{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FT24MCKQLEUVKNRSIM55E5K6DA","short_pith_number":"pith:FT24MCKQ","canonical_record":{"source":{"id":"1904.04025","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-08T12:53:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1d251fd52716f248a0699dafe4507a8e1785a357edcff4859d3d9e16bd630be3","abstract_canon_sha256":"c03a0632f1b89fb63b5e35eca14c46d7a0b271340bc9a51530fca3c2726fb199"},"schema_version":"1.0"},"canonical_sha256":"2cf5c609505929553632433bd2755e18129e25ed693c4f272c813b89e4f52792","source":{"kind":"arxiv","id":"1904.04025","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04025","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04025v5","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04025","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"pith_short_12","alias_value":"FT24MCKQLEUV","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"pith_short_16","alias_value":"FT24MCKQLEUVKNRS","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"pith_short_8","alias_value":"FT24MCKQ","created_at":"2026-07-05T01:53:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FT24MCKQLEUVKNRSIM55E5K6DA","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04025","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-08T12:53:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1d251fd52716f248a0699dafe4507a8e1785a357edcff4859d3d9e16bd630be3","abstract_canon_sha256":"c03a0632f1b89fb63b5e35eca14c46d7a0b271340bc9a51530fca3c2726fb199"},"schema_version":"1.0"},"canonical_sha256":"2cf5c609505929553632433bd2755e18129e25ed693c4f272c813b89e4f52792","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:06.353339Z","signature_b64":"UfWJ2grp/2zNncdv57KlIgPiM71d+cTSbOTu2dCK+f0/uJWwMdfLOrtLP9ckB/bSTYp+kG8q+wljGHbT33EbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf5c609505929553632433bd2755e18129e25ed693c4f272c813b89e4f52792","last_reissued_at":"2026-07-05T01:53:06.352796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:06.352796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04025","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":"2026-07-05T01:53:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d81q7XvR0oQZxmV9bF2ULkViz9ydw20h+RVZEAHNLxVKloxrmW+00oJ2HAA6a9wcGkNhvlZthtudcdCvT2bSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:29:16.988147Z"},"content_sha256":"060e921b0e4a1243940c26c5bbcac8dd1471800bc3af36786a888c2a9757c71e","schema_version":"1.0","event_id":"sha256:060e921b0e4a1243940c26c5bbcac8dd1471800bc3af36786a888c2a9757c71e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FT24MCKQLEUVKNRSIM55E5K6DA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Philippe Preux, Yannis Flet-Berliac","submitted_at":"2019-04-08T12:53:12Z","abstract_excerpt":"In reinforcement learning, policy gradient algorithms optimize the policy directly and rely on sampling efficiently an environment. Nevertheless, while most sampling procedures are based on direct policy sampling, self-performance measures could be used to improve such sampling prior to each policy update. Following this line of thought, we introduce SAUNA, a method where non-informative transitions are rejected from the gradient update. The level of information is estimated according to the fraction of variance explained by the value function: a measure of the discrepancy between V and the em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04025","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/1904.04025/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":"2026-07-05T01:53:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/4L+R9De5plfB61d1cJCn6UDY0BCWY4/+PpgHmlTeridq3tFUR2+v3Rx93pULLn5z1A3YaarHItFtP957GmLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:29:16.988883Z"},"content_sha256":"af63a0be71521b2873f05e25af771e02ab55e1806b609bb862ae9482336a8d9b","schema_version":"1.0","event_id":"sha256:af63a0be71521b2873f05e25af771e02ab55e1806b609bb862ae9482336a8d9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FT24MCKQLEUVKNRSIM55E5K6DA/bundle.json","state_url":"https://pith.science/pith/FT24MCKQLEUVKNRSIM55E5K6DA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FT24MCKQLEUVKNRSIM55E5K6DA/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":"2026-08-04T21:29:16Z","links":{"resolver":"https://pith.science/pith/FT24MCKQLEUVKNRSIM55E5K6DA","bundle":"https://pith.science/pith/FT24MCKQLEUVKNRSIM55E5K6DA/bundle.json","state":"https://pith.science/pith/FT24MCKQLEUVKNRSIM55E5K6DA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FT24MCKQLEUVKNRSIM55E5K6DA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FT24MCKQLEUVKNRSIM55E5K6DA","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":"c03a0632f1b89fb63b5e35eca14c46d7a0b271340bc9a51530fca3c2726fb199","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-08T12:53:12Z","title_canon_sha256":"1d251fd52716f248a0699dafe4507a8e1785a357edcff4859d3d9e16bd630be3"},"schema_version":"1.0","source":{"id":"1904.04025","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04025","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04025v5","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04025","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"pith_short_12","alias_value":"FT24MCKQLEUV","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"pith_short_16","alias_value":"FT24MCKQLEUVKNRS","created_at":"2026-07-05T01:53:06Z"},{"alias_kind":"pith_short_8","alias_value":"FT24MCKQ","created_at":"2026-07-05T01:53:06Z"}],"graph_snapshots":[{"event_id":"sha256:af63a0be71521b2873f05e25af771e02ab55e1806b609bb862ae9482336a8d9b","target":"graph","created_at":"2026-07-05T01:53:06Z","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/1904.04025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, policy gradient algorithms optimize the policy directly and rely on sampling efficiently an environment. Nevertheless, while most sampling procedures are based on direct policy sampling, self-performance measures could be used to improve such sampling prior to each policy update. Following this line of thought, we introduce SAUNA, a method where non-informative transitions are rejected from the gradient update. The level of information is estimated according to the fraction of variance explained by the value function: a measure of the discrepancy between V and the em","authors_text":"Philippe Preux, Yannis Flet-Berliac","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-08T12:53:12Z","title":"Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04025","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":"sha256:060e921b0e4a1243940c26c5bbcac8dd1471800bc3af36786a888c2a9757c71e","target":"record","created_at":"2026-07-05T01:53:06Z","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":"c03a0632f1b89fb63b5e35eca14c46d7a0b271340bc9a51530fca3c2726fb199","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-08T12:53:12Z","title_canon_sha256":"1d251fd52716f248a0699dafe4507a8e1785a357edcff4859d3d9e16bd630be3"},"schema_version":"1.0","source":{"id":"1904.04025","kind":"arxiv","version":5}},"canonical_sha256":"2cf5c609505929553632433bd2755e18129e25ed693c4f272c813b89e4f52792","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cf5c609505929553632433bd2755e18129e25ed693c4f272c813b89e4f52792","first_computed_at":"2026-07-05T01:53:06.352796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:06.352796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UfWJ2grp/2zNncdv57KlIgPiM71d+cTSbOTu2dCK+f0/uJWwMdfLOrtLP9ckB/bSTYp+kG8q+wljGHbT33EbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:06.353339Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04025","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:060e921b0e4a1243940c26c5bbcac8dd1471800bc3af36786a888c2a9757c71e","sha256:af63a0be71521b2873f05e25af771e02ab55e1806b609bb862ae9482336a8d9b"],"state_sha256":"da84459d1279c110d2c1eb599b952bcb8cb7e0ba5f671ea4b013fde5a726b601"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOjMSf3OijBZs9Nd7RPaIDg16QWEP91Z5YwggWrspEM+djUx9Q4OjFD1Wbsiqih3s/ar+PLwuApZiHtmRunbAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:29:16.995008Z","bundle_sha256":"b1bbfabb3a6bf111d52245c47f55a07ebc312f8a08b63929240a0e0cd358664d"}}