{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:74HYMRFZZH5AFCAFWWJQVHXBEY","short_pith_number":"pith:74HYMRFZ","canonical_record":{"source":{"id":"2210.02585","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T22:25:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"42535d16f731f959c75f547b32a14e58f770563f724a0654c0f7e31357319e06","abstract_canon_sha256":"9677d9c59ea084391936efc0db2ff68897eccb7e06a6d95f27db289ceec65f7b"},"schema_version":"1.0"},"canonical_sha256":"ff0f8644b9c9fa028805b5930a9ee1260b432b210d408165a03ca562c9fe495f","source":{"kind":"arxiv","id":"2210.02585","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02585","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02585v1","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02585","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"74HYMRFZZH5A","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"74HYMRFZZH5AFCAF","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"74HYMRFZ","created_at":"2026-07-05T05:03:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:74HYMRFZZH5AFCAFWWJQVHXBEY","target":"record","payload":{"canonical_record":{"source":{"id":"2210.02585","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T22:25:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"42535d16f731f959c75f547b32a14e58f770563f724a0654c0f7e31357319e06","abstract_canon_sha256":"9677d9c59ea084391936efc0db2ff68897eccb7e06a6d95f27db289ceec65f7b"},"schema_version":"1.0"},"canonical_sha256":"ff0f8644b9c9fa028805b5930a9ee1260b432b210d408165a03ca562c9fe495f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:54.378901Z","signature_b64":"GL0X730VOGfD+s8ydHL8S5IhlngBheWFubpaxT5bbXNrv/3Q2Pu4xCiFo2IVmpzxPW/opRt1/YylqKH125sPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff0f8644b9c9fa028805b5930a9ee1260b432b210d408165a03ca562c9fe495f","last_reissued_at":"2026-07-05T05:03:54.378490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:54.378490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.02585","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":"2026-07-05T05:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f53TsQsP4HLg8YZrq39TyAxmr49UQ+9DXEEgvoT0yXfcur4KLXQMOFbylj86VB5EA3DzoVsNpOX3GQcXRvgcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:28:25.341466Z"},"content_sha256":"ce94701724ad866f509a4cf6e1e2d04c7bfb8ce5e7ab6ba534415d53bbde5e96","schema_version":"1.0","event_id":"sha256:ce94701724ad866f509a4cf6e1e2d04c7bfb8ce5e7ab6ba534415d53bbde5e96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:74HYMRFZZH5AFCAFWWJQVHXBEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Query The Agent: Improving sample efficiency through epistemic uncertainty estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrei Barbu, Boris Katz, Julian Alverio","submitted_at":"2022-10-05T22:25:15Z","abstract_excerpt":"Curricula for goal-conditioned reinforcement learning agents typically rely on poor estimates of the agent's epistemic uncertainty or fail to consider the agents' epistemic uncertainty altogether, resulting in poor sample efficiency. We propose a novel algorithm, Query The Agent (QTA), which significantly improves sample efficiency by estimating the agent's epistemic uncertainty throughout the state space and setting goals in highly uncertain areas. Encouraging the agent to collect data in highly uncertain states allows the agent to improve its estimation of the value function rapidly. QTA uti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02585","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/2210.02585/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":"2026-07-05T05:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+SCQSbInuWUOxdQYdQ+Xupe9G1ip7hwV8YNUi6A0bZm6tEtLCjQPy/J+6AINgaCZoycCIsEaSiIHqMkrvBbmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:28:25.341961Z"},"content_sha256":"1b13ffdae453102b123bb36e73b40035e1dd132546d3afdd482ae045d534b03d","schema_version":"1.0","event_id":"sha256:1b13ffdae453102b123bb36e73b40035e1dd132546d3afdd482ae045d534b03d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/74HYMRFZZH5AFCAFWWJQVHXBEY/bundle.json","state_url":"https://pith.science/pith/74HYMRFZZH5AFCAFWWJQVHXBEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/74HYMRFZZH5AFCAFWWJQVHXBEY/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":"2026-08-10T07:28:25Z","links":{"resolver":"https://pith.science/pith/74HYMRFZZH5AFCAFWWJQVHXBEY","bundle":"https://pith.science/pith/74HYMRFZZH5AFCAFWWJQVHXBEY/bundle.json","state":"https://pith.science/pith/74HYMRFZZH5AFCAFWWJQVHXBEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/74HYMRFZZH5AFCAFWWJQVHXBEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:74HYMRFZZH5AFCAFWWJQVHXBEY","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":"9677d9c59ea084391936efc0db2ff68897eccb7e06a6d95f27db289ceec65f7b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T22:25:15Z","title_canon_sha256":"42535d16f731f959c75f547b32a14e58f770563f724a0654c0f7e31357319e06"},"schema_version":"1.0","source":{"id":"2210.02585","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02585","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02585v1","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02585","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"74HYMRFZZH5A","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"74HYMRFZZH5AFCAF","created_at":"2026-07-05T05:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"74HYMRFZ","created_at":"2026-07-05T05:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:1b13ffdae453102b123bb36e73b40035e1dd132546d3afdd482ae045d534b03d","target":"graph","created_at":"2026-07-05T05:03:54Z","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/2210.02585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Curricula for goal-conditioned reinforcement learning agents typically rely on poor estimates of the agent's epistemic uncertainty or fail to consider the agents' epistemic uncertainty altogether, resulting in poor sample efficiency. We propose a novel algorithm, Query The Agent (QTA), which significantly improves sample efficiency by estimating the agent's epistemic uncertainty throughout the state space and setting goals in highly uncertain areas. Encouraging the agent to collect data in highly uncertain states allows the agent to improve its estimation of the value function rapidly. QTA uti","authors_text":"Andrei Barbu, Boris Katz, Julian Alverio","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T22:25:15Z","title":"Query The Agent: Improving sample efficiency through epistemic uncertainty estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02585","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:ce94701724ad866f509a4cf6e1e2d04c7bfb8ce5e7ab6ba534415d53bbde5e96","target":"record","created_at":"2026-07-05T05:03:54Z","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":"9677d9c59ea084391936efc0db2ff68897eccb7e06a6d95f27db289ceec65f7b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T22:25:15Z","title_canon_sha256":"42535d16f731f959c75f547b32a14e58f770563f724a0654c0f7e31357319e06"},"schema_version":"1.0","source":{"id":"2210.02585","kind":"arxiv","version":1}},"canonical_sha256":"ff0f8644b9c9fa028805b5930a9ee1260b432b210d408165a03ca562c9fe495f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff0f8644b9c9fa028805b5930a9ee1260b432b210d408165a03ca562c9fe495f","first_computed_at":"2026-07-05T05:03:54.378490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:54.378490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GL0X730VOGfD+s8ydHL8S5IhlngBheWFubpaxT5bbXNrv/3Q2Pu4xCiFo2IVmpzxPW/opRt1/YylqKH125sPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:54.378901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.02585","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce94701724ad866f509a4cf6e1e2d04c7bfb8ce5e7ab6ba534415d53bbde5e96","sha256:1b13ffdae453102b123bb36e73b40035e1dd132546d3afdd482ae045d534b03d"],"state_sha256":"8838f9ff4c03be9090c0183a6022cc32b90c5cb4b9fcdcb78985079866cb26ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2CaD0BXWaRqDThnH6G3CeWpHhxCyz8iytWr6x+cr24BCPcnClwSskNdoidjj7HwajVSacfwlXHYjNoxnMhAlCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:28:25.345139Z","bundle_sha256":"f68ec7abcd367835aeaf00e1775eca0a8522a622fda6921b0a5c78b905503a7c"}}