{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SP7OOQMJFV7NWPGFDU5DCMWV5E","short_pith_number":"pith:SP7OOQMJ","canonical_record":{"source":{"id":"2210.05805","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T22:10:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5ac73d5aaeb7339705efe8c9436f7fc631cfa5455682c6bc10238a90922b9fb","abstract_canon_sha256":"c679f609fd7eca5ef1a274cd6d17c9bafee0fe3bf1680bc198d9bad5f78a63d8"},"schema_version":"1.0"},"canonical_sha256":"93fee741892d7edb3cc51d3a3132d5e90b0aa8772f162c315900938b5b1e2ae0","source":{"kind":"arxiv","id":"2210.05805","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05805","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05805v2","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05805","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"SP7OOQMJFV7N","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SP7OOQMJFV7NWPGF","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SP7OOQMJ","created_at":"2026-07-05T05:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SP7OOQMJFV7NWPGFDU5DCMWV5E","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05805","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T22:10:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5ac73d5aaeb7339705efe8c9436f7fc631cfa5455682c6bc10238a90922b9fb","abstract_canon_sha256":"c679f609fd7eca5ef1a274cd6d17c9bafee0fe3bf1680bc198d9bad5f78a63d8"},"schema_version":"1.0"},"canonical_sha256":"93fee741892d7edb3cc51d3a3132d5e90b0aa8772f162c315900938b5b1e2ae0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:44.384053Z","signature_b64":"0P/sE5rj9U0c6GQ4UwTV+wiHNru+deiayBSY/ttCHGbg1sd2Z7F+WbxajjaQJysBNCHYc+F8r9aVhWjIkkBQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93fee741892d7edb3cc51d3a3132d5e90b0aa8772f162c315900938b5b1e2ae0","last_reissued_at":"2026-07-05T05:30:44.383512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:44.383512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05805","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vwhvHzdDJjvC2HqyQGoGATPtLbrM18B2xjmJu9E7yPCddyr/AmHHMpZbb1WbE2YIYT5s3Bwydj7ZcG5WGvv1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:13:15.133877Z"},"content_sha256":"86355d5211bedfd3c853895f40975daf20182226ae461ae3df6a2a8613b15802","schema_version":"1.0","event_id":"sha256:86355d5211bedfd3c853895f40975daf20182226ae461ae3df6a2a8613b15802"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SP7OOQMJFV7NWPGFDU5DCMWV5E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploration via Elliptical Episodic Bonuses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mikael Henaff, Minqi Jiang, Roberta Raileanu, Tim Rockt\\\"aschel","submitted_at":"2022-10-11T22:10:23Z","abstract_excerpt":"In recent years, a number of reinforcement learning (RL) methods have been proposed to explore complex environments which differ across episodes. In this work, we show that the effectiveness of these methods critically relies on a count-based episodic term in their exploration bonus. As a result, despite their success in relatively simple, noise-free settings, these methods fall short in more realistic scenarios where the state space is vast and prone to noise. To address this limitation, we introduce Exploration via Elliptical Episodic Bonuses (E3B), a new method which extends count-based epi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05805","kind":"arxiv","version":2},"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/2210.05805/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":"2026-07-05T05:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1XHHnfQEW0bntB8OxGOwoKuyDdu+e1AMd3m9d7bEbjxi+JUODrGZDOwjsfKP1evDNg/mb6QS9jHTMhS4hjJvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:13:15.134366Z"},"content_sha256":"241018f9c5a67644384231b06a32ff6e05173725e89260699a7e253b70afc475","schema_version":"1.0","event_id":"sha256:241018f9c5a67644384231b06a32ff6e05173725e89260699a7e253b70afc475"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SP7OOQMJFV7NWPGFDU5DCMWV5E/bundle.json","state_url":"https://pith.science/pith/SP7OOQMJFV7NWPGFDU5DCMWV5E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SP7OOQMJFV7NWPGFDU5DCMWV5E/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":"2026-08-11T08:13:15Z","links":{"resolver":"https://pith.science/pith/SP7OOQMJFV7NWPGFDU5DCMWV5E","bundle":"https://pith.science/pith/SP7OOQMJFV7NWPGFDU5DCMWV5E/bundle.json","state":"https://pith.science/pith/SP7OOQMJFV7NWPGFDU5DCMWV5E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SP7OOQMJFV7NWPGFDU5DCMWV5E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SP7OOQMJFV7NWPGFDU5DCMWV5E","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":"c679f609fd7eca5ef1a274cd6d17c9bafee0fe3bf1680bc198d9bad5f78a63d8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T22:10:23Z","title_canon_sha256":"f5ac73d5aaeb7339705efe8c9436f7fc631cfa5455682c6bc10238a90922b9fb"},"schema_version":"1.0","source":{"id":"2210.05805","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05805","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05805v2","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05805","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"SP7OOQMJFV7N","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SP7OOQMJFV7NWPGF","created_at":"2026-07-05T05:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SP7OOQMJ","created_at":"2026-07-05T05:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:241018f9c5a67644384231b06a32ff6e05173725e89260699a7e253b70afc475","target":"graph","created_at":"2026-07-05T05:30:44Z","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/2210.05805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, a number of reinforcement learning (RL) methods have been proposed to explore complex environments which differ across episodes. In this work, we show that the effectiveness of these methods critically relies on a count-based episodic term in their exploration bonus. As a result, despite their success in relatively simple, noise-free settings, these methods fall short in more realistic scenarios where the state space is vast and prone to noise. To address this limitation, we introduce Exploration via Elliptical Episodic Bonuses (E3B), a new method which extends count-based epi","authors_text":"Mikael Henaff, Minqi Jiang, Roberta Raileanu, Tim Rockt\\\"aschel","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T22:10:23Z","title":"Exploration via Elliptical Episodic Bonuses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05805","kind":"arxiv","version":2},"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":"sha256:86355d5211bedfd3c853895f40975daf20182226ae461ae3df6a2a8613b15802","target":"record","created_at":"2026-07-05T05:30:44Z","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":"c679f609fd7eca5ef1a274cd6d17c9bafee0fe3bf1680bc198d9bad5f78a63d8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-11T22:10:23Z","title_canon_sha256":"f5ac73d5aaeb7339705efe8c9436f7fc631cfa5455682c6bc10238a90922b9fb"},"schema_version":"1.0","source":{"id":"2210.05805","kind":"arxiv","version":2}},"canonical_sha256":"93fee741892d7edb3cc51d3a3132d5e90b0aa8772f162c315900938b5b1e2ae0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93fee741892d7edb3cc51d3a3132d5e90b0aa8772f162c315900938b5b1e2ae0","first_computed_at":"2026-07-05T05:30:44.383512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:44.383512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0P/sE5rj9U0c6GQ4UwTV+wiHNru+deiayBSY/ttCHGbg1sd2Z7F+WbxajjaQJysBNCHYc+F8r9aVhWjIkkBQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:44.384053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05805","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86355d5211bedfd3c853895f40975daf20182226ae461ae3df6a2a8613b15802","sha256:241018f9c5a67644384231b06a32ff6e05173725e89260699a7e253b70afc475"],"state_sha256":"5f8a6f400da69000eb5e38577eda4e92d1defd917b9f9222830e9af5afc1049a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fFYoSZGPRTZ2nXX70oFWPTxVAbzdeHkKt5UVF9tTTZQaksD5Kh3I8sNIV46Zkf8PxUxx+Lakwm+6Bktp/85hBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:13:15.138833Z","bundle_sha256":"e466a5d9192e12adbc330a8a13ef4d2a10935d9601e41e117328e33bca6ec7d4"}}