{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AZKTROVPJOYQDHZMYHTEU5BFQI","short_pith_number":"pith:AZKTROVP","canonical_record":{"source":{"id":"1903.06309","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-15T00:40:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"624210dad6d0949939a0ff4e47048bf0bfa54434abc5785e2b1090ac5e547499","abstract_canon_sha256":"5e7b23880d584b251be4701080df11d9c1c96ed44511dcc756645a4fbd7bc27d"},"schema_version":"1.0"},"canonical_sha256":"065538baaf4bb1019f2cc1e64a742582218b16f490438ba9385fb1462af64ca2","source":{"kind":"arxiv","id":"1903.06309","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.06309","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.06309v2","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06309","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"AZKTROVPJOYQ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AZKTROVPJOYQDHZM","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AZKTROVP","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AZKTROVPJOYQDHZMYHTEU5BFQI","target":"record","payload":{"canonical_record":{"source":{"id":"1903.06309","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-15T00:40:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"624210dad6d0949939a0ff4e47048bf0bfa54434abc5785e2b1090ac5e547499","abstract_canon_sha256":"5e7b23880d584b251be4701080df11d9c1c96ed44511dcc756645a4fbd7bc27d"},"schema_version":"1.0"},"canonical_sha256":"065538baaf4bb1019f2cc1e64a742582218b16f490438ba9385fb1462af64ca2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:40.934418Z","signature_b64":"sQNSDTflmZ3qX6pigtwHhs+pNdI0KICqAPrABew6WENvUk7MGE/IBASTDV3KUIJVBrDGbyPEqZJ6gzE545CQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"065538baaf4bb1019f2cc1e64a742582218b16f490438ba9385fb1462af64ca2","last_reissued_at":"2026-05-17T23:46:40.933708Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:40.933708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.06309","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":"2026-05-17T23:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RYAmy4pRXkLRKC7nGtkNRPwGj4aJ6wGgQfxEo06himaHmcJLM04YuxKZJ+vbVFQ4UQXIm3UbxlJRXpQW5JATCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:34:22.603540Z"},"content_sha256":"2ca1c16580d8101dad01d63e41ca20c251676c90b96f50bf6e58bdebd50fa200","schema_version":"1.0","event_id":"sha256:2ca1c16580d8101dad01d63e41ca20c251676c90b96f50bf6e58bdebd50fa200"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AZKTROVPJOYQDHZMYHTEU5BFQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Variance for Changing Sparse-Reward Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Carlos Florensa, David Held, Pengsheng Guo, Xingyu Lin","submitted_at":"2019-03-15T00:40:59Z","abstract_excerpt":"Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better exploration in changing sparse-reward environments. Unlike previous works which explicitly model environmental changes, we analyze the relationship between the value function and the optimal exploration for a Gaussian-parameterized policy and show that our theory leads to an effective strategy for adjusting the variance of the policy, enabling fast adapt to changes in a variety of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06309","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":""},"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":"2026-05-17T23:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qk5uRDuXhy8KAP9LG772y9UpE0i5oQjqhP1udy6w7fJNGoyorpyBhCbwIRGmHBS7vUF1uvQh+NkCd5uRZjyNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:34:22.603888Z"},"content_sha256":"44a28ab61149423e841ffd0450916da71cc19c91996f1a3a260fd5283e315652","schema_version":"1.0","event_id":"sha256:44a28ab61149423e841ffd0450916da71cc19c91996f1a3a260fd5283e315652"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/bundle.json","state_url":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/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":"2026-06-01T11:34:22Z","links":{"resolver":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI","bundle":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/bundle.json","state":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AZKTROVPJOYQDHZMYHTEU5BFQI","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":"5e7b23880d584b251be4701080df11d9c1c96ed44511dcc756645a4fbd7bc27d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-15T00:40:59Z","title_canon_sha256":"624210dad6d0949939a0ff4e47048bf0bfa54434abc5785e2b1090ac5e547499"},"schema_version":"1.0","source":{"id":"1903.06309","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.06309","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.06309v2","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06309","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"AZKTROVPJOYQ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AZKTROVPJOYQDHZM","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AZKTROVP","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:44a28ab61149423e841ffd0450916da71cc19c91996f1a3a260fd5283e315652","target":"graph","created_at":"2026-05-17T23:46:40Z","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"},"paper":{"abstract_excerpt":"Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better exploration in changing sparse-reward environments. Unlike previous works which explicitly model environmental changes, we analyze the relationship between the value function and the optimal exploration for a Gaussian-parameterized policy and show that our theory leads to an effective strategy for adjusting the variance of the policy, enabling fast adapt to changes in a variety of s","authors_text":"Carlos Florensa, David Held, Pengsheng Guo, Xingyu Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-15T00:40:59Z","title":"Adaptive Variance for Changing Sparse-Reward Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06309","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":"sha256:2ca1c16580d8101dad01d63e41ca20c251676c90b96f50bf6e58bdebd50fa200","target":"record","created_at":"2026-05-17T23:46:40Z","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":"5e7b23880d584b251be4701080df11d9c1c96ed44511dcc756645a4fbd7bc27d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-15T00:40:59Z","title_canon_sha256":"624210dad6d0949939a0ff4e47048bf0bfa54434abc5785e2b1090ac5e547499"},"schema_version":"1.0","source":{"id":"1903.06309","kind":"arxiv","version":2}},"canonical_sha256":"065538baaf4bb1019f2cc1e64a742582218b16f490438ba9385fb1462af64ca2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"065538baaf4bb1019f2cc1e64a742582218b16f490438ba9385fb1462af64ca2","first_computed_at":"2026-05-17T23:46:40.933708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:40.933708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sQNSDTflmZ3qX6pigtwHhs+pNdI0KICqAPrABew6WENvUk7MGE/IBASTDV3KUIJVBrDGbyPEqZJ6gzE545CQBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:40.934418Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.06309","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ca1c16580d8101dad01d63e41ca20c251676c90b96f50bf6e58bdebd50fa200","sha256:44a28ab61149423e841ffd0450916da71cc19c91996f1a3a260fd5283e315652"],"state_sha256":"5b243322c05870b20de825f2fb06dd9cf8ac0f29abf897531b508b9222c082b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6VUFLq3TTBuBSIsmBa2wNpKeWs/OoUwv+RDMLh1T6RdvRBuCeZdPqEE0t54LloQi9raoIET3kyzAiNesK7E6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T11:34:22.605869Z","bundle_sha256":"a456f30ab36fffb7ebad14f87b9cfe8da57c8b97d8c4efd303a890e1eea4dc1f"}}