{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YBN7DMFZ7LGVPHUOMFERIOGXHO","short_pith_number":"pith:YBN7DMFZ","canonical_record":{"source":{"id":"2207.07710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-07-15T19:09:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"16e903c8fff0e0b195d141f8c2adf932bd5d70eaa081c82d95e85e6536e93043","abstract_canon_sha256":"f487f68fd11c610d4576ab88ac26406e4b28bcbd966baf8bc822998b36f6a938"},"schema_version":"1.0"},"canonical_sha256":"c05bf1b0b9facd579e8e61491438d73b99eb0640108e5d5471a7fe9034c8aa34","source":{"kind":"arxiv","id":"2207.07710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07710","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07710v1","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07710","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"YBN7DMFZ7LGV","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"YBN7DMFZ7LGVPHUO","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"YBN7DMFZ","created_at":"2026-07-05T04:40:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YBN7DMFZ7LGVPHUOMFERIOGXHO","target":"record","payload":{"canonical_record":{"source":{"id":"2207.07710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-07-15T19:09:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"16e903c8fff0e0b195d141f8c2adf932bd5d70eaa081c82d95e85e6536e93043","abstract_canon_sha256":"f487f68fd11c610d4576ab88ac26406e4b28bcbd966baf8bc822998b36f6a938"},"schema_version":"1.0"},"canonical_sha256":"c05bf1b0b9facd579e8e61491438d73b99eb0640108e5d5471a7fe9034c8aa34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:36.158410Z","signature_b64":"TueHt/b4kdVeGRpwk+x3l5Q5OqHhLz3RuBJd32Bd/+qqFt0rqZ0Q/IEsiwU0H5mG8CPiAJcFw1rHhDetVWw5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c05bf1b0b9facd579e8e61491438d73b99eb0640108e5d5471a7fe9034c8aa34","last_reissued_at":"2026-07-05T04:40:36.157970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:36.157970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.07710","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":"2026-07-05T04:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ub8kTk4THGTijcYTcJ39x/E/OeHImx4cY4MA6h0nyUbHlOTQSp2IxyWnKXOGUYXuHzRFq1c/ceUYH9/2fgccAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:52:51.508016Z"},"content_sha256":"c03c9f27199d20466949d3a749056db24c85500b6aea477ecc9e57fda64380fc","schema_version":"1.0","event_id":"sha256:c03c9f27199d20466949d3a749056db24c85500b6aea477ecc9e57fda64380fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YBN7DMFZ7LGVPHUOMFERIOGXHO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Eric Yeh, Jesse Hostetler, Melinda Gervasio, Pedro Sequeira","submitted_at":"2022-07-15T19:09:54Z","abstract_excerpt":"We present a novel generative method for producing unseen and plausible counterfactual examples for reinforcement learning (RL) agents based upon outcome variables that characterize agent behavior. Our approach uses a variational autoencoder to train a latent space that jointly encodes information about the observations and outcome variables pertaining to an agent's behavior. Counterfactuals are generated using traversals in this latent space, via gradient-driven updates as well as latent interpolations against cases drawn from a pool of examples. These include updates to raise the likelihood "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07710","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/2207.07710/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":"2026-07-05T04:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eGZ8+ehipdOfSKIQa5bA6YfO0L8Nk4webCBcOeK5icctNLsMa7Sj1yH1wwuvjhAUt3W+xFPm0TTblHTkdA6gAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:52:51.508405Z"},"content_sha256":"21b8a05dc123c8f87d985c116c66363e0fd29b3872fb1440249e9a3b23f50e94","schema_version":"1.0","event_id":"sha256:21b8a05dc123c8f87d985c116c66363e0fd29b3872fb1440249e9a3b23f50e94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBN7DMFZ7LGVPHUOMFERIOGXHO/bundle.json","state_url":"https://pith.science/pith/YBN7DMFZ7LGVPHUOMFERIOGXHO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBN7DMFZ7LGVPHUOMFERIOGXHO/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":"2026-07-05T13:52:51Z","links":{"resolver":"https://pith.science/pith/YBN7DMFZ7LGVPHUOMFERIOGXHO","bundle":"https://pith.science/pith/YBN7DMFZ7LGVPHUOMFERIOGXHO/bundle.json","state":"https://pith.science/pith/YBN7DMFZ7LGVPHUOMFERIOGXHO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBN7DMFZ7LGVPHUOMFERIOGXHO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YBN7DMFZ7LGVPHUOMFERIOGXHO","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":"f487f68fd11c610d4576ab88ac26406e4b28bcbd966baf8bc822998b36f6a938","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-07-15T19:09:54Z","title_canon_sha256":"16e903c8fff0e0b195d141f8c2adf932bd5d70eaa081c82d95e85e6536e93043"},"schema_version":"1.0","source":{"id":"2207.07710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07710","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07710v1","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07710","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"YBN7DMFZ7LGV","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"YBN7DMFZ7LGVPHUO","created_at":"2026-07-05T04:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"YBN7DMFZ","created_at":"2026-07-05T04:40:36Z"}],"graph_snapshots":[{"event_id":"sha256:21b8a05dc123c8f87d985c116c66363e0fd29b3872fb1440249e9a3b23f50e94","target":"graph","created_at":"2026-07-05T04:40:36Z","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/2207.07710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel generative method for producing unseen and plausible counterfactual examples for reinforcement learning (RL) agents based upon outcome variables that characterize agent behavior. Our approach uses a variational autoencoder to train a latent space that jointly encodes information about the observations and outcome variables pertaining to an agent's behavior. Counterfactuals are generated using traversals in this latent space, via gradient-driven updates as well as latent interpolations against cases drawn from a pool of examples. These include updates to raise the likelihood ","authors_text":"Eric Yeh, Jesse Hostetler, Melinda Gervasio, Pedro Sequeira","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-07-15T19:09:54Z","title":"Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07710","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:c03c9f27199d20466949d3a749056db24c85500b6aea477ecc9e57fda64380fc","target":"record","created_at":"2026-07-05T04:40:36Z","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":"f487f68fd11c610d4576ab88ac26406e4b28bcbd966baf8bc822998b36f6a938","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-07-15T19:09:54Z","title_canon_sha256":"16e903c8fff0e0b195d141f8c2adf932bd5d70eaa081c82d95e85e6536e93043"},"schema_version":"1.0","source":{"id":"2207.07710","kind":"arxiv","version":1}},"canonical_sha256":"c05bf1b0b9facd579e8e61491438d73b99eb0640108e5d5471a7fe9034c8aa34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c05bf1b0b9facd579e8e61491438d73b99eb0640108e5d5471a7fe9034c8aa34","first_computed_at":"2026-07-05T04:40:36.157970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:36.157970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TueHt/b4kdVeGRpwk+x3l5Q5OqHhLz3RuBJd32Bd/+qqFt0rqZ0Q/IEsiwU0H5mG8CPiAJcFw1rHhDetVWw5Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:36.158410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.07710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c03c9f27199d20466949d3a749056db24c85500b6aea477ecc9e57fda64380fc","sha256:21b8a05dc123c8f87d985c116c66363e0fd29b3872fb1440249e9a3b23f50e94"],"state_sha256":"40f28b44851629b2c49430b95fc67cf1d2092e929e7614d9c42516ed9b502bfa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kl3gWkFoeSNXehc24oLioTAHsmkOCqZI8zrAuMaw+JTlMBb3iF6axlBzI6Mj2LMdnyPNjhTqJHGl50uophoDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:52:51.510760Z","bundle_sha256":"2a9e4076a1044ba674fe18e7dd610b6070894b2be637005ee296e322cda33e30"}}