{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MDNYOIIXBDX65VT3YL5IFGPDA6","short_pith_number":"pith:MDNYOIIX","schema_version":"1.0","canonical_sha256":"60db87211708efeed67bc2fa8299e307b4c7f31f26133a980e2a7729db5b4354","source":{"kind":"arxiv","id":"2107.05978","version":1},"attestation_state":"computed","paper":{"title":"DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Adrian Weller, Isabel Chien, Muhammad Bilal Zafar, Umang Bhatt","submitted_at":"2021-07-13T10:50:58Z","abstract_excerpt":"As the complexity of machine learning (ML) models increases, resulting in a lack of prediction explainability, several methods have been developed to explain a model's behavior in terms of the training data points that most influence the model. However, these methods tend to mark outliers as highly influential points, limiting the insights that practitioners can draw from points that are not representative of the training data. In this work, we take a step towards finding influential training points that also represent the training data well. We first review methods for assigning importance sc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2107.05978","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T10:50:58Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"94d1933d330be5aef164d77ab09cced9c64940afffbfd6e5de6b82524942e62b","abstract_canon_sha256":"a6096719c08fe612e72f194dfb52d22394e8bb0f19961de56f54bec71e6197e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:30.030394Z","signature_b64":"InQ51hJ+6EeyaitfjOz0VP4YVoTe4Ak3R8AxyYyDx9aPj29QRwckFDM9di9klnVNkaSW6fKBnvINhrZIIJX5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60db87211708efeed67bc2fa8299e307b4c7f31f26133a980e2a7729db5b4354","last_reissued_at":"2026-07-05T02:57:30.029982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:30.029982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Adrian Weller, Isabel Chien, Muhammad Bilal Zafar, Umang Bhatt","submitted_at":"2021-07-13T10:50:58Z","abstract_excerpt":"As the complexity of machine learning (ML) models increases, resulting in a lack of prediction explainability, several methods have been developed to explain a model's behavior in terms of the training data points that most influence the model. However, these methods tend to mark outliers as highly influential points, limiting the insights that practitioners can draw from points that are not representative of the training data. In this work, we take a step towards finding influential training points that also represent the training data well. We first review methods for assigning importance sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05978","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/2107.05978/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2107.05978","created_at":"2026-07-05T02:57:30.030040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.05978v1","created_at":"2026-07-05T02:57:30.030040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05978","created_at":"2026-07-05T02:57:30.030040+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDNYOIIXBDX6","created_at":"2026-07-05T02:57:30.030040+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDNYOIIXBDX65VT3","created_at":"2026-07-05T02:57:30.030040+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDNYOIIX","created_at":"2026-07-05T02:57:30.030040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDNYOIIXBDX65VT3YL5IFGPDA6","json":"https://pith.science/pith/MDNYOIIXBDX65VT3YL5IFGPDA6.json","graph_json":"https://pith.science/api/pith-number/MDNYOIIXBDX65VT3YL5IFGPDA6/graph.json","events_json":"https://pith.science/api/pith-number/MDNYOIIXBDX65VT3YL5IFGPDA6/events.json","paper":"https://pith.science/paper/MDNYOIIX"},"agent_actions":{"view_html":"https://pith.science/pith/MDNYOIIXBDX65VT3YL5IFGPDA6","download_json":"https://pith.science/pith/MDNYOIIXBDX65VT3YL5IFGPDA6.json","view_paper":"https://pith.science/paper/MDNYOIIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.05978&json=true","fetch_graph":"https://pith.science/api/pith-number/MDNYOIIXBDX65VT3YL5IFGPDA6/graph.json","fetch_events":"https://pith.science/api/pith-number/MDNYOIIXBDX65VT3YL5IFGPDA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDNYOIIXBDX65VT3YL5IFGPDA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDNYOIIXBDX65VT3YL5IFGPDA6/action/storage_attestation","attest_author":"https://pith.science/pith/MDNYOIIXBDX65VT3YL5IFGPDA6/action/author_attestation","sign_citation":"https://pith.science/pith/MDNYOIIXBDX65VT3YL5IFGPDA6/action/citation_signature","submit_replication":"https://pith.science/pith/MDNYOIIXBDX65VT3YL5IFGPDA6/action/replication_record"}},"created_at":"2026-07-05T02:57:30.030040+00:00","updated_at":"2026-07-05T02:57:30.030040+00:00"}