{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QDB2WISAVOMLCDPMBNCCNDICED","short_pith_number":"pith:QDB2WISA","canonical_record":{"source":{"id":"2110.03109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T23:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"c387ae71163c96553ac1dd2d55f4f6db077c39dd91788eb84ab3cdcef9ba1832","abstract_canon_sha256":"0e1c1ef3254ee3b3dd6957e2e82061781ff08208cb2802b4eed7ed177696e408"},"schema_version":"1.0"},"canonical_sha256":"80c3ab2240ab98b10dec0b44268d0220ef7dcf9c3d74d361f62f6a0fac79275f","source":{"kind":"arxiv","id":"2110.03109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03109","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03109v1","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03109","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"QDB2WISAVOML","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_16","alias_value":"QDB2WISAVOMLCDPM","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_8","alias_value":"QDB2WISA","created_at":"2026-07-05T03:20:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QDB2WISAVOMLCDPMBNCCNDICED","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T23:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"c387ae71163c96553ac1dd2d55f4f6db077c39dd91788eb84ab3cdcef9ba1832","abstract_canon_sha256":"0e1c1ef3254ee3b3dd6957e2e82061781ff08208cb2802b4eed7ed177696e408"},"schema_version":"1.0"},"canonical_sha256":"80c3ab2240ab98b10dec0b44268d0220ef7dcf9c3d74d361f62f6a0fac79275f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:39.621972Z","signature_b64":"ih01c35MIz07Ek/kCPvMJWXk7FtixnI+EN9V9mXL+SSi5QiDUoTd2nCOak7drhUKjk/t+xnoyxwp+bp2bdjpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80c3ab2240ab98b10dec0b44268d0220ef7dcf9c3d74d361f62f6a0fac79275f","last_reissued_at":"2026-07-05T03:20:39.621557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:39.621557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03109","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":"2026-07-05T03:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oPtonlNOwn9fkUzTDk/V5lxP1lLu0IiRH9pI71KahwAEi92dEU6KnD0cG1TvB40j4ujBVand40gqKhtD/ycBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:58:06.066253Z"},"content_sha256":"15f9724fe68cf25a376bd2522a2e32b03705c29289a007789771fc72006b87af","schema_version":"1.0","event_id":"sha256:15f9724fe68cf25a376bd2522a2e32b03705c29289a007789771fc72006b87af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QDB2WISAVOMLCDPMBNCCNDICED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Consistent Counterfactuals for Deep Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anupam Datta, Emily Black, Matt Fredrikson, Zifan Wang","submitted_at":"2021-10-06T23:48:55Z","abstract_excerpt":"Counterfactual examples are one of the most commonly-cited methods for explaining the predictions of machine learning models in key areas such as finance and medical diagnosis. Counterfactuals are often discussed under the assumption that the model on which they will be used is static, but in deployment models may be periodically retrained or fine-tuned. This paper studies the consistency of model prediction on counterfactual examples in deep networks under small changes to initial training conditions, such as weight initialization and leave-one-out variations in data, as often occurs during m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03109","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/2110.03109/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":"2026-07-05T03:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S9FlIMNpO+Gr1fs1VBgTJ+qbOZltXNIsCKpT1JzL/YKs1tw8sB0BvRM1xa+S0mPvpx9sj5SE6Zeuhrg8Q2LrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:58:06.066738Z"},"content_sha256":"814e651d2c15e223c9b280538bb190f708d5d8563bb1f0ee407f665285c4cd58","schema_version":"1.0","event_id":"sha256:814e651d2c15e223c9b280538bb190f708d5d8563bb1f0ee407f665285c4cd58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDB2WISAVOMLCDPMBNCCNDICED/bundle.json","state_url":"https://pith.science/pith/QDB2WISAVOMLCDPMBNCCNDICED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDB2WISAVOMLCDPMBNCCNDICED/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":"2026-08-06T23:58:06Z","links":{"resolver":"https://pith.science/pith/QDB2WISAVOMLCDPMBNCCNDICED","bundle":"https://pith.science/pith/QDB2WISAVOMLCDPMBNCCNDICED/bundle.json","state":"https://pith.science/pith/QDB2WISAVOMLCDPMBNCCNDICED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDB2WISAVOMLCDPMBNCCNDICED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QDB2WISAVOMLCDPMBNCCNDICED","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":"0e1c1ef3254ee3b3dd6957e2e82061781ff08208cb2802b4eed7ed177696e408","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T23:48:55Z","title_canon_sha256":"c387ae71163c96553ac1dd2d55f4f6db077c39dd91788eb84ab3cdcef9ba1832"},"schema_version":"1.0","source":{"id":"2110.03109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03109","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03109v1","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03109","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"QDB2WISAVOML","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_16","alias_value":"QDB2WISAVOMLCDPM","created_at":"2026-07-05T03:20:39Z"},{"alias_kind":"pith_short_8","alias_value":"QDB2WISA","created_at":"2026-07-05T03:20:39Z"}],"graph_snapshots":[{"event_id":"sha256:814e651d2c15e223c9b280538bb190f708d5d8563bb1f0ee407f665285c4cd58","target":"graph","created_at":"2026-07-05T03:20:39Z","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/2110.03109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual examples are one of the most commonly-cited methods for explaining the predictions of machine learning models in key areas such as finance and medical diagnosis. Counterfactuals are often discussed under the assumption that the model on which they will be used is static, but in deployment models may be periodically retrained or fine-tuned. This paper studies the consistency of model prediction on counterfactual examples in deep networks under small changes to initial training conditions, such as weight initialization and leave-one-out variations in data, as often occurs during m","authors_text":"Anupam Datta, Emily Black, Matt Fredrikson, Zifan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T23:48:55Z","title":"Consistent Counterfactuals for Deep Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03109","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":"sha256:15f9724fe68cf25a376bd2522a2e32b03705c29289a007789771fc72006b87af","target":"record","created_at":"2026-07-05T03:20:39Z","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":"0e1c1ef3254ee3b3dd6957e2e82061781ff08208cb2802b4eed7ed177696e408","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T23:48:55Z","title_canon_sha256":"c387ae71163c96553ac1dd2d55f4f6db077c39dd91788eb84ab3cdcef9ba1832"},"schema_version":"1.0","source":{"id":"2110.03109","kind":"arxiv","version":1}},"canonical_sha256":"80c3ab2240ab98b10dec0b44268d0220ef7dcf9c3d74d361f62f6a0fac79275f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80c3ab2240ab98b10dec0b44268d0220ef7dcf9c3d74d361f62f6a0fac79275f","first_computed_at":"2026-07-05T03:20:39.621557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:39.621557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ih01c35MIz07Ek/kCPvMJWXk7FtixnI+EN9V9mXL+SSi5QiDUoTd2nCOak7drhUKjk/t+xnoyxwp+bp2bdjpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:39.621972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15f9724fe68cf25a376bd2522a2e32b03705c29289a007789771fc72006b87af","sha256:814e651d2c15e223c9b280538bb190f708d5d8563bb1f0ee407f665285c4cd58"],"state_sha256":"f0d5724f3d6a9a297413616694f7b88a3a1e08199862a0aa54e28e63f4901075"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZLvfbiQqzXQ2niw67yXfyLGZZ6Fo2kOY+KPd2fbxvXO8DPt/iYbDDWkn1m/QKuP9vYdm4CCRlHSDS1Ep4rGvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T23:58:06.070341Z","bundle_sha256":"a761f3565652acf48053aca7e57385151340e46df66121e1d66e3d0a0e111d7b"}}