{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QZFQOWZBHP5MSRIV6OLWDKOOEE","short_pith_number":"pith:QZFQOWZB","schema_version":"1.0","canonical_sha256":"864b075b213bfac94515f39761a9ce2101c55ec06126f1668bb7a92b5a3a0560","source":{"kind":"arxiv","id":"2009.10795","version":2},"attestation_state":"computed","paper":{"title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Nicholas Lourie, Noah A. Smith, Roy Schwartz, Swabha Swayamdipta, Yejin Choi, Yizhong Wang","submitted_at":"2020-09-22T20:19:41Z","abstract_excerpt":"Large datasets have become commonplace in NLP research. However, the increased emphasis on data quantity has made it challenging to assess the quality of data. We introduce Data Maps---a model-based tool to characterize and diagnose datasets. We leverage a largely ignored source of information: the behavior of the model on individual instances during training (training dynamics) for building data maps. This yields two intuitive measures for each example---the model's confidence in the true class, and the variability of this confidence across epochs---obtained in a single run of training. Exper"},"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":"2009.10795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T20:19:41Z","cross_cats_sorted":[],"title_canon_sha256":"e68e6274e4ba7d94f7f9bdcecb774b22a0cbc3e003eaed822ecbf771c289a575","abstract_canon_sha256":"089ca30425564fb209a4e5241a7b6494dd5104f3a4a1496ce1ac46c7bc120748"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:16.356853Z","signature_b64":"qL2/1MT/pQc31NI05mv63pZf9DySZpVpYop6ALlH1QVK9hPROyAnxaq5kORCKVJBPGzAqbjR4HvdY0Ylp6qSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"864b075b213bfac94515f39761a9ce2101c55ec06126f1668bb7a92b5a3a0560","last_reissued_at":"2026-07-05T01:43:16.356448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:16.356448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Nicholas Lourie, Noah A. Smith, Roy Schwartz, Swabha Swayamdipta, Yejin Choi, Yizhong Wang","submitted_at":"2020-09-22T20:19:41Z","abstract_excerpt":"Large datasets have become commonplace in NLP research. However, the increased emphasis on data quantity has made it challenging to assess the quality of data. We introduce Data Maps---a model-based tool to characterize and diagnose datasets. We leverage a largely ignored source of information: the behavior of the model on individual instances during training (training dynamics) for building data maps. This yields two intuitive measures for each example---the model's confidence in the true class, and the variability of this confidence across epochs---obtained in a single run of training. Exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10795","kind":"arxiv","version":2},"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/2009.10795/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":"2009.10795","created_at":"2026-07-05T01:43:16.356518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.10795v2","created_at":"2026-07-05T01:43:16.356518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10795","created_at":"2026-07-05T01:43:16.356518+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZFQOWZBHP5M","created_at":"2026-07-05T01:43:16.356518+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZFQOWZBHP5MSRIV","created_at":"2026-07-05T01:43:16.356518+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZFQOWZB","created_at":"2026-07-05T01:43:16.356518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29720","citing_title":"Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2508.04149","citing_title":"Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02351","citing_title":"Ordinal Adaptive Correction: A Data-Centric Approach to Ordinal Image Classification with Noisy Labels","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20786","citing_title":"LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.24176","citing_title":"Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions","ref_index":287,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09404","citing_title":"Let the Target Select for Itself: Data Selection via Target-Aligned Paths","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20720","citing_title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08977","citing_title":"Testing the Assumptions of Active Learning for Translation Tasks with Few Samples","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZFQOWZBHP5MSRIV6OLWDKOOEE","json":"https://pith.science/pith/QZFQOWZBHP5MSRIV6OLWDKOOEE.json","graph_json":"https://pith.science/api/pith-number/QZFQOWZBHP5MSRIV6OLWDKOOEE/graph.json","events_json":"https://pith.science/api/pith-number/QZFQOWZBHP5MSRIV6OLWDKOOEE/events.json","paper":"https://pith.science/paper/QZFQOWZB"},"agent_actions":{"view_html":"https://pith.science/pith/QZFQOWZBHP5MSRIV6OLWDKOOEE","download_json":"https://pith.science/pith/QZFQOWZBHP5MSRIV6OLWDKOOEE.json","view_paper":"https://pith.science/paper/QZFQOWZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.10795&json=true","fetch_graph":"https://pith.science/api/pith-number/QZFQOWZBHP5MSRIV6OLWDKOOEE/graph.json","fetch_events":"https://pith.science/api/pith-number/QZFQOWZBHP5MSRIV6OLWDKOOEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZFQOWZBHP5MSRIV6OLWDKOOEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZFQOWZBHP5MSRIV6OLWDKOOEE/action/storage_attestation","attest_author":"https://pith.science/pith/QZFQOWZBHP5MSRIV6OLWDKOOEE/action/author_attestation","sign_citation":"https://pith.science/pith/QZFQOWZBHP5MSRIV6OLWDKOOEE/action/citation_signature","submit_replication":"https://pith.science/pith/QZFQOWZBHP5MSRIV6OLWDKOOEE/action/replication_record"}},"created_at":"2026-07-05T01:43:16.356518+00:00","updated_at":"2026-07-05T01:43:16.356518+00:00"}