{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L2PQ3BQ5NJYDE7VWGS3UH77UVJ","short_pith_number":"pith:L2PQ3BQ5","canonical_record":{"source":{"id":"2501.16142","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T15:36:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22824e16616b995a91a6f142a51c4df2fdc0f0487a350b64d1e4872272d9f692","abstract_canon_sha256":"5894988ad09d4007e020e735a5d5d97363ed650f011ea0feb80b78be5b7324de"},"schema_version":"1.0"},"canonical_sha256":"5e9f0d861d6a70327eb634b743fff4aa5bec16ef0230925fa7313955296d7c3c","source":{"kind":"arxiv","id":"2501.16142","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16142","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16142v1","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16142","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"L2PQ3BQ5NJYD","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"L2PQ3BQ5NJYDE7VW","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"L2PQ3BQ5","created_at":"2026-07-05T10:05:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L2PQ3BQ5NJYDE7VWGS3UH77UVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16142","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T15:36:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22824e16616b995a91a6f142a51c4df2fdc0f0487a350b64d1e4872272d9f692","abstract_canon_sha256":"5894988ad09d4007e020e735a5d5d97363ed650f011ea0feb80b78be5b7324de"},"schema_version":"1.0"},"canonical_sha256":"5e9f0d861d6a70327eb634b743fff4aa5bec16ef0230925fa7313955296d7c3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:55.964557Z","signature_b64":"Mleh6I8eAjgDq8lB4W1IeOS9dj1q5ZT9Oq9eFSO86Jwht9ef2OQo11j9crGtjA9VP4JZiNVBkqUvt0ckahljDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e9f0d861d6a70327eb634b743fff4aa5bec16ef0230925fa7313955296d7c3c","last_reissued_at":"2026-07-05T10:05:55.964046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:55.964046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16142","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":"2026-07-05T10:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8MM2xo1v8ltHHw4C/lcpcYVUY8tFK86m/VKAqBlxMAwmrM7TY6ZBFf2YCWiBP4ZJUD/HRU7GvezR5bso6Eb8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:39:20.427933Z"},"content_sha256":"da1d6d58193939ac9a0ca7f97aa730d465e60094e3954f89eb60213efb663551","schema_version":"1.0","event_id":"sha256:da1d6d58193939ac9a0ca7f97aa730d465e60094e3954f89eb60213efb663551"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L2PQ3BQ5NJYDE7VWGS3UH77UVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards General-Purpose Model-Free Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Michael Rabbat, Pierluca D'Oro, Scott Fujimoto, Yuandong Tian","submitted_at":"2025-01-27T15:36:37Z","abstract_excerpt":"Reinforcement learning (RL) promises a framework for near-universal problem-solving. In practice however, RL algorithms are often tailored to specific benchmarks, relying on carefully tuned hyperparameters and algorithmic choices. Recently, powerful model-based RL methods have shown impressive general results across benchmarks but come at the cost of increased complexity and slow run times, limiting their broader applicability. In this paper, we attempt to find a unifying model-free deep RL algorithm that can address a diverse class of domains and problem settings. To achieve this, we leverage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16142","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/2501.16142/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":"2026-07-05T10:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1gcRT/Cix7AYG8OITYxlSrpx4y4KbXRt+KjL5x7efkSjirgjEx+6ya92NfVdieI9uM5WxIODNqu7lGZN6fj8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:39:20.428790Z"},"content_sha256":"b7f3c4e6172d7d68c4c250a102e1e61e605b42945db86522825c5bbb48a96e56","schema_version":"1.0","event_id":"sha256:b7f3c4e6172d7d68c4c250a102e1e61e605b42945db86522825c5bbb48a96e56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L2PQ3BQ5NJYDE7VWGS3UH77UVJ/bundle.json","state_url":"https://pith.science/pith/L2PQ3BQ5NJYDE7VWGS3UH77UVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L2PQ3BQ5NJYDE7VWGS3UH77UVJ/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":"2026-08-14T08:39:20Z","links":{"resolver":"https://pith.science/pith/L2PQ3BQ5NJYDE7VWGS3UH77UVJ","bundle":"https://pith.science/pith/L2PQ3BQ5NJYDE7VWGS3UH77UVJ/bundle.json","state":"https://pith.science/pith/L2PQ3BQ5NJYDE7VWGS3UH77UVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L2PQ3BQ5NJYDE7VWGS3UH77UVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L2PQ3BQ5NJYDE7VWGS3UH77UVJ","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":"5894988ad09d4007e020e735a5d5d97363ed650f011ea0feb80b78be5b7324de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T15:36:37Z","title_canon_sha256":"22824e16616b995a91a6f142a51c4df2fdc0f0487a350b64d1e4872272d9f692"},"schema_version":"1.0","source":{"id":"2501.16142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16142","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16142v1","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16142","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"L2PQ3BQ5NJYD","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"L2PQ3BQ5NJYDE7VW","created_at":"2026-07-05T10:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"L2PQ3BQ5","created_at":"2026-07-05T10:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:b7f3c4e6172d7d68c4c250a102e1e61e605b42945db86522825c5bbb48a96e56","target":"graph","created_at":"2026-07-05T10:05:55Z","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/2501.16142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) promises a framework for near-universal problem-solving. In practice however, RL algorithms are often tailored to specific benchmarks, relying on carefully tuned hyperparameters and algorithmic choices. Recently, powerful model-based RL methods have shown impressive general results across benchmarks but come at the cost of increased complexity and slow run times, limiting their broader applicability. In this paper, we attempt to find a unifying model-free deep RL algorithm that can address a diverse class of domains and problem settings. To achieve this, we leverage","authors_text":"Amy Zhang, Michael Rabbat, Pierluca D'Oro, Scott Fujimoto, Yuandong Tian","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T15:36:37Z","title":"Towards General-Purpose Model-Free Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16142","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:da1d6d58193939ac9a0ca7f97aa730d465e60094e3954f89eb60213efb663551","target":"record","created_at":"2026-07-05T10:05:55Z","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":"5894988ad09d4007e020e735a5d5d97363ed650f011ea0feb80b78be5b7324de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T15:36:37Z","title_canon_sha256":"22824e16616b995a91a6f142a51c4df2fdc0f0487a350b64d1e4872272d9f692"},"schema_version":"1.0","source":{"id":"2501.16142","kind":"arxiv","version":1}},"canonical_sha256":"5e9f0d861d6a70327eb634b743fff4aa5bec16ef0230925fa7313955296d7c3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e9f0d861d6a70327eb634b743fff4aa5bec16ef0230925fa7313955296d7c3c","first_computed_at":"2026-07-05T10:05:55.964046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:55.964046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mleh6I8eAjgDq8lB4W1IeOS9dj1q5ZT9Oq9eFSO86Jwht9ef2OQo11j9crGtjA9VP4JZiNVBkqUvt0ckahljDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:55.964557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da1d6d58193939ac9a0ca7f97aa730d465e60094e3954f89eb60213efb663551","sha256:b7f3c4e6172d7d68c4c250a102e1e61e605b42945db86522825c5bbb48a96e56"],"state_sha256":"3d3ae0018650e0b27350dc378c0f0f153625c00810effda2796cf4e496f63ac3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9fAAhakGGx9drhnJrVesVvY7KG7meEwT1csnjO02SRbhMZNjO+cmlapp+4dGEr9jqQCWhu90uoQTbvo7Yr8CAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:39:20.434885Z","bundle_sha256":"3558793118255e51f8527c3e4a59a92176d4ac74fdc7c3c7c50ff37a132bcf2f"}}