{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4ZTLVWMPNIDWGWWBWFDZGEM4DO","short_pith_number":"pith:4ZTLVWMP","canonical_record":{"source":{"id":"2205.15540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-31T04:57:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"29ad4607e5db34ad930643e5da6ca3d1e75fad4c21c244dcfdc2421b61ea0e7e","abstract_canon_sha256":"8739fd8ba8294de6fa9f60a872c257ff18f8fc4f94cef0ba613f0686382387b8"},"schema_version":"1.0"},"canonical_sha256":"e666bad98f6a07635ac1b14793119c1ba0264dafc9eb528b1a8d48f048bab08b","source":{"kind":"arxiv","id":"2205.15540","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15540","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15540v1","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15540","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"pith_short_12","alias_value":"4ZTLVWMPNIDW","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"4ZTLVWMPNIDWGWWB","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"4ZTLVWMP","created_at":"2026-07-05T04:27:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4ZTLVWMPNIDWGWWBWFDZGEM4DO","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-31T04:57:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"29ad4607e5db34ad930643e5da6ca3d1e75fad4c21c244dcfdc2421b61ea0e7e","abstract_canon_sha256":"8739fd8ba8294de6fa9f60a872c257ff18f8fc4f94cef0ba613f0686382387b8"},"schema_version":"1.0"},"canonical_sha256":"e666bad98f6a07635ac1b14793119c1ba0264dafc9eb528b1a8d48f048bab08b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:34.089250Z","signature_b64":"NUe1+NygxxuzXfk5hfnquTHJrD2tMkNXcMeE1aXNwpivPHzK+rU6d8b0XtW4nK/H3rc3PeNDtrEuzDveGOPVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e666bad98f6a07635ac1b14793119c1ba0264dafc9eb528b1a8d48f048bab08b","last_reissued_at":"2026-07-05T04:27:34.088743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:34.088743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15540","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":"2026-07-05T04:27:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YT9i7EKBHngzqK/gzf2ckT03hf621lr3oQs67ltoBB+cRYL/3HfjXnD8Kf9qVnhuxzGGKazq4zVPcdV0ARtuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:12:29.857595Z"},"content_sha256":"65aacccf52ccf6be63a1667f376a1681b783c2ce7884a65d39e4d83c6d0899db","schema_version":"1.0","event_id":"sha256:65aacccf52ccf6be63a1667f376a1681b783c2ce7884a65d39e4d83c6d0899db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4ZTLVWMPNIDWGWWBWFDZGEM4DO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Caiming Xiong, Jia Li, Steven C.H. Hoi, Wenzhuo Yang","submitted_at":"2022-05-31T04:57:06Z","abstract_excerpt":"Counterfactual explanation is an important Explainable AI technique to explain machine learning predictions. Despite being studied actively, existing optimization-based methods often assume that the underlying machine-learning model is differentiable and treat categorical attributes as continuous ones, which restricts their real-world applications when categorical attributes have many different values or the model is non-differentiable. To make counterfactual explanation suitable for real-world applications, we propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE), whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15540","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/2205.15540/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":"2026-07-05T04:27:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3pqWtxKB090pWnKc0gNTks+l55XFMxqXmWM/IyU9apLZDcg7QOJSwV9juTUIFEvhYCR3YGl8k4J6LATirT4BAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:12:29.858271Z"},"content_sha256":"51bfdd110dc7360d78050f37300a739d754732aa939329a42ddd237cdac91230","schema_version":"1.0","event_id":"sha256:51bfdd110dc7360d78050f37300a739d754732aa939329a42ddd237cdac91230"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ZTLVWMPNIDWGWWBWFDZGEM4DO/bundle.json","state_url":"https://pith.science/pith/4ZTLVWMPNIDWGWWBWFDZGEM4DO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ZTLVWMPNIDWGWWBWFDZGEM4DO/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":"2026-08-21T13:12:29Z","links":{"resolver":"https://pith.science/pith/4ZTLVWMPNIDWGWWBWFDZGEM4DO","bundle":"https://pith.science/pith/4ZTLVWMPNIDWGWWBWFDZGEM4DO/bundle.json","state":"https://pith.science/pith/4ZTLVWMPNIDWGWWBWFDZGEM4DO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ZTLVWMPNIDWGWWBWFDZGEM4DO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4ZTLVWMPNIDWGWWBWFDZGEM4DO","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":"8739fd8ba8294de6fa9f60a872c257ff18f8fc4f94cef0ba613f0686382387b8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-31T04:57:06Z","title_canon_sha256":"29ad4607e5db34ad930643e5da6ca3d1e75fad4c21c244dcfdc2421b61ea0e7e"},"schema_version":"1.0","source":{"id":"2205.15540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15540","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15540v1","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15540","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"pith_short_12","alias_value":"4ZTLVWMPNIDW","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"4ZTLVWMPNIDWGWWB","created_at":"2026-07-05T04:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"4ZTLVWMP","created_at":"2026-07-05T04:27:34Z"}],"graph_snapshots":[{"event_id":"sha256:51bfdd110dc7360d78050f37300a739d754732aa939329a42ddd237cdac91230","target":"graph","created_at":"2026-07-05T04:27:34Z","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/2205.15540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual explanation is an important Explainable AI technique to explain machine learning predictions. Despite being studied actively, existing optimization-based methods often assume that the underlying machine-learning model is differentiable and treat categorical attributes as continuous ones, which restricts their real-world applications when categorical attributes have many different values or the model is non-differentiable. To make counterfactual explanation suitable for real-world applications, we propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE), whic","authors_text":"Caiming Xiong, Jia Li, Steven C.H. Hoi, Wenzhuo Yang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-31T04:57:06Z","title":"MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15540","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":"sha256:65aacccf52ccf6be63a1667f376a1681b783c2ce7884a65d39e4d83c6d0899db","target":"record","created_at":"2026-07-05T04:27:34Z","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":"8739fd8ba8294de6fa9f60a872c257ff18f8fc4f94cef0ba613f0686382387b8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-31T04:57:06Z","title_canon_sha256":"29ad4607e5db34ad930643e5da6ca3d1e75fad4c21c244dcfdc2421b61ea0e7e"},"schema_version":"1.0","source":{"id":"2205.15540","kind":"arxiv","version":1}},"canonical_sha256":"e666bad98f6a07635ac1b14793119c1ba0264dafc9eb528b1a8d48f048bab08b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e666bad98f6a07635ac1b14793119c1ba0264dafc9eb528b1a8d48f048bab08b","first_computed_at":"2026-07-05T04:27:34.088743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:34.088743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NUe1+NygxxuzXfk5hfnquTHJrD2tMkNXcMeE1aXNwpivPHzK+rU6d8b0XtW4nK/H3rc3PeNDtrEuzDveGOPVBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:34.089250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65aacccf52ccf6be63a1667f376a1681b783c2ce7884a65d39e4d83c6d0899db","sha256:51bfdd110dc7360d78050f37300a739d754732aa939329a42ddd237cdac91230"],"state_sha256":"7ccb9f686de9b8abf407b2711e008fcb50327b58478666e2ca1a9f5bd39537fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XbP6BnIUph7S3eUcdajNTR/2/jz1A4sYn/+RBKff57c7qYwOkZ2xC+ywSJwbRSMKYw8UEbozZNNwna+B1W8pCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T13:12:29.862898Z","bundle_sha256":"018089e4aa6cfacd3dfc56294183c72b4367d451934eb63ff55f90f7d0cdcad4"}}