{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PE6DHQQGCXL54WBTRLPDFUJ4P4","short_pith_number":"pith:PE6DHQQG","canonical_record":{"source":{"id":"2502.13751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-19T14:12:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"75d842c76b3468c5ec184402c46dc91bedccf53e38acb2b2ce018894ead70585","abstract_canon_sha256":"6221549aee379ab7b39ba872f02cf60b07be7cb27cae17e6eb9f8f6b86762536"},"schema_version":"1.0"},"canonical_sha256":"793c33c20615d7de58338ade32d13c7f221e9a52ea18b1959b8bbe77575a8968","source":{"kind":"arxiv","id":"2502.13751","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13751","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13751v1","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13751","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"PE6DHQQGCXL5","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"PE6DHQQGCXL54WBT","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"PE6DHQQG","created_at":"2026-07-05T10:17:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PE6DHQQGCXL54WBTRLPDFUJ4P4","target":"record","payload":{"canonical_record":{"source":{"id":"2502.13751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-19T14:12:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"75d842c76b3468c5ec184402c46dc91bedccf53e38acb2b2ce018894ead70585","abstract_canon_sha256":"6221549aee379ab7b39ba872f02cf60b07be7cb27cae17e6eb9f8f6b86762536"},"schema_version":"1.0"},"canonical_sha256":"793c33c20615d7de58338ade32d13c7f221e9a52ea18b1959b8bbe77575a8968","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:00.194540Z","signature_b64":"lml8B0MCeoKLKu/2HT7kIt3kkmVJtQh2vi7on/HyKL8iPKoKr352FnkyjJdu9gjiILefmuDb2Iez0sEzkQE3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"793c33c20615d7de58338ade32d13c7f221e9a52ea18b1959b8bbe77575a8968","last_reissued_at":"2026-07-05T10:17:00.194004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:00.194004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.13751","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":"2026-07-05T10:17:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wHb3rxlUjlig7wDytiNqAFfw140nthiNbnr/nrVl8yOAobs9GfV8jGD5vTwzTRAuXGWNCL4iUUTJIrU2L6HDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:21:53.147162Z"},"content_sha256":"78b99d100181352f2e74e4b061eb2fb487316bb88eb23d7f6f8581932883b3b8","schema_version":"1.0","event_id":"sha256:78b99d100181352f2e74e4b061eb2fb487316bb88eb23d7f6f8581932883b3b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PE6DHQQGCXL54WBTRLPDFUJ4P4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RobustX: Robust Counterfactual Explanations Made Easy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aaryan Purohit, Francesco Leofante, Junqi Jiang, Luca Marzari","submitted_at":"2025-02-19T14:12:01Z","abstract_excerpt":"The increasing use of Machine Learning (ML) models to aid decision-making in high-stakes industries demands explainability to facilitate trust. Counterfactual Explanations (CEs) are ideally suited for this, as they can offer insights into the predictions of an ML model by illustrating how changes in its input data may lead to different outcomes. However, for CEs to realise their explanatory potential, significant challenges remain in ensuring their robustness under slight changes in the scenario being explained. Despite the widespread recognition of CEs' robustness as a fundamental requirement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13751","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/2502.13751/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":"2026-07-05T10:17:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73p57Os6Tv1hWrqXPUd3WR17/UpxTbHWH7VNX+OufMhXTQe9b8vqZrAa6TSUV2sCxwSkrkRShJsAdQ4bhnp0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:21:53.147670Z"},"content_sha256":"2f8bc4f1d11bf33c888fdd87ce382f21e03954ddef54540353eb28c247ca2e8f","schema_version":"1.0","event_id":"sha256:2f8bc4f1d11bf33c888fdd87ce382f21e03954ddef54540353eb28c247ca2e8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PE6DHQQGCXL54WBTRLPDFUJ4P4/bundle.json","state_url":"https://pith.science/pith/PE6DHQQGCXL54WBTRLPDFUJ4P4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PE6DHQQGCXL54WBTRLPDFUJ4P4/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":"2026-08-08T10:21:53Z","links":{"resolver":"https://pith.science/pith/PE6DHQQGCXL54WBTRLPDFUJ4P4","bundle":"https://pith.science/pith/PE6DHQQGCXL54WBTRLPDFUJ4P4/bundle.json","state":"https://pith.science/pith/PE6DHQQGCXL54WBTRLPDFUJ4P4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PE6DHQQGCXL54WBTRLPDFUJ4P4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PE6DHQQGCXL54WBTRLPDFUJ4P4","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":"6221549aee379ab7b39ba872f02cf60b07be7cb27cae17e6eb9f8f6b86762536","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-19T14:12:01Z","title_canon_sha256":"75d842c76b3468c5ec184402c46dc91bedccf53e38acb2b2ce018894ead70585"},"schema_version":"1.0","source":{"id":"2502.13751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13751","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13751v1","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13751","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"PE6DHQQGCXL5","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"PE6DHQQGCXL54WBT","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"PE6DHQQG","created_at":"2026-07-05T10:17:00Z"}],"graph_snapshots":[{"event_id":"sha256:2f8bc4f1d11bf33c888fdd87ce382f21e03954ddef54540353eb28c247ca2e8f","target":"graph","created_at":"2026-07-05T10:17:00Z","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/2502.13751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing use of Machine Learning (ML) models to aid decision-making in high-stakes industries demands explainability to facilitate trust. Counterfactual Explanations (CEs) are ideally suited for this, as they can offer insights into the predictions of an ML model by illustrating how changes in its input data may lead to different outcomes. However, for CEs to realise their explanatory potential, significant challenges remain in ensuring their robustness under slight changes in the scenario being explained. Despite the widespread recognition of CEs' robustness as a fundamental requirement","authors_text":"Aaryan Purohit, Francesco Leofante, Junqi Jiang, Luca Marzari","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-19T14:12:01Z","title":"RobustX: Robust Counterfactual Explanations Made Easy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13751","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":"sha256:78b99d100181352f2e74e4b061eb2fb487316bb88eb23d7f6f8581932883b3b8","target":"record","created_at":"2026-07-05T10:17:00Z","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":"6221549aee379ab7b39ba872f02cf60b07be7cb27cae17e6eb9f8f6b86762536","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-19T14:12:01Z","title_canon_sha256":"75d842c76b3468c5ec184402c46dc91bedccf53e38acb2b2ce018894ead70585"},"schema_version":"1.0","source":{"id":"2502.13751","kind":"arxiv","version":1}},"canonical_sha256":"793c33c20615d7de58338ade32d13c7f221e9a52ea18b1959b8bbe77575a8968","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"793c33c20615d7de58338ade32d13c7f221e9a52ea18b1959b8bbe77575a8968","first_computed_at":"2026-07-05T10:17:00.194004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:00.194004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lml8B0MCeoKLKu/2HT7kIt3kkmVJtQh2vi7on/HyKL8iPKoKr352FnkyjJdu9gjiILefmuDb2Iez0sEzkQE3BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:00.194540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78b99d100181352f2e74e4b061eb2fb487316bb88eb23d7f6f8581932883b3b8","sha256:2f8bc4f1d11bf33c888fdd87ce382f21e03954ddef54540353eb28c247ca2e8f"],"state_sha256":"47b7cc86fc97473f82d17a0621a6086dfd0cc0516c8297d3925f0ded25b98d51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQNSLOBkXXwMRBfGH4LNX7woELchqIWHZ4uQEK4iEpFQRBfCQzDhHkwrR5C1fAITwu4pyODeE5afWKa/TmKXAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:21:53.152460Z","bundle_sha256":"d3eef73829c53ad935c51765cf8ec62e85bd54bd61652db962baaad6aadf2c48"}}