{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XVZXI4WOGRJYPHXY72BWNS4N5R","short_pith_number":"pith:XVZXI4WO","canonical_record":{"source":{"id":"2210.01231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T21:08:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c92e16da2425b980c6d10cbfaf382de7ae84418d14c9330276e4eff9f7a18738","abstract_canon_sha256":"edfa5a49b2bef33c151f5bf0dc72daf6dda2fdb2db24b6687113317633c2ea8c"},"schema_version":"1.0"},"canonical_sha256":"bd737472ce3453879ef8fe8366cb8dec5b10290c1097177ea8095250e60d2e36","source":{"kind":"arxiv","id":"2210.01231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01231","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01231v1","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01231","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"XVZXI4WOGRJY","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"XVZXI4WOGRJYPHXY","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"XVZXI4WO","created_at":"2026-07-05T05:03:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XVZXI4WOGRJYPHXY72BWNS4N5R","target":"record","payload":{"canonical_record":{"source":{"id":"2210.01231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T21:08:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c92e16da2425b980c6d10cbfaf382de7ae84418d14c9330276e4eff9f7a18738","abstract_canon_sha256":"edfa5a49b2bef33c151f5bf0dc72daf6dda2fdb2db24b6687113317633c2ea8c"},"schema_version":"1.0"},"canonical_sha256":"bd737472ce3453879ef8fe8366cb8dec5b10290c1097177ea8095250e60d2e36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:08.448466Z","signature_b64":"qVMLPBIS9IATuplSXO8YTio/d4LEHCnqd1cSSVqZH3JWuRbLOsbDvFth+QdxCDs1f9hFKMM1MAjgHDfoSecRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd737472ce3453879ef8fe8366cb8dec5b10290c1097177ea8095250e60d2e36","last_reissued_at":"2026-07-05T05:03:08.448087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:08.448087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.01231","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":"2026-07-05T05:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SndczsuBvEjCQvQCYC+cARP8hTuZxbg+cioRdfQ6fvu/2e+lur3ejfwJTaMaNX2YhfPza+LXd/BorqHm4vK4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:53:43.013200Z"},"content_sha256":"b36e826201a3e39f78964dbb58deaf3c60b05a4aebfe6216e5c62f4f18b9cd47","schema_version":"1.0","event_id":"sha256:b36e826201a3e39f78964dbb58deaf3c60b05a4aebfe6216e5c62f4f18b9cd47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XVZXI4WOGRJYPHXY72BWNS4N5R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Morten Goodwin, Ole-Christoffer Granmo, Per-Arne Andersen","submitted_at":"2022-10-03T21:08:39Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is unquestionably a robust framework to train autonomous agents in a wide variety of disciplines. However, traditional deep and shallow model-free RL algorithms suffer from low sample efficiency and inadequate generalization for sparse state spaces. The options framework with temporal abstractions is perhaps the most promising method to solve these problems, but it still has noticeable shortcomings. It only guarantees local convergence, and it is challenging to automate initiation and termination conditions, which in practice are commonly hand-crafted.\n  Our pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01231","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/2210.01231/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":"2026-07-05T05:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cwr08MdEc9JF14FRFy8B3NNxivrH/ojmrA288YalJgsSQuSM2pABjEW9PDmbEe4n98Jw1bCRM7JN39aYi7nNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:53:43.013627Z"},"content_sha256":"437cd36f9b9a203da16ccfb3b7ab324b4394cd8924f4cc19b96a3be6e13f59d2","schema_version":"1.0","event_id":"sha256:437cd36f9b9a203da16ccfb3b7ab324b4394cd8924f4cc19b96a3be6e13f59d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVZXI4WOGRJYPHXY72BWNS4N5R/bundle.json","state_url":"https://pith.science/pith/XVZXI4WOGRJYPHXY72BWNS4N5R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVZXI4WOGRJYPHXY72BWNS4N5R/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":"2026-07-07T06:53:43Z","links":{"resolver":"https://pith.science/pith/XVZXI4WOGRJYPHXY72BWNS4N5R","bundle":"https://pith.science/pith/XVZXI4WOGRJYPHXY72BWNS4N5R/bundle.json","state":"https://pith.science/pith/XVZXI4WOGRJYPHXY72BWNS4N5R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVZXI4WOGRJYPHXY72BWNS4N5R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XVZXI4WOGRJYPHXY72BWNS4N5R","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":"edfa5a49b2bef33c151f5bf0dc72daf6dda2fdb2db24b6687113317633c2ea8c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T21:08:39Z","title_canon_sha256":"c92e16da2425b980c6d10cbfaf382de7ae84418d14c9330276e4eff9f7a18738"},"schema_version":"1.0","source":{"id":"2210.01231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01231","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01231v1","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01231","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"XVZXI4WOGRJY","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"XVZXI4WOGRJYPHXY","created_at":"2026-07-05T05:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"XVZXI4WO","created_at":"2026-07-05T05:03:08Z"}],"graph_snapshots":[{"event_id":"sha256:437cd36f9b9a203da16ccfb3b7ab324b4394cd8924f4cc19b96a3be6e13f59d2","target":"graph","created_at":"2026-07-05T05:03:08Z","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/2210.01231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (RL) is unquestionably a robust framework to train autonomous agents in a wide variety of disciplines. However, traditional deep and shallow model-free RL algorithms suffer from low sample efficiency and inadequate generalization for sparse state spaces. The options framework with temporal abstractions is perhaps the most promising method to solve these problems, but it still has noticeable shortcomings. It only guarantees local convergence, and it is challenging to automate initiation and termination conditions, which in practice are commonly hand-crafted.\n  Our pr","authors_text":"Morten Goodwin, Ole-Christoffer Granmo, Per-Arne Andersen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T21:08:39Z","title":"Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01231","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:b36e826201a3e39f78964dbb58deaf3c60b05a4aebfe6216e5c62f4f18b9cd47","target":"record","created_at":"2026-07-05T05:03:08Z","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":"edfa5a49b2bef33c151f5bf0dc72daf6dda2fdb2db24b6687113317633c2ea8c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T21:08:39Z","title_canon_sha256":"c92e16da2425b980c6d10cbfaf382de7ae84418d14c9330276e4eff9f7a18738"},"schema_version":"1.0","source":{"id":"2210.01231","kind":"arxiv","version":1}},"canonical_sha256":"bd737472ce3453879ef8fe8366cb8dec5b10290c1097177ea8095250e60d2e36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd737472ce3453879ef8fe8366cb8dec5b10290c1097177ea8095250e60d2e36","first_computed_at":"2026-07-05T05:03:08.448087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:08.448087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qVMLPBIS9IATuplSXO8YTio/d4LEHCnqd1cSSVqZH3JWuRbLOsbDvFth+QdxCDs1f9hFKMM1MAjgHDfoSecRAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:08.448466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.01231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b36e826201a3e39f78964dbb58deaf3c60b05a4aebfe6216e5c62f4f18b9cd47","sha256:437cd36f9b9a203da16ccfb3b7ab324b4394cd8924f4cc19b96a3be6e13f59d2"],"state_sha256":"63e93cc4cd3014421b27a902d45222e3e01f1eb3ba547c3a5578b9507e74fb13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3eR3KPUvJ6Zv7ThKJ4OZpHpt9Nh8qPfET2h4ryAazu4MlL0YGJVtWuFNyLv342v5EITF0PH9XSl4V/kGpzEXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:53:43.015591Z","bundle_sha256":"8d2b45dee459b6098c8078925f421e6da98424a944ea60c168adbbd6cc11f254"}}