{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PAKZCIMJPMC3QK55FB26M73IT3","short_pith_number":"pith:PAKZCIMJ","canonical_record":{"source":{"id":"2110.11960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-22T17:08:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"518e8a077930d0c3fd308ea3ab86704c91c517071014891f4204b194aab6ea95","abstract_canon_sha256":"28867e6c7dcb440e741a3bfbb69f0a7d91cea72d7eb581b5359e8e00b4731b5c"},"schema_version":"1.0"},"canonical_sha256":"78159121897b05b82bbd2875e67f689ed2fd8d7c20ace66240748fc218e3319d","source":{"kind":"arxiv","id":"2110.11960","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.11960","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"arxiv_version","alias_value":"2110.11960v2","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11960","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"pith_short_12","alias_value":"PAKZCIMJPMC3","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"pith_short_16","alias_value":"PAKZCIMJPMC3QK55","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"pith_short_8","alias_value":"PAKZCIMJ","created_at":"2026-07-05T06:39:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PAKZCIMJPMC3QK55FB26M73IT3","target":"record","payload":{"canonical_record":{"source":{"id":"2110.11960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-22T17:08:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"518e8a077930d0c3fd308ea3ab86704c91c517071014891f4204b194aab6ea95","abstract_canon_sha256":"28867e6c7dcb440e741a3bfbb69f0a7d91cea72d7eb581b5359e8e00b4731b5c"},"schema_version":"1.0"},"canonical_sha256":"78159121897b05b82bbd2875e67f689ed2fd8d7c20ace66240748fc218e3319d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:28.800281Z","signature_b64":"GzSuyl0LN+O5u6iopiYGMbyz/XjG6FV2JBnfbdKPa1wdpR1cg6gt0T88ZXC0CRfeUtwlfEJ4clSbdGThtNZWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78159121897b05b82bbd2875e67f689ed2fd8d7c20ace66240748fc218e3319d","last_reissued_at":"2026-07-05T06:39:28.799737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:28.799737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.11960","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:39:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDpCW1TKR/d1eg2ffHujErWu7rx4zB/nuu5103LVDrABZBrSpsIYAgtUmjJ/O+cCcWRoRSb2Xe7ioVV2aP/mDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:13:57.432728Z"},"content_sha256":"0bf257f778f70b38bb78381511abb52753a8a8472ea4c8baba813a735a63d9a1","schema_version":"1.0","event_id":"sha256:0bf257f778f70b38bb78381511abb52753a8a8472ea4c8baba813a735a63d9a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PAKZCIMJPMC3QK55FB26M73IT3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fabrizio Silvestri, Gabriele Tolomei, He Zhu, Hongshik Ahn, Jia Wang, Ziheng Chen","submitted_at":"2021-10-22T17:08:49Z","abstract_excerpt":"Counterfactual examples (CFs) are one of the most popular methods for attaching post-hoc explanations to machine learning (ML) models. However, existing CF generation methods either exploit the internals of specific models or depend on each sample's neighborhood, thus they are hard to generalize for complex models and inefficient for large datasets. This work aims to overcome these limitations and introduces ReLAX, a model-agnostic algorithm to generate optimal counterfactual explanations. Specifically, we formulate the problem of crafting CFs as a sequential decision-making task and then find"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11960","kind":"arxiv","version":2},"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/2110.11960/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":"2026-07-05T06:39:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JCjwmCCmPVEbJXfxEYZXTEkgVgFGNGo6aDNDqZgH1DU+ID6JXAwINEuwVYxdfR3I/NeyeYMjKwIK086XhgBNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:13:57.433664Z"},"content_sha256":"0b7f7eee64991286918297f4887d390981c77e7a706a46546d03cc63c753f076","schema_version":"1.0","event_id":"sha256:0b7f7eee64991286918297f4887d390981c77e7a706a46546d03cc63c753f076"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PAKZCIMJPMC3QK55FB26M73IT3/bundle.json","state_url":"https://pith.science/pith/PAKZCIMJPMC3QK55FB26M73IT3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PAKZCIMJPMC3QK55FB26M73IT3/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":"2026-08-03T17:13:57Z","links":{"resolver":"https://pith.science/pith/PAKZCIMJPMC3QK55FB26M73IT3","bundle":"https://pith.science/pith/PAKZCIMJPMC3QK55FB26M73IT3/bundle.json","state":"https://pith.science/pith/PAKZCIMJPMC3QK55FB26M73IT3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PAKZCIMJPMC3QK55FB26M73IT3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PAKZCIMJPMC3QK55FB26M73IT3","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":"28867e6c7dcb440e741a3bfbb69f0a7d91cea72d7eb581b5359e8e00b4731b5c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-22T17:08:49Z","title_canon_sha256":"518e8a077930d0c3fd308ea3ab86704c91c517071014891f4204b194aab6ea95"},"schema_version":"1.0","source":{"id":"2110.11960","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.11960","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"arxiv_version","alias_value":"2110.11960v2","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11960","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"pith_short_12","alias_value":"PAKZCIMJPMC3","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"pith_short_16","alias_value":"PAKZCIMJPMC3QK55","created_at":"2026-07-05T06:39:28Z"},{"alias_kind":"pith_short_8","alias_value":"PAKZCIMJ","created_at":"2026-07-05T06:39:28Z"}],"graph_snapshots":[{"event_id":"sha256:0b7f7eee64991286918297f4887d390981c77e7a706a46546d03cc63c753f076","target":"graph","created_at":"2026-07-05T06:39:28Z","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/2110.11960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual examples (CFs) are one of the most popular methods for attaching post-hoc explanations to machine learning (ML) models. However, existing CF generation methods either exploit the internals of specific models or depend on each sample's neighborhood, thus they are hard to generalize for complex models and inefficient for large datasets. This work aims to overcome these limitations and introduces ReLAX, a model-agnostic algorithm to generate optimal counterfactual explanations. Specifically, we formulate the problem of crafting CFs as a sequential decision-making task and then find","authors_text":"Fabrizio Silvestri, Gabriele Tolomei, He Zhu, Hongshik Ahn, Jia Wang, Ziheng Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-22T17:08:49Z","title":"ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11960","kind":"arxiv","version":2},"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":"sha256:0bf257f778f70b38bb78381511abb52753a8a8472ea4c8baba813a735a63d9a1","target":"record","created_at":"2026-07-05T06:39:28Z","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":"28867e6c7dcb440e741a3bfbb69f0a7d91cea72d7eb581b5359e8e00b4731b5c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-22T17:08:49Z","title_canon_sha256":"518e8a077930d0c3fd308ea3ab86704c91c517071014891f4204b194aab6ea95"},"schema_version":"1.0","source":{"id":"2110.11960","kind":"arxiv","version":2}},"canonical_sha256":"78159121897b05b82bbd2875e67f689ed2fd8d7c20ace66240748fc218e3319d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78159121897b05b82bbd2875e67f689ed2fd8d7c20ace66240748fc218e3319d","first_computed_at":"2026-07-05T06:39:28.799737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:28.799737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzSuyl0LN+O5u6iopiYGMbyz/XjG6FV2JBnfbdKPa1wdpR1cg6gt0T88ZXC0CRfeUtwlfEJ4clSbdGThtNZWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:28.800281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.11960","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bf257f778f70b38bb78381511abb52753a8a8472ea4c8baba813a735a63d9a1","sha256:0b7f7eee64991286918297f4887d390981c77e7a706a46546d03cc63c753f076"],"state_sha256":"1e5826036d1df2fd7d4a6a2291748d90ea092b5e630d402eeac80fcf9c37f77d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1xsEPGzlj3ek2byK57z/eIN1uvCIPVO1fPMdrCTqoEjRtda43nGqugWIF2+srtecNqHitaM1/tCjfNf0nDIAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:13:57.452441Z","bundle_sha256":"f494199aba77d5cbd77eff95461f5ed90b585d1ac99a17076466db180c7c00cf"}}