{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ORLTHEOTSZPSBKQ6Z3CLK3PLJF","short_pith_number":"pith:ORLTHEOT","canonical_record":{"source":{"id":"2106.02597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T16:54:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"227e947e3b5eafedd8c62096cce0724f18ca0d70401c968ffbb0110a9ddd8add","abstract_canon_sha256":"75ec87f0a2f0a626c1562e52ad1878e94b6e7c991ee468ae9db66bece06db19e"},"schema_version":"1.0"},"canonical_sha256":"74573391d3965f20aa1ecec4b56deb4958b1b42a1221c5675b0bb1ab9649fb32","source":{"kind":"arxiv","id":"2106.02597","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02597","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02597v1","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02597","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"pith_short_12","alias_value":"ORLTHEOTSZPS","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"pith_short_16","alias_value":"ORLTHEOTSZPSBKQ6","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"pith_short_8","alias_value":"ORLTHEOT","created_at":"2026-07-05T02:46:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ORLTHEOTSZPSBKQ6Z3CLK3PLJF","target":"record","payload":{"canonical_record":{"source":{"id":"2106.02597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T16:54:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"227e947e3b5eafedd8c62096cce0724f18ca0d70401c968ffbb0110a9ddd8add","abstract_canon_sha256":"75ec87f0a2f0a626c1562e52ad1878e94b6e7c991ee468ae9db66bece06db19e"},"schema_version":"1.0"},"canonical_sha256":"74573391d3965f20aa1ecec4b56deb4958b1b42a1221c5675b0bb1ab9649fb32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:21.346643Z","signature_b64":"oN+debFZQws35Ptmm4r6kqglTXAtBcFqyhyCt0xLtxFitA6iDjq5Na6yQRypGfXC6v/59i7tEaK2R0qfrP9iDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74573391d3965f20aa1ecec4b56deb4958b1b42a1221c5675b0bb1ab9649fb32","last_reissued_at":"2026-07-05T02:46:21.346180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:21.346180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.02597","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":"2026-07-05T02:46:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X0mR4HkQl5zvAA4HEX3hJowkJanEDfA/aUu+uAwEtmkYq7KvYDgLQ0kLN8KrLKf1MrY5VT8BZymgQZn9s3F3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:52:43.869955Z"},"content_sha256":"0967f0726d0c8466da2277b80998584a4d2a10210c58fc788ab84261dc1b3abe","schema_version":"1.0","event_id":"sha256:0967f0726d0c8466da2277b80998584a4d2a10210c58fc788ab84261dc1b3abe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ORLTHEOTSZPSBKQ6Z3CLK3PLJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Van Looveren, Janis Klaise, Robert-Florian Samoilescu","submitted_at":"2021-06-04T16:54:36Z","abstract_excerpt":"Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous approaches require a separate, computationally expensive optimization procedure per instance, making them impractical for both large amounts of data and high-dimensional data. Moreover, these methods are often restricted to certain subclasses of machine learning models (e.g. differentiable or tree-based models). In this work, we propose a deep reinforcement learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02597","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/2106.02597/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":"2026-07-05T02:46:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1U/CdmuNkoXLUPZ+RjQD4Bw2mQDHxlhFFRAkW57uyGwNgTsXS+wb4f9xi1wbG6SboBaTub67ND1/0xhPMHr5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:52:43.870532Z"},"content_sha256":"51167597563d10eed252585cca02e6c6256b4a0ca744d23a3dd3fc0794cafcb7","schema_version":"1.0","event_id":"sha256:51167597563d10eed252585cca02e6c6256b4a0ca744d23a3dd3fc0794cafcb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORLTHEOTSZPSBKQ6Z3CLK3PLJF/bundle.json","state_url":"https://pith.science/pith/ORLTHEOTSZPSBKQ6Z3CLK3PLJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORLTHEOTSZPSBKQ6Z3CLK3PLJF/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":"2026-08-08T16:52:43Z","links":{"resolver":"https://pith.science/pith/ORLTHEOTSZPSBKQ6Z3CLK3PLJF","bundle":"https://pith.science/pith/ORLTHEOTSZPSBKQ6Z3CLK3PLJF/bundle.json","state":"https://pith.science/pith/ORLTHEOTSZPSBKQ6Z3CLK3PLJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORLTHEOTSZPSBKQ6Z3CLK3PLJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ORLTHEOTSZPSBKQ6Z3CLK3PLJF","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":"75ec87f0a2f0a626c1562e52ad1878e94b6e7c991ee468ae9db66bece06db19e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T16:54:36Z","title_canon_sha256":"227e947e3b5eafedd8c62096cce0724f18ca0d70401c968ffbb0110a9ddd8add"},"schema_version":"1.0","source":{"id":"2106.02597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02597","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02597v1","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02597","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"pith_short_12","alias_value":"ORLTHEOTSZPS","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"pith_short_16","alias_value":"ORLTHEOTSZPSBKQ6","created_at":"2026-07-05T02:46:21Z"},{"alias_kind":"pith_short_8","alias_value":"ORLTHEOT","created_at":"2026-07-05T02:46:21Z"}],"graph_snapshots":[{"event_id":"sha256:51167597563d10eed252585cca02e6c6256b4a0ca744d23a3dd3fc0794cafcb7","target":"graph","created_at":"2026-07-05T02:46:21Z","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/2106.02597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous approaches require a separate, computationally expensive optimization procedure per instance, making them impractical for both large amounts of data and high-dimensional data. Moreover, these methods are often restricted to certain subclasses of machine learning models (e.g. differentiable or tree-based models). In this work, we propose a deep reinforcement learning","authors_text":"Arnaud Van Looveren, Janis Klaise, Robert-Florian Samoilescu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T16:54:36Z","title":"Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02597","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":"sha256:0967f0726d0c8466da2277b80998584a4d2a10210c58fc788ab84261dc1b3abe","target":"record","created_at":"2026-07-05T02:46:21Z","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":"75ec87f0a2f0a626c1562e52ad1878e94b6e7c991ee468ae9db66bece06db19e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T16:54:36Z","title_canon_sha256":"227e947e3b5eafedd8c62096cce0724f18ca0d70401c968ffbb0110a9ddd8add"},"schema_version":"1.0","source":{"id":"2106.02597","kind":"arxiv","version":1}},"canonical_sha256":"74573391d3965f20aa1ecec4b56deb4958b1b42a1221c5675b0bb1ab9649fb32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74573391d3965f20aa1ecec4b56deb4958b1b42a1221c5675b0bb1ab9649fb32","first_computed_at":"2026-07-05T02:46:21.346180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:21.346180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oN+debFZQws35Ptmm4r6kqglTXAtBcFqyhyCt0xLtxFitA6iDjq5Na6yQRypGfXC6v/59i7tEaK2R0qfrP9iDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:21.346643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0967f0726d0c8466da2277b80998584a4d2a10210c58fc788ab84261dc1b3abe","sha256:51167597563d10eed252585cca02e6c6256b4a0ca744d23a3dd3fc0794cafcb7"],"state_sha256":"8aa23c0fc8be6605d400be529d4facc78bbd5bdbf0d904ee9b382ab540a37575"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WiOqiuObItFdVLozbxJclPAV97Jy1p3oUIhcN4muOvtWYWGeCMryR2T1rZczaWDjAPFAdW7w413pMOrSZGR4Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:52:43.874707Z","bundle_sha256":"5178d0b23cfd4e7c4dd6786b8195bcf7b396b76d052dd389b503a5e817d03026"}}