{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XOWEOWXSG2O7OUJVLGC23OSGIU","short_pith_number":"pith:XOWEOWXS","canonical_record":{"source":{"id":"2105.12941","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-05-27T05:11:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2d3dd364a0e4f17d1b3169176bc03a2c27a3a7c835d76812010092d0be0eba49","abstract_canon_sha256":"1d9ca903baaf4b2fe99830ee07ba2ac1e60c10f5b754e293026caa3def666106"},"schema_version":"1.0"},"canonical_sha256":"bbac475af2369df751355985adba464522eb3f866e6ed2cf7474d5bfcb0d511d","source":{"kind":"arxiv","id":"2105.12941","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.12941","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2105.12941v3","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.12941","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"XOWEOWXSG2O7","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"XOWEOWXSG2O7OUJV","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"XOWEOWXS","created_at":"2026-07-05T04:13:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XOWEOWXSG2O7OUJVLGC23OSGIU","target":"record","payload":{"canonical_record":{"source":{"id":"2105.12941","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-05-27T05:11:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2d3dd364a0e4f17d1b3169176bc03a2c27a3a7c835d76812010092d0be0eba49","abstract_canon_sha256":"1d9ca903baaf4b2fe99830ee07ba2ac1e60c10f5b754e293026caa3def666106"},"schema_version":"1.0"},"canonical_sha256":"bbac475af2369df751355985adba464522eb3f866e6ed2cf7474d5bfcb0d511d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:29.851351Z","signature_b64":"PYO5/xgcyIQ14eV1UHPXB/MhXB58UhdSdOOcxaIXESmSPApFyDtE0ezzLTq2s0Q6G7QD2CcraxR2CulwJNUEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbac475af2369df751355985adba464522eb3f866e6ed2cf7474d5bfcb0d511d","last_reissued_at":"2026-07-05T04:13:29.850895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:29.850895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.12941","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KXxzm7p+0y/hAT2sQQdppsugySAy5xwdlJTzrmfcN1i/DCupPoLucn82c0amSiKwHDUFQoX1xCNhmb+fzYr4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:02:44.023605Z"},"content_sha256":"246413d7f7c3aac306e3db286c730c7b958b334f920261fde23932bb909c07ca","schema_version":"1.0","event_id":"sha256:246413d7f7c3aac306e3db286c730c7b958b334f920261fde23932bb909c07ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XOWEOWXSG2O7OUJVLGC23OSGIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CrystalCandle: A User-Facing Model Explainer for Narrative Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Diana Negoescu, Jilei Yang, Parvez Ahammad","submitted_at":"2021-05-27T05:11:47Z","abstract_excerpt":"Predictive machine learning models often lack interpretability, resulting in low trust from model end users despite having high predictive performance. While many model interpretation approaches return top important features to help interpret model predictions, these top features may not be well-organized or intuitive to end users, which limits model adoption rates. In this paper, we propose CrystalCandle, a user-facing model explainer that creates user-digestible interpretations and insights reflecting the rationale behind model predictions. CrystalCandle builds an end-to-end pipeline from ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.12941","kind":"arxiv","version":3},"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/2105.12941/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":"2026-07-05T04:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"92sjEklPCco9IDmZMq1r1e21dWmTeKysupdK2Y7KhUvfwFdipxdMk9AYQaseT5I+uJfHETnOdPx0HHxGbfcyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:02:44.024207Z"},"content_sha256":"448ed3479120bee106c80c3899fe5220a30fb89df5f275e87cf3bd7c39ce3640","schema_version":"1.0","event_id":"sha256:448ed3479120bee106c80c3899fe5220a30fb89df5f275e87cf3bd7c39ce3640"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XOWEOWXSG2O7OUJVLGC23OSGIU/bundle.json","state_url":"https://pith.science/pith/XOWEOWXSG2O7OUJVLGC23OSGIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XOWEOWXSG2O7OUJVLGC23OSGIU/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":"2026-08-15T14:02:44Z","links":{"resolver":"https://pith.science/pith/XOWEOWXSG2O7OUJVLGC23OSGIU","bundle":"https://pith.science/pith/XOWEOWXSG2O7OUJVLGC23OSGIU/bundle.json","state":"https://pith.science/pith/XOWEOWXSG2O7OUJVLGC23OSGIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XOWEOWXSG2O7OUJVLGC23OSGIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XOWEOWXSG2O7OUJVLGC23OSGIU","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":"1d9ca903baaf4b2fe99830ee07ba2ac1e60c10f5b754e293026caa3def666106","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-05-27T05:11:47Z","title_canon_sha256":"2d3dd364a0e4f17d1b3169176bc03a2c27a3a7c835d76812010092d0be0eba49"},"schema_version":"1.0","source":{"id":"2105.12941","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.12941","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2105.12941v3","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.12941","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"XOWEOWXSG2O7","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"XOWEOWXSG2O7OUJV","created_at":"2026-07-05T04:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"XOWEOWXS","created_at":"2026-07-05T04:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:448ed3479120bee106c80c3899fe5220a30fb89df5f275e87cf3bd7c39ce3640","target":"graph","created_at":"2026-07-05T04:13:29Z","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/2105.12941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Predictive machine learning models often lack interpretability, resulting in low trust from model end users despite having high predictive performance. While many model interpretation approaches return top important features to help interpret model predictions, these top features may not be well-organized or intuitive to end users, which limits model adoption rates. In this paper, we propose CrystalCandle, a user-facing model explainer that creates user-digestible interpretations and insights reflecting the rationale behind model predictions. CrystalCandle builds an end-to-end pipeline from ma","authors_text":"Diana Negoescu, Jilei Yang, Parvez Ahammad","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-05-27T05:11:47Z","title":"CrystalCandle: A User-Facing Model Explainer for Narrative Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.12941","kind":"arxiv","version":3},"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":"sha256:246413d7f7c3aac306e3db286c730c7b958b334f920261fde23932bb909c07ca","target":"record","created_at":"2026-07-05T04:13:29Z","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":"1d9ca903baaf4b2fe99830ee07ba2ac1e60c10f5b754e293026caa3def666106","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-05-27T05:11:47Z","title_canon_sha256":"2d3dd364a0e4f17d1b3169176bc03a2c27a3a7c835d76812010092d0be0eba49"},"schema_version":"1.0","source":{"id":"2105.12941","kind":"arxiv","version":3}},"canonical_sha256":"bbac475af2369df751355985adba464522eb3f866e6ed2cf7474d5bfcb0d511d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbac475af2369df751355985adba464522eb3f866e6ed2cf7474d5bfcb0d511d","first_computed_at":"2026-07-05T04:13:29.850895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:29.850895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PYO5/xgcyIQ14eV1UHPXB/MhXB58UhdSdOOcxaIXESmSPApFyDtE0ezzLTq2s0Q6G7QD2CcraxR2CulwJNUEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:29.851351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.12941","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:246413d7f7c3aac306e3db286c730c7b958b334f920261fde23932bb909c07ca","sha256:448ed3479120bee106c80c3899fe5220a30fb89df5f275e87cf3bd7c39ce3640"],"state_sha256":"0cc4480a911344772046b988a219f305d826d26977a7cfa075c66e3e7d57466d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xvAO0fB91TpqQAr1WvTGZDnXtNl2pohhtxzpoyet5f4L9WQI3BzL9IHYQf5Zt+OKWxeqaNW1CAN2Fdn6kokoAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T14:02:44.028080Z","bundle_sha256":"94493b41f6fe4ca0796ed7060f9d3d26ffafeb198c6a7a0e8c60b6fa16d0575a"}}