{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OQRDMSRX75VCZL7UW3NRZXPEGV","short_pith_number":"pith:OQRDMSRX","canonical_record":{"source":{"id":"2007.03749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:27:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fafbd8251c78049bc26670dd93159ac0269503b628fae2fb4d00b754b3e577e4","abstract_canon_sha256":"cc40c995cecf28d08be5c04c287566978192148b53cabf72b216e03c39272f2a"},"schema_version":"1.0"},"canonical_sha256":"7422364a37ff6a2caff4b6db1cdde4356cf916bb0d1176056e2f74f536d7c979","source":{"kind":"arxiv","id":"2007.03749","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03749","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03749v1","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03749","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"OQRDMSRX75VC","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"OQRDMSRX75VCZL7U","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"OQRDMSRX","created_at":"2026-07-05T01:17:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OQRDMSRX75VCZL7UW3NRZXPEGV","target":"record","payload":{"canonical_record":{"source":{"id":"2007.03749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:27:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fafbd8251c78049bc26670dd93159ac0269503b628fae2fb4d00b754b3e577e4","abstract_canon_sha256":"cc40c995cecf28d08be5c04c287566978192148b53cabf72b216e03c39272f2a"},"schema_version":"1.0"},"canonical_sha256":"7422364a37ff6a2caff4b6db1cdde4356cf916bb0d1176056e2f74f536d7c979","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:09.272772Z","signature_b64":"V3c820dwS01XDtFPAKf2P6Q5Q72jN79iyFiAvxv4tCbboeCADtUJ4cfnpYZjkHcXKvf5wXsUxDxfr4T36QPnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7422364a37ff6a2caff4b6db1cdde4356cf916bb0d1176056e2f74f536d7c979","last_reissued_at":"2026-07-05T01:17:09.272378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:09.272378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.03749","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":"2026-07-05T01:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfdk0N+7Tp+SfcamTeQCFjUZ1vDXJk9PamlOE2EW3abe3krcab+XkShMi7arzlWQUpZRa4BzkThX2PVX5Df2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:15:33.900515Z"},"content_sha256":"b9f82202450fcf9b047536853d8a09141fed52387632f0da3b30271dd36e5eb9","schema_version":"1.0","event_id":"sha256:b9f82202450fcf9b047536853d8a09141fed52387632f0da3b30271dd36e5eb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OQRDMSRX75VCZL7UW3NRZXPEGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sharp Analysis of Smoothed Bellman Error Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Touati, Pascal Vincent","submitted_at":"2020-07-07T19:27:09Z","abstract_excerpt":"The \\textit{Smoothed Bellman Error Embedding} algorithm~\\citep{dai2018sbeed}, known as SBEED, was proposed as a provably convergent reinforcement learning algorithm with general nonlinear function approximation. It has been successfully implemented with neural networks and achieved strong empirical results. In this work, we study the theoretical behavior of SBEED in batch-mode reinforcement learning. We prove a near-optimal performance guarantee that depends on the representation power of the used function classes and a tight notion of the distribution shift. Our results improve upon prior gua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03749","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/2007.03749/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":"2026-07-05T01:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VG7sNLdmLhmThinO7uFDHfQRFYtHWL/72c5XKMsf5HPTkYfuy7IJii1r9ElqoQeCdylL0zj0u4mZID77DufMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:15:33.901135Z"},"content_sha256":"a3c57beb60467acc40228d3915220583afe925e0638a1b63dbc3e7bd80d2095b","schema_version":"1.0","event_id":"sha256:a3c57beb60467acc40228d3915220583afe925e0638a1b63dbc3e7bd80d2095b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQRDMSRX75VCZL7UW3NRZXPEGV/bundle.json","state_url":"https://pith.science/pith/OQRDMSRX75VCZL7UW3NRZXPEGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQRDMSRX75VCZL7UW3NRZXPEGV/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":"2026-08-06T02:15:33Z","links":{"resolver":"https://pith.science/pith/OQRDMSRX75VCZL7UW3NRZXPEGV","bundle":"https://pith.science/pith/OQRDMSRX75VCZL7UW3NRZXPEGV/bundle.json","state":"https://pith.science/pith/OQRDMSRX75VCZL7UW3NRZXPEGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQRDMSRX75VCZL7UW3NRZXPEGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OQRDMSRX75VCZL7UW3NRZXPEGV","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":"cc40c995cecf28d08be5c04c287566978192148b53cabf72b216e03c39272f2a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:27:09Z","title_canon_sha256":"fafbd8251c78049bc26670dd93159ac0269503b628fae2fb4d00b754b3e577e4"},"schema_version":"1.0","source":{"id":"2007.03749","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03749","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03749v1","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03749","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"OQRDMSRX75VC","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"OQRDMSRX75VCZL7U","created_at":"2026-07-05T01:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"OQRDMSRX","created_at":"2026-07-05T01:17:09Z"}],"graph_snapshots":[{"event_id":"sha256:a3c57beb60467acc40228d3915220583afe925e0638a1b63dbc3e7bd80d2095b","target":"graph","created_at":"2026-07-05T01:17:09Z","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/2007.03749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The \\textit{Smoothed Bellman Error Embedding} algorithm~\\citep{dai2018sbeed}, known as SBEED, was proposed as a provably convergent reinforcement learning algorithm with general nonlinear function approximation. It has been successfully implemented with neural networks and achieved strong empirical results. In this work, we study the theoretical behavior of SBEED in batch-mode reinforcement learning. We prove a near-optimal performance guarantee that depends on the representation power of the used function classes and a tight notion of the distribution shift. Our results improve upon prior gua","authors_text":"Ahmed Touati, Pascal Vincent","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:27:09Z","title":"Sharp Analysis of Smoothed Bellman Error Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03749","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:b9f82202450fcf9b047536853d8a09141fed52387632f0da3b30271dd36e5eb9","target":"record","created_at":"2026-07-05T01:17:09Z","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":"cc40c995cecf28d08be5c04c287566978192148b53cabf72b216e03c39272f2a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T19:27:09Z","title_canon_sha256":"fafbd8251c78049bc26670dd93159ac0269503b628fae2fb4d00b754b3e577e4"},"schema_version":"1.0","source":{"id":"2007.03749","kind":"arxiv","version":1}},"canonical_sha256":"7422364a37ff6a2caff4b6db1cdde4356cf916bb0d1176056e2f74f536d7c979","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7422364a37ff6a2caff4b6db1cdde4356cf916bb0d1176056e2f74f536d7c979","first_computed_at":"2026-07-05T01:17:09.272378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:17:09.272378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V3c820dwS01XDtFPAKf2P6Q5Q72jN79iyFiAvxv4tCbboeCADtUJ4cfnpYZjkHcXKvf5wXsUxDxfr4T36QPnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:17:09.272772Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03749","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9f82202450fcf9b047536853d8a09141fed52387632f0da3b30271dd36e5eb9","sha256:a3c57beb60467acc40228d3915220583afe925e0638a1b63dbc3e7bd80d2095b"],"state_sha256":"fbc68dcff317f5ee899ab18e9afd5ad61688d4a8e6318e5bd0539175282555a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lhaxYpwKlm5GulGLA8r3JXw3wyzcCnlAkVNQrEmMzuj+az/sRP5pcLIsXlDNWACR6WlMVLmnSMuH0qw8rVmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:15:33.905311Z","bundle_sha256":"d07c379d09baaaedcc7d227c350075f3441ba763916428cf76c98b6d78ea4d11"}}