{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OHUJH2YVDRMMNTHZGNQ4K62FOE","short_pith_number":"pith:OHUJH2YV","canonical_record":{"source":{"id":"2207.06269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T15:17:26Z","cross_cats_sorted":[],"title_canon_sha256":"34e4951ccf58da4e0b8f7cfc8efd93616f68a77f551cb87315310edab2b372ae","abstract_canon_sha256":"ce08cf662a6a9ec7cc283c8e12049b38b50ef466d9ef53afde78fc50c87f5e22"},"schema_version":"1.0"},"canonical_sha256":"71e893eb151c58c6ccf93361c57b457135a9e83b7e0d125f2db71c7ce6bed72b","source":{"kind":"arxiv","id":"2207.06269","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06269","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06269v1","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06269","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"pith_short_12","alias_value":"OHUJH2YVDRMM","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"pith_short_16","alias_value":"OHUJH2YVDRMMNTHZ","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"pith_short_8","alias_value":"OHUJH2YV","created_at":"2026-07-05T04:40:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OHUJH2YVDRMMNTHZGNQ4K62FOE","target":"record","payload":{"canonical_record":{"source":{"id":"2207.06269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T15:17:26Z","cross_cats_sorted":[],"title_canon_sha256":"34e4951ccf58da4e0b8f7cfc8efd93616f68a77f551cb87315310edab2b372ae","abstract_canon_sha256":"ce08cf662a6a9ec7cc283c8e12049b38b50ef466d9ef53afde78fc50c87f5e22"},"schema_version":"1.0"},"canonical_sha256":"71e893eb151c58c6ccf93361c57b457135a9e83b7e0d125f2db71c7ce6bed72b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:03.388805Z","signature_b64":"4sapHZsgwU3mbz1pJU7M+2mZBijvrMnU6TnndgbQHXENKx4WIu2blH/dfONDDUeVG7jopP/K9cyByQu7FYdnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71e893eb151c58c6ccf93361c57b457135a9e83b7e0d125f2db71c7ce6bed72b","last_reissued_at":"2026-07-05T04:40:03.388247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:03.388247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.06269","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":"2026-07-05T04:40:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hu+e3IGravfxGn59GUJgCgimnlz9ROohfDWP3Y6idgPQpViO81BhzBUvoLlady4I6Ay35YGbpSOE6hc2PDkcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:16:44.391809Z"},"content_sha256":"9740cb8302c6f6ed86226d03511a788ea4cabc309d6bd2b9af70c2cff757a00f","schema_version":"1.0","event_id":"sha256:9740cb8302c6f6ed86226d03511a788ea4cabc309d6bd2b9af70c2cff757a00f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OHUJH2YVDRMMNTHZGNQ4K62FOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Optimization with Sparse Global Contrastive Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Finale Doshi-Velez, Jiayu Yao, Sonali Parbhoo, Weiwei Pan","submitted_at":"2022-07-13T15:17:26Z","abstract_excerpt":"We develop a Reinforcement Learning (RL) framework for improving an existing behavior policy via sparse, user-interpretable changes. Our goal is to make minimal changes while gaining as much benefit as possible. We define a minimal change as having a sparse, global contrastive explanation between the original and proposed policy. We improve the current policy with the constraint of keeping that global contrastive explanation short. We demonstrate our framework with a discrete MDP and a continuous 2D navigation domain."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06269","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/2207.06269/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":"2026-07-05T04:40:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fAYZ8VdBIdlBKmJPkiPxbG0xFtbvemQCkOsJrLJbyRC+OXAMEiA+CbW0oblujIOnvSEPNOpCCDskOtKBqqhgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:16:44.393168Z"},"content_sha256":"dc105c2186fb4cdb768c6a6eb2ec13ba632395a67084e8bca3f81cdbf435bc6c","schema_version":"1.0","event_id":"sha256:dc105c2186fb4cdb768c6a6eb2ec13ba632395a67084e8bca3f81cdbf435bc6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHUJH2YVDRMMNTHZGNQ4K62FOE/bundle.json","state_url":"https://pith.science/pith/OHUJH2YVDRMMNTHZGNQ4K62FOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHUJH2YVDRMMNTHZGNQ4K62FOE/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":"2026-08-20T01:16:44Z","links":{"resolver":"https://pith.science/pith/OHUJH2YVDRMMNTHZGNQ4K62FOE","bundle":"https://pith.science/pith/OHUJH2YVDRMMNTHZGNQ4K62FOE/bundle.json","state":"https://pith.science/pith/OHUJH2YVDRMMNTHZGNQ4K62FOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHUJH2YVDRMMNTHZGNQ4K62FOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OHUJH2YVDRMMNTHZGNQ4K62FOE","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":"ce08cf662a6a9ec7cc283c8e12049b38b50ef466d9ef53afde78fc50c87f5e22","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T15:17:26Z","title_canon_sha256":"34e4951ccf58da4e0b8f7cfc8efd93616f68a77f551cb87315310edab2b372ae"},"schema_version":"1.0","source":{"id":"2207.06269","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06269","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06269v1","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06269","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"pith_short_12","alias_value":"OHUJH2YVDRMM","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"pith_short_16","alias_value":"OHUJH2YVDRMMNTHZ","created_at":"2026-07-05T04:40:03Z"},{"alias_kind":"pith_short_8","alias_value":"OHUJH2YV","created_at":"2026-07-05T04:40:03Z"}],"graph_snapshots":[{"event_id":"sha256:dc105c2186fb4cdb768c6a6eb2ec13ba632395a67084e8bca3f81cdbf435bc6c","target":"graph","created_at":"2026-07-05T04:40:03Z","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/2207.06269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We develop a Reinforcement Learning (RL) framework for improving an existing behavior policy via sparse, user-interpretable changes. Our goal is to make minimal changes while gaining as much benefit as possible. We define a minimal change as having a sparse, global contrastive explanation between the original and proposed policy. We improve the current policy with the constraint of keeping that global contrastive explanation short. We demonstrate our framework with a discrete MDP and a continuous 2D navigation domain.","authors_text":"Finale Doshi-Velez, Jiayu Yao, Sonali Parbhoo, Weiwei Pan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T15:17:26Z","title":"Policy Optimization with Sparse Global Contrastive Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06269","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":"sha256:9740cb8302c6f6ed86226d03511a788ea4cabc309d6bd2b9af70c2cff757a00f","target":"record","created_at":"2026-07-05T04:40:03Z","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":"ce08cf662a6a9ec7cc283c8e12049b38b50ef466d9ef53afde78fc50c87f5e22","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T15:17:26Z","title_canon_sha256":"34e4951ccf58da4e0b8f7cfc8efd93616f68a77f551cb87315310edab2b372ae"},"schema_version":"1.0","source":{"id":"2207.06269","kind":"arxiv","version":1}},"canonical_sha256":"71e893eb151c58c6ccf93361c57b457135a9e83b7e0d125f2db71c7ce6bed72b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71e893eb151c58c6ccf93361c57b457135a9e83b7e0d125f2db71c7ce6bed72b","first_computed_at":"2026-07-05T04:40:03.388247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:03.388247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4sapHZsgwU3mbz1pJU7M+2mZBijvrMnU6TnndgbQHXENKx4WIu2blH/dfONDDUeVG7jopP/K9cyByQu7FYdnCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:03.388805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.06269","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9740cb8302c6f6ed86226d03511a788ea4cabc309d6bd2b9af70c2cff757a00f","sha256:dc105c2186fb4cdb768c6a6eb2ec13ba632395a67084e8bca3f81cdbf435bc6c"],"state_sha256":"d84f6c53188004900af426a780a00d30885ef401123579f011aed2d654f3491d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EnY0XAApwUeUT2awG5xnLyPGLy5MKrCS/hY3sVQW6CP1W9R7iytmlGmar1y4xOoMcj2Z7pAkKE5bevVWwDMHCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:16:44.397611Z","bundle_sha256":"4f631a4429e5389fc3827132dc847f22dc17296c8b16377ecd58019307913a90"}}