHODSLPI52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2Q3THMXYH5FPWWE6BHODSLPI52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2Q3THMXYH5FPWWE6BHODSLPI52","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":"39b1f822a7b175fbc105e22149d02d8397e6543ca243aa51ac44a01a1ad940c6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T19:02:38Z","title_canon_sha256":"7896afc2371c2b550eb4aada9818d2522cbd64c0bd5a5be2539a537ca4f7631e"},"schema_version":"1.0","source":{"id":"2107.00703","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.00703","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2107.00703v1","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00703","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"2Q3THMXYH5FP","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"2Q3THMXYH5FPWWE6","created_at":"2026-07-05T02:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"2Q3THMXY","created_at":"2026-07-05T02:54:32Z"}],"graph_snapshots":[{"event_id":"sha256:f60c25b86a25f5baf7c56d7965c3ac3407f34194d4008e612416d64a71bb68a9","target":"graph","created_at":"2026-07-05T02:54:32Z","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/2107.00703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering steps (\"tricks\") which may be needed to effectively use RL, such as reward shaping, curriculum learning, and splitting a large task into smaller chunks. Such tricks are common, if not necessary, to achieve state-of-the-art results and win RL competitions. To ease the engineering efforts, we distill descriptions of tricks from state-of-the-art results and stud","authors_text":"Anssi Kanervisto, Christian Scheller, Ville Hautam\\\"aki, Yanick Schraner","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T19:02:38Z","title":"Distilling Reinforcement Learning Tricks for Video Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00703","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":"sha256:282b778ab30a66ee752e434b7957be88abec0f3c36314cadfeb5b58cb12f60a6","target":"record","created_at":"2026-07-05T02:54:32Z","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":"39b1f822a7b175fbc105e22149d02d8397e6543ca243aa51ac44a01a1ad940c6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T19:02:38Z","title_canon_sha256":"7896afc2371c2b550eb4aada9818d2522cbd64c0bd5a5be2539a537ca4f7631e"},"schema_version":"1.0","source":{"id":"2107.00703","kind":"arxiv","version":1}},"canonical_sha256":"d43733b2f83f4afb589e09dc392de8eeb98641db5326051af4ad63b9797d59dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d43733b2f83f4afb589e09dc392de8eeb98641db5326051af4ad63b9797d59dd","first_computed_at":"2026-07-05T02:54:32.718595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:32.718595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5p7YwqvZSzTujzMbFFaOIqL3wSMPjmQ3LZKSgkzuI63yK2a4EtTFQ0uGQGGc1yXnNidxG39NuQ/YiHMOFhK5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:32.719091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.00703","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:282b778ab30a66ee752e434b7957be88abec0f3c36314cadfeb5b58cb12f60a6","sha256:f60c25b86a25f5baf7c56d7965c3ac3407f34194d4008e612416d64a71bb68a9"],"state_sha256":"f2fdd120552d42fa6135047fa1304fa9e358b02ea6512c9169b1d88ea298dd36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4NpZiuVxZ25pyolxTWSeeiF8FSPyYud2evWPrN1LanFtK3/PHQEhBBOgVDovxeiGsWXhn9sNCIek1xHBGh5BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T15:36:16.229441Z","bundle_sha256":"ec693203d3be0a91db9a283e25862c325f03e37a27ce0d50b6ca639b6844de58"}}