{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7TH3VAOBZXZODSEQYOFCVSEI26","short_pith_number":"pith:7TH3VAOB","canonical_record":{"source":{"id":"2405.16158","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T09:53:25Z","cross_cats_sorted":[],"title_canon_sha256":"88feb6048c768ae63552194696fd77723a94e7c0cf6e2cf917701d49fa50596b","abstract_canon_sha256":"fca7406018097b979d486f5f1f78b0f40afb2692444e743752b00bfaea45713c"},"schema_version":"1.0"},"canonical_sha256":"fccfba81c1cdf2e1c890c38a2ac888d7bd2f7c1c04ab3f25806fda25cffaf246","source":{"kind":"arxiv","id":"2405.16158","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16158","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16158v3","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16158","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"7TH3VAOBZXZO","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"pith_short_16","alias_value":"7TH3VAOBZXZODSEQ","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"pith_short_8","alias_value":"7TH3VAOB","created_at":"2026-07-05T09:43:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7TH3VAOBZXZODSEQYOFCVSEI26","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16158","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T09:53:25Z","cross_cats_sorted":[],"title_canon_sha256":"88feb6048c768ae63552194696fd77723a94e7c0cf6e2cf917701d49fa50596b","abstract_canon_sha256":"fca7406018097b979d486f5f1f78b0f40afb2692444e743752b00bfaea45713c"},"schema_version":"1.0"},"canonical_sha256":"fccfba81c1cdf2e1c890c38a2ac888d7bd2f7c1c04ab3f25806fda25cffaf246","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:29.770232Z","signature_b64":"THNLYKGXofdRaMmyIiQpFkoMt0QqonJ93phfmGT2e38m50Ml8z5ZAniZI/HtmZTVx7Y8j/Xb0K1Fe8Cl42zrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fccfba81c1cdf2e1c890c38a2ac888d7bd2f7c1c04ab3f25806fda25cffaf246","last_reissued_at":"2026-07-05T09:43:29.769725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:29.769725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16158","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+RL/eZGZY7z0MZCnRRWsTIAnk3NY8rIEtWn1zkz0TF3I7iAz0eBrGk7TsxJkZVMoA4CjqZsbrFeFgTlyBiHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:26:33.233977Z"},"content_sha256":"c5cdf16c0358b58d6dc4be83513c987245d8960c8d596cd9611180ba1d5c04ce","schema_version":"1.0","event_id":"sha256:c5cdf16c0358b58d6dc4be83513c987245d8960c8d596cd9611180ba1d5c04ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7TH3VAOBZXZODSEQYOFCVSEI26","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Krzysztof Jankowski, Marek Cygan, Mateusz Ostaszewski, Michal Nauman, Piotr Mi{\\l}o\\'s","submitted_at":"2024-05-25T09:53:25Z","abstract_excerpt":"Sample efficiency in Reinforcement Learning (RL) has traditionally been driven by algorithmic enhancements. In this work, we demonstrate that scaling can also lead to substantial improvements. We conduct a thorough investigation into the interplay of scaling model capacity and domain-specific RL enhancements. These empirical findings inform the design choices underlying our proposed BRO (Bigger, Regularized, Optimistic) algorithm. The key innovation behind BRO is that strong regularization allows for effective scaling of the critic networks, which, paired with optimistic exploration, leads to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16158","kind":"arxiv","version":3},"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/2405.16158/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":"2026-07-05T09:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rUnuJfQZSz5TzdFqEUSXAdAfA6nfqju0QZOoKWFYYVbf/BdnC6ysabF/aAZ8QsR4HB3ajfxvaIksfkYM7QWCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:26:33.234349Z"},"content_sha256":"8c5f531d57a12b4adfe6f51a545e13af0692e79f04c355723373decfd107ea14","schema_version":"1.0","event_id":"sha256:8c5f531d57a12b4adfe6f51a545e13af0692e79f04c355723373decfd107ea14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7TH3VAOBZXZODSEQYOFCVSEI26/bundle.json","state_url":"https://pith.science/pith/7TH3VAOBZXZODSEQYOFCVSEI26/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7TH3VAOBZXZODSEQYOFCVSEI26/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":"2026-07-07T10:26:33Z","links":{"resolver":"https://pith.science/pith/7TH3VAOBZXZODSEQYOFCVSEI26","bundle":"https://pith.science/pith/7TH3VAOBZXZODSEQYOFCVSEI26/bundle.json","state":"https://pith.science/pith/7TH3VAOBZXZODSEQYOFCVSEI26/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7TH3VAOBZXZODSEQYOFCVSEI26/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7TH3VAOBZXZODSEQYOFCVSEI26","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":"fca7406018097b979d486f5f1f78b0f40afb2692444e743752b00bfaea45713c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T09:53:25Z","title_canon_sha256":"88feb6048c768ae63552194696fd77723a94e7c0cf6e2cf917701d49fa50596b"},"schema_version":"1.0","source":{"id":"2405.16158","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16158","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16158v3","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16158","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"7TH3VAOBZXZO","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"pith_short_16","alias_value":"7TH3VAOBZXZODSEQ","created_at":"2026-07-05T09:43:29Z"},{"alias_kind":"pith_short_8","alias_value":"7TH3VAOB","created_at":"2026-07-05T09:43:29Z"}],"graph_snapshots":[{"event_id":"sha256:8c5f531d57a12b4adfe6f51a545e13af0692e79f04c355723373decfd107ea14","target":"graph","created_at":"2026-07-05T09:43:29Z","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/2405.16158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample efficiency in Reinforcement Learning (RL) has traditionally been driven by algorithmic enhancements. In this work, we demonstrate that scaling can also lead to substantial improvements. We conduct a thorough investigation into the interplay of scaling model capacity and domain-specific RL enhancements. These empirical findings inform the design choices underlying our proposed BRO (Bigger, Regularized, Optimistic) algorithm. The key innovation behind BRO is that strong regularization allows for effective scaling of the critic networks, which, paired with optimistic exploration, leads to ","authors_text":"Krzysztof Jankowski, Marek Cygan, Mateusz Ostaszewski, Michal Nauman, Piotr Mi{\\l}o\\'s","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T09:53:25Z","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16158","kind":"arxiv","version":3},"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:c5cdf16c0358b58d6dc4be83513c987245d8960c8d596cd9611180ba1d5c04ce","target":"record","created_at":"2026-07-05T09:43:29Z","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":"fca7406018097b979d486f5f1f78b0f40afb2692444e743752b00bfaea45713c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T09:53:25Z","title_canon_sha256":"88feb6048c768ae63552194696fd77723a94e7c0cf6e2cf917701d49fa50596b"},"schema_version":"1.0","source":{"id":"2405.16158","kind":"arxiv","version":3}},"canonical_sha256":"fccfba81c1cdf2e1c890c38a2ac888d7bd2f7c1c04ab3f25806fda25cffaf246","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fccfba81c1cdf2e1c890c38a2ac888d7bd2f7c1c04ab3f25806fda25cffaf246","first_computed_at":"2026-07-05T09:43:29.769725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:29.769725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"THNLYKGXofdRaMmyIiQpFkoMt0QqonJ93phfmGT2e38m50Ml8z5ZAniZI/HtmZTVx7Y8j/Xb0K1Fe8Cl42zrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:29.770232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16158","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5cdf16c0358b58d6dc4be83513c987245d8960c8d596cd9611180ba1d5c04ce","sha256:8c5f531d57a12b4adfe6f51a545e13af0692e79f04c355723373decfd107ea14"],"state_sha256":"c780d987dca1bcfd6c6b5027b4ba9529eef42a6ae79fa9b86594825d8c358f38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1kA+iYQMWSlhiSnXYfKERVZooOs6zC2CSwoGuRg0+S0ruRos9BgcJ98RtfEambWGPzr3WsshL1ykdsEdVRsbCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:26:33.236245Z","bundle_sha256":"c97bf31a5b528065874c0a0bf75f1f9ec2473dc91d3f0e212e882880018aa867"}}