{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EQQPHUFXEEAU4FOR6XZYD3TOOU","short_pith_number":"pith:EQQPHUFX","canonical_record":{"source":{"id":"1807.10299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-26T18:05:45Z","cross_cats_sorted":[],"title_canon_sha256":"f92e74466a9c2c8b01d825d30a4b85e1e9acbb589fcf2fa3a93a135b8e1ed599","abstract_canon_sha256":"9000987d36c2dbcd637264696fa4524a7d03abb91372537d55d55c3900fc5325"},"schema_version":"1.0"},"canonical_sha256":"2420f3d0b721014e15d1f5f381ee6e751b405021952c09c689750a3dad14098d","source":{"kind":"arxiv","id":"1807.10299","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.10299","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"1807.10299v1","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10299","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"EQQPHUFXEEAU","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EQQPHUFXEEAU4FOR","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EQQPHUFX","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EQQPHUFXEEAU4FOR6XZYD3TOOU","target":"record","payload":{"canonical_record":{"source":{"id":"1807.10299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-26T18:05:45Z","cross_cats_sorted":[],"title_canon_sha256":"f92e74466a9c2c8b01d825d30a4b85e1e9acbb589fcf2fa3a93a135b8e1ed599","abstract_canon_sha256":"9000987d36c2dbcd637264696fa4524a7d03abb91372537d55d55c3900fc5325"},"schema_version":"1.0"},"canonical_sha256":"2420f3d0b721014e15d1f5f381ee6e751b405021952c09c689750a3dad14098d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:41.037705Z","signature_b64":"o64b9wlSaEE0+WhCbkJBJdke0jl/h/fACZeSzyQFIddFLasbc8m7kLpT0jAS2Zm9kwp7z/5yFf/hitcSwx49BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2420f3d0b721014e15d1f5f381ee6e751b405021952c09c689750a3dad14098d","last_reissued_at":"2026-05-18T00:09:41.037179Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:41.037179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.10299","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":"2026-05-18T00:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ca9+q77pJhfPDs7QTff2IqkBHwzJYcMtXqSLOIgWRQ5qQVXCpnUP4HBg03dIFBFsDeXAMuxtUxqLjakTUG+bAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:08:25.820287Z"},"content_sha256":"603986f93575c4c82a6e6bf873230c6c50f06a484bc32c0a57b1ead81f845fe6","schema_version":"1.0","event_id":"sha256:603986f93575c4c82a6e6bf873230c6c50f06a484bc32c0a57b1ead81f845fe6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EQQPHUFXEEAU4FOR6XZYD3TOOU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Option Discovery Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dario Amodei, Harrison Edwards, Joshua Achiam, Pieter Abbeel","submitted_at":"2018-07-26T18:05:45Z","abstract_excerpt":"We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational Autoencoding Learning of Options by Reinforcement (VALOR), a new method derived from the connection. In VALOR, the policy encodes contexts from a noise distribution into trajectories, and the decoder recovers the contexts from the complete trajectories. Second: we propose a curriculum learning approach where the number of contexts seen by the agen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10299","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":""},"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":"2026-05-18T00:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BIKzk+HyKTLEuOhSuz6JCAAILjvYtZlgIu8kjGKkKN4OGBwlZdMKknyssxa+/Kzq8YadFn9Q0juXCRU9ZuvUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:08:25.820724Z"},"content_sha256":"7744d1c6e26284804f5e779dcdc7ec1c67c90692bc346ccb93751decf5804dfe","schema_version":"1.0","event_id":"sha256:7744d1c6e26284804f5e779dcdc7ec1c67c90692bc346ccb93751decf5804dfe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/bundle.json","state_url":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/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":"2026-06-06T20:08:25Z","links":{"resolver":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU","bundle":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/bundle.json","state":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EQQPHUFXEEAU4FOR6XZYD3TOOU","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":"9000987d36c2dbcd637264696fa4524a7d03abb91372537d55d55c3900fc5325","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-26T18:05:45Z","title_canon_sha256":"f92e74466a9c2c8b01d825d30a4b85e1e9acbb589fcf2fa3a93a135b8e1ed599"},"schema_version":"1.0","source":{"id":"1807.10299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.10299","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"1807.10299v1","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10299","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"EQQPHUFXEEAU","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EQQPHUFXEEAU4FOR","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EQQPHUFX","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:7744d1c6e26284804f5e779dcdc7ec1c67c90692bc346ccb93751decf5804dfe","target":"graph","created_at":"2026-05-18T00:09:41Z","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":"We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational Autoencoding Learning of Options by Reinforcement (VALOR), a new method derived from the connection. In VALOR, the policy encodes contexts from a noise distribution into trajectories, and the decoder recovers the contexts from the complete trajectories. Second: we propose a curriculum learning approach where the number of contexts seen by the agen","authors_text":"Dario Amodei, Harrison Edwards, Joshua Achiam, Pieter Abbeel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-26T18:05:45Z","title":"Variational Option Discovery Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10299","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":"sha256:603986f93575c4c82a6e6bf873230c6c50f06a484bc32c0a57b1ead81f845fe6","target":"record","created_at":"2026-05-18T00:09:41Z","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":"9000987d36c2dbcd637264696fa4524a7d03abb91372537d55d55c3900fc5325","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-26T18:05:45Z","title_canon_sha256":"f92e74466a9c2c8b01d825d30a4b85e1e9acbb589fcf2fa3a93a135b8e1ed599"},"schema_version":"1.0","source":{"id":"1807.10299","kind":"arxiv","version":1}},"canonical_sha256":"2420f3d0b721014e15d1f5f381ee6e751b405021952c09c689750a3dad14098d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2420f3d0b721014e15d1f5f381ee6e751b405021952c09c689750a3dad14098d","first_computed_at":"2026-05-18T00:09:41.037179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:41.037179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o64b9wlSaEE0+WhCbkJBJdke0jl/h/fACZeSzyQFIddFLasbc8m7kLpT0jAS2Zm9kwp7z/5yFf/hitcSwx49BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:41.037705Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.10299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:603986f93575c4c82a6e6bf873230c6c50f06a484bc32c0a57b1ead81f845fe6","sha256:7744d1c6e26284804f5e779dcdc7ec1c67c90692bc346ccb93751decf5804dfe"],"state_sha256":"2f9ee5b6185f4458c70f5c0fd7c43131d7c0a2cb7d5a41aed93bdc96889476f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p9IwxOWV60Uv2J6ZQzgDuPTN/IC/1iAnTdZAcLeEkEph80QHkRnmFGl1DZL1dtNWLw3EnkSoNvm776nCS8lHAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T20:08:25.823959Z","bundle_sha256":"96ca9b6e06646e9a0cf8ecd2eee4c9b823bd8275a42edf7d9a8f7ab8488395a2"}}