{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:X3O5THQBIYM4TP3JI6VRS5WKUW","short_pith_number":"pith:X3O5THQB","canonical_record":{"source":{"id":"2108.05828","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T16:19:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6222cb7cc9e9886d41c817738d2c3b8eed032e3e3ed65880b9545de9250952f3","abstract_canon_sha256":"3b150658428b655ddf96aae1db4b2bee84b99c7ca86cccdb9a36b7cc28102d86"},"schema_version":"1.0"},"canonical_sha256":"beddd99e014619c9bf6947ab1976caa58ac73eee9ea4167cbbfac1f3a5909341","source":{"kind":"arxiv","id":"2108.05828","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05828","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05828v5","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05828","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"pith_short_12","alias_value":"X3O5THQBIYM4","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"pith_short_16","alias_value":"X3O5THQBIYM4TP3J","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"pith_short_8","alias_value":"X3O5THQB","created_at":"2026-07-05T07:07:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:X3O5THQBIYM4TP3JI6VRS5WKUW","target":"record","payload":{"canonical_record":{"source":{"id":"2108.05828","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T16:19:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6222cb7cc9e9886d41c817738d2c3b8eed032e3e3ed65880b9545de9250952f3","abstract_canon_sha256":"3b150658428b655ddf96aae1db4b2bee84b99c7ca86cccdb9a36b7cc28102d86"},"schema_version":"1.0"},"canonical_sha256":"beddd99e014619c9bf6947ab1976caa58ac73eee9ea4167cbbfac1f3a5909341","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:02.677029Z","signature_b64":"x7KVGnwOLYe1P4O2QeLa12kIQL6R5dyd4oyKJJ5rI0UwbsxSpVvouAtDBVcJ7ZWHhMZJhjIlnAO8f462/xqQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"beddd99e014619c9bf6947ab1976caa58ac73eee9ea4167cbbfac1f3a5909341","last_reissued_at":"2026-07-05T07:07:02.676509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:02.676509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.05828","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:07:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EXLQ6O8WEvE4h8K1WTVdw0B63kqi5nkJ8aruA0JCd45qxMzg7zgw/jbgtp7RPhtDPPFAzIw12z1l3p/6DbvLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:07:44.574694Z"},"content_sha256":"3c1dce7158622c3ed7dee506ca376411be5d3ade0becb2655b90da7536e6cee5","schema_version":"1.0","event_id":"sha256:3c1dce7158622c3ed7dee506ca376411be5d3ade0becb2655b90da7536e6cee5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:X3O5THQBIYM4TP3JI6VRS5WKUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A general class of surrogate functions for stable and efficient reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marlos C. Machado, Matthieu Geist, Nicolas Le Roux, Olivier Bachem, Pablo Samuel Castro, Robert Mueller, Sharan Vaswani, Shivam Garg, Simone Totaro","submitted_at":"2021-08-12T16:19:19Z","abstract_excerpt":"Common policy gradient methods rely on the maximization of a sequence of surrogate functions. In recent years, many such surrogate functions have been proposed, most without strong theoretical guarantees, leading to algorithms such as TRPO, PPO or MPO. Rather than design yet another surrogate function, we instead propose a general framework (FMA-PG) based on functional mirror ascent that gives rise to an entire family of surrogate functions. We construct surrogate functions that enable policy improvement guarantees, a property not shared by most existing surrogate functions. Crucially, these g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05828","kind":"arxiv","version":5},"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/2108.05828/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":"2026-07-05T07:07:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vAmGe9IZum/djgtAUmlMYUm0t8EHXwXNq7rIKH2FdiSRPARBxPTksk5xsjzgCxgZSKh6A2x5IuVUoSNFSnFsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:07:44.575753Z"},"content_sha256":"30e2d016adefd80c015fa81b155069be6ba865150b55892d0f4845c8b7b19d62","schema_version":"1.0","event_id":"sha256:30e2d016adefd80c015fa81b155069be6ba865150b55892d0f4845c8b7b19d62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X3O5THQBIYM4TP3JI6VRS5WKUW/bundle.json","state_url":"https://pith.science/pith/X3O5THQBIYM4TP3JI6VRS5WKUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X3O5THQBIYM4TP3JI6VRS5WKUW/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":"2026-08-19T14:07:44Z","links":{"resolver":"https://pith.science/pith/X3O5THQBIYM4TP3JI6VRS5WKUW","bundle":"https://pith.science/pith/X3O5THQBIYM4TP3JI6VRS5WKUW/bundle.json","state":"https://pith.science/pith/X3O5THQBIYM4TP3JI6VRS5WKUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X3O5THQBIYM4TP3JI6VRS5WKUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:X3O5THQBIYM4TP3JI6VRS5WKUW","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":"3b150658428b655ddf96aae1db4b2bee84b99c7ca86cccdb9a36b7cc28102d86","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T16:19:19Z","title_canon_sha256":"6222cb7cc9e9886d41c817738d2c3b8eed032e3e3ed65880b9545de9250952f3"},"schema_version":"1.0","source":{"id":"2108.05828","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05828","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05828v5","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05828","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"pith_short_12","alias_value":"X3O5THQBIYM4","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"pith_short_16","alias_value":"X3O5THQBIYM4TP3J","created_at":"2026-07-05T07:07:02Z"},{"alias_kind":"pith_short_8","alias_value":"X3O5THQB","created_at":"2026-07-05T07:07:02Z"}],"graph_snapshots":[{"event_id":"sha256:30e2d016adefd80c015fa81b155069be6ba865150b55892d0f4845c8b7b19d62","target":"graph","created_at":"2026-07-05T07:07:02Z","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/2108.05828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Common policy gradient methods rely on the maximization of a sequence of surrogate functions. In recent years, many such surrogate functions have been proposed, most without strong theoretical guarantees, leading to algorithms such as TRPO, PPO or MPO. Rather than design yet another surrogate function, we instead propose a general framework (FMA-PG) based on functional mirror ascent that gives rise to an entire family of surrogate functions. We construct surrogate functions that enable policy improvement guarantees, a property not shared by most existing surrogate functions. Crucially, these g","authors_text":"Marlos C. Machado, Matthieu Geist, Nicolas Le Roux, Olivier Bachem, Pablo Samuel Castro, Robert Mueller, Sharan Vaswani, Shivam Garg, Simone Totaro","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T16:19:19Z","title":"A general class of surrogate functions for stable and efficient reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05828","kind":"arxiv","version":5},"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":"sha256:3c1dce7158622c3ed7dee506ca376411be5d3ade0becb2655b90da7536e6cee5","target":"record","created_at":"2026-07-05T07:07:02Z","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":"3b150658428b655ddf96aae1db4b2bee84b99c7ca86cccdb9a36b7cc28102d86","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-12T16:19:19Z","title_canon_sha256":"6222cb7cc9e9886d41c817738d2c3b8eed032e3e3ed65880b9545de9250952f3"},"schema_version":"1.0","source":{"id":"2108.05828","kind":"arxiv","version":5}},"canonical_sha256":"beddd99e014619c9bf6947ab1976caa58ac73eee9ea4167cbbfac1f3a5909341","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"beddd99e014619c9bf6947ab1976caa58ac73eee9ea4167cbbfac1f3a5909341","first_computed_at":"2026-07-05T07:07:02.676509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:02.676509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x7KVGnwOLYe1P4O2QeLa12kIQL6R5dyd4oyKJJ5rI0UwbsxSpVvouAtDBVcJ7ZWHhMZJhjIlnAO8f462/xqQCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:02.677029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.05828","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c1dce7158622c3ed7dee506ca376411be5d3ade0becb2655b90da7536e6cee5","sha256:30e2d016adefd80c015fa81b155069be6ba865150b55892d0f4845c8b7b19d62"],"state_sha256":"5007392f301e2281a1afc6e4d3ee656fedc3b21d631d6d9f6870b778faaaab78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7PeWi8WNh0AZ8rVePHXr63rjUqKklLQ78gzxgyxDzXVYurju79+tm+9Hcan5jhnGS8AcVPVLMAUnKvowpc5ODQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:07:44.582912Z","bundle_sha256":"ecdc8f70de5d3d7c1969df2ce5ba66008025f36db712684d6e740d6e2a952f0f"}}