{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QZFQOWZBHP5MSRIV6OLWDKOOEE","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":"089ca30425564fb209a4e5241a7b6494dd5104f3a4a1496ce1ac46c7bc120748","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T20:19:41Z","title_canon_sha256":"e68e6274e4ba7d94f7f9bdcecb774b22a0cbc3e003eaed822ecbf771c289a575"},"schema_version":"1.0","source":{"id":"2009.10795","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10795","created_at":"2026-07-05T01:43:16Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10795v2","created_at":"2026-07-05T01:43:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10795","created_at":"2026-07-05T01:43:16Z"},{"alias_kind":"pith_short_12","alias_value":"QZFQOWZBHP5M","created_at":"2026-07-05T01:43:16Z"},{"alias_kind":"pith_short_16","alias_value":"QZFQOWZBHP5MSRIV","created_at":"2026-07-05T01:43:16Z"},{"alias_kind":"pith_short_8","alias_value":"QZFQOWZB","created_at":"2026-07-05T01:43:16Z"}],"graph_snapshots":[{"event_id":"sha256:66778004a1e82a1193a1d7b7d4f6858654a5f90f56d203fa813456ae82df7d83","target":"graph","created_at":"2026-07-05T01:43:16Z","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/2009.10795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hannaneh Hajishirzi, Nicholas Lourie, Noah A. Smith, Roy Schwartz, Swabha Swayamdipta, Yejin Choi, Yizhong Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T20:19:41Z","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10795","kind":"arxiv","version":2},"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:fa495c75027fea3e55999f15230c4ae22afb73e9bcfbf20b43054f76b164889a","target":"record","created_at":"2026-07-05T01:43:16Z","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":"089ca30425564fb209a4e5241a7b6494dd5104f3a4a1496ce1ac46c7bc120748","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T20:19:41Z","title_canon_sha256":"e68e6274e4ba7d94f7f9bdcecb774b22a0cbc3e003eaed822ecbf771c289a575"},"schema_version":"1.0","source":{"id":"2009.10795","kind":"arxiv","version":2}},"canonical_sha256":"864b075b213bfac94515f39761a9ce2101c55ec06126f1668bb7a92b5a3a0560","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"864b075b213bfac94515f39761a9ce2101c55ec06126f1668bb7a92b5a3a0560","first_computed_at":"2026-07-05T01:43:16.356448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:16.356448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qL2/1MT/pQc31NI05mv63pZf9DySZpVpYop6ALlH1QVK9hPROyAnxaq5kORCKVJBPGzAqbjR4HvdY0Ylp6qSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:16.356853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.10795","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa495c75027fea3e55999f15230c4ae22afb73e9bcfbf20b43054f76b164889a","sha256:66778004a1e82a1193a1d7b7d4f6858654a5f90f56d203fa813456ae82df7d83"],"state_sha256":"d7a92d52f6005fb1d19e04617ff88094c7f512b4482747bacf3e1717e0223764"}