{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JAV723NTLWJSZK522UY3GCVCZW","short_pith_number":"pith:JAV723NT","canonical_record":{"source":{"id":"1911.08701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T04:30:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"08f88db93ac9d59bec4a1bbff0754cf7fae5e2d434905737195481f3f8055db3","abstract_canon_sha256":"121cc0ae81ecfa39de56d40b4d77be4ff1c29c84a62e16f3eb967a7ae2428a1a"},"schema_version":"1.0"},"canonical_sha256":"482bfd6db35d932cabbad531b30aa2cdb1c453e8ce1c3df4d293e862a1bb7da0","source":{"kind":"arxiv","id":"1911.08701","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.08701","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"arxiv_version","alias_value":"1911.08701v1","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08701","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"pith_short_12","alias_value":"JAV723NTLWJS","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"pith_short_16","alias_value":"JAV723NTLWJSZK52","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"pith_short_8","alias_value":"JAV723NT","created_at":"2026-07-05T00:20:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JAV723NTLWJSZK522UY3GCVCZW","target":"record","payload":{"canonical_record":{"source":{"id":"1911.08701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T04:30:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"08f88db93ac9d59bec4a1bbff0754cf7fae5e2d434905737195481f3f8055db3","abstract_canon_sha256":"121cc0ae81ecfa39de56d40b4d77be4ff1c29c84a62e16f3eb967a7ae2428a1a"},"schema_version":"1.0"},"canonical_sha256":"482bfd6db35d932cabbad531b30aa2cdb1c453e8ce1c3df4d293e862a1bb7da0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:35.328277Z","signature_b64":"SNqPK2pp7vYb4lDw+mXBM/GMyq9LV/Cr+WCiigEbXgvJnAAuEldMb/x7a4SQ3kjh+6Fo9RBPNyALVrJxih5MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"482bfd6db35d932cabbad531b30aa2cdb1c453e8ce1c3df4d293e862a1bb7da0","last_reissued_at":"2026-07-05T00:20:35.327868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:35.327868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.08701","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":"2026-07-05T00:20:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QqNRpk/i1pBvveinjMN7uo6viGgbcNEHz2hFBMmHWKHKFxncy87UtLYgyLEzHVAedHJJVQ9qq2ceqbVVWMpDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:55:14.739258Z"},"content_sha256":"f6cff27bf1e89ed107d337316d84eeefb41f6a95339787865c20d5113289179b","schema_version":"1.0","event_id":"sha256:f6cff27bf1e89ed107d337316d84eeefb41f6a95339787865c20d5113289179b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JAV723NTLWJSZK522UY3GCVCZW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Curiosity for Efficient Exploration in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Ramos, Lionel Ott, Tom Blau","submitted_at":"2019-11-20T04:30:20Z","abstract_excerpt":"Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\\epsilon$-greedy. This contributes to the problem of high sample complexity, as the algorithm wastes effort by repeatedly visiting parts of the state space that have already been explored. We introduce a novel method based on Bayesian linear regression and latent space embedding to generate an intrinsic reward signal that encourages the learning agent to seek out unexplored parts of the state space. This method is computationally ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08701","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/1911.08701/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":"2026-07-05T00:20:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9mWTQGqT3bXHGCycrY63U5ovPj5+0ljxVvPOBauF0dizwFHiIkgbzciC7G//pC2FY8fL1x/weOoCKZavusu4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:55:14.739904Z"},"content_sha256":"6fd4e232daea1fea7ddec4259425139ca3b7b4c3b9a34fdaafe72584d24aff93","schema_version":"1.0","event_id":"sha256:6fd4e232daea1fea7ddec4259425139ca3b7b4c3b9a34fdaafe72584d24aff93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW/bundle.json","state_url":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JAV723NTLWJSZK522UY3GCVCZW/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":"2026-07-09T05:55:14Z","links":{"resolver":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW","bundle":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW/bundle.json","state":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JAV723NTLWJSZK522UY3GCVCZW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JAV723NTLWJSZK522UY3GCVCZW","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":"121cc0ae81ecfa39de56d40b4d77be4ff1c29c84a62e16f3eb967a7ae2428a1a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T04:30:20Z","title_canon_sha256":"08f88db93ac9d59bec4a1bbff0754cf7fae5e2d434905737195481f3f8055db3"},"schema_version":"1.0","source":{"id":"1911.08701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.08701","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"arxiv_version","alias_value":"1911.08701v1","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08701","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"pith_short_12","alias_value":"JAV723NTLWJS","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"pith_short_16","alias_value":"JAV723NTLWJSZK52","created_at":"2026-07-05T00:20:35Z"},{"alias_kind":"pith_short_8","alias_value":"JAV723NT","created_at":"2026-07-05T00:20:35Z"}],"graph_snapshots":[{"event_id":"sha256:6fd4e232daea1fea7ddec4259425139ca3b7b4c3b9a34fdaafe72584d24aff93","target":"graph","created_at":"2026-07-05T00:20:35Z","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/1911.08701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\\epsilon$-greedy. This contributes to the problem of high sample complexity, as the algorithm wastes effort by repeatedly visiting parts of the state space that have already been explored. We introduce a novel method based on Bayesian linear regression and latent space embedding to generate an intrinsic reward signal that encourages the learning agent to seek out unexplored parts of the state space. This method is computationally ef","authors_text":"Fabio Ramos, Lionel Ott, Tom Blau","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T04:30:20Z","title":"Bayesian Curiosity for Efficient Exploration in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08701","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:f6cff27bf1e89ed107d337316d84eeefb41f6a95339787865c20d5113289179b","target":"record","created_at":"2026-07-05T00:20:35Z","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":"121cc0ae81ecfa39de56d40b4d77be4ff1c29c84a62e16f3eb967a7ae2428a1a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T04:30:20Z","title_canon_sha256":"08f88db93ac9d59bec4a1bbff0754cf7fae5e2d434905737195481f3f8055db3"},"schema_version":"1.0","source":{"id":"1911.08701","kind":"arxiv","version":1}},"canonical_sha256":"482bfd6db35d932cabbad531b30aa2cdb1c453e8ce1c3df4d293e862a1bb7da0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"482bfd6db35d932cabbad531b30aa2cdb1c453e8ce1c3df4d293e862a1bb7da0","first_computed_at":"2026-07-05T00:20:35.327868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:20:35.327868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SNqPK2pp7vYb4lDw+mXBM/GMyq9LV/Cr+WCiigEbXgvJnAAuEldMb/x7a4SQ3kjh+6Fo9RBPNyALVrJxih5MAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:20:35.328277Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.08701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6cff27bf1e89ed107d337316d84eeefb41f6a95339787865c20d5113289179b","sha256:6fd4e232daea1fea7ddec4259425139ca3b7b4c3b9a34fdaafe72584d24aff93"],"state_sha256":"055aebb2d4bc9e18ecb335dc0c7bab21a2c399238c9fdd61d25fd897954aff06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FnFBXC/SmCyyZIMO9CByKu4STNow/SmhntMQbVv0eTPmvN3nWbnFTO1o9SBWjaYnBEikS65iWSwBCMqJUuRDDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:55:14.743523Z","bundle_sha256":"a611b432e8c101df30b74cd7a34897bd2fadd1d3e15353c505794a9a6d0baa63"}}