{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J6WIKYI4Y3EFSRFMMPIVKCT742","short_pith_number":"pith:J6WIKYI4","schema_version":"1.0","canonical_sha256":"4fac85611cc6c85944ac63d1550a7fe69734466d6972a3eb99eaa1eb5c872410","source":{"kind":"arxiv","id":"2302.13959","version":2},"attestation_state":"computed","paper":{"title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Artem Sokolov, Irina Bejan, Katja Filippova","submitted_at":"2023-02-27T17:00:06Z","abstract_excerpt":"Increasingly larger datasets have become a standard ingredient to advancing the state-of-the-art in NLP. However, data quality might have already become the bottleneck to unlock further gains. Given the diversity and the sizes of modern datasets, standard data filtering is not straight-forward to apply, because of the multifacetedness of the harmful data and elusiveness of filtering rules that would generalize across multiple tasks. We study the fitness of task-agnostic self-influence scores of training examples for data cleaning, analyze their efficacy in capturing naturally occurring outlier"},"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":"2302.13959","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-27T17:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"18f9661ac1ab7d57b2d66271c1c25b4f4282f8a0449c1b0b76a21ffdaaf5a028","abstract_canon_sha256":"0eeee88e0d850ebaa046d9adb1f4985a7ae91ee961fc03dbcfa8bfc207202e43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:39.595947Z","signature_b64":"xH960upNhf6gP4Suao5liDpwr5pBv76w67RL/j3kyg7o+whT8pN5Cbqvj9fA7DgeM2R7JjwlhnuR0k4mUxieCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fac85611cc6c85944ac63d1550a7fe69734466d6972a3eb99eaa1eb5c872410","last_reissued_at":"2026-07-05T07:01:39.595448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:39.595448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Artem Sokolov, Irina Bejan, Katja Filippova","submitted_at":"2023-02-27T17:00:06Z","abstract_excerpt":"Increasingly larger datasets have become a standard ingredient to advancing the state-of-the-art in NLP. However, data quality might have already become the bottleneck to unlock further gains. Given the diversity and the sizes of modern datasets, standard data filtering is not straight-forward to apply, because of the multifacetedness of the harmful data and elusiveness of filtering rules that would generalize across multiple tasks. We study the fitness of task-agnostic self-influence scores of training examples for data cleaning, analyze their efficacy in capturing naturally occurring outlier"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13959","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/2302.13959/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":"2302.13959","created_at":"2026-07-05T07:01:39.595508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13959v2","created_at":"2026-07-05T07:01:39.595508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13959","created_at":"2026-07-05T07:01:39.595508+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6WIKYI4Y3EF","created_at":"2026-07-05T07:01:39.595508+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6WIKYI4Y3EFSRFM","created_at":"2026-07-05T07:01:39.595508+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6WIKYI4","created_at":"2026-07-05T07:01:39.595508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19361","citing_title":"Dynamic Skill Adaptation for Large Language Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6WIKYI4Y3EFSRFMMPIVKCT742","json":"https://pith.science/pith/J6WIKYI4Y3EFSRFMMPIVKCT742.json","graph_json":"https://pith.science/api/pith-number/J6WIKYI4Y3EFSRFMMPIVKCT742/graph.json","events_json":"https://pith.science/api/pith-number/J6WIKYI4Y3EFSRFMMPIVKCT742/events.json","paper":"https://pith.science/paper/J6WIKYI4"},"agent_actions":{"view_html":"https://pith.science/pith/J6WIKYI4Y3EFSRFMMPIVKCT742","download_json":"https://pith.science/pith/J6WIKYI4Y3EFSRFMMPIVKCT742.json","view_paper":"https://pith.science/paper/J6WIKYI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13959&json=true","fetch_graph":"https://pith.science/api/pith-number/J6WIKYI4Y3EFSRFMMPIVKCT742/graph.json","fetch_events":"https://pith.science/api/pith-number/J6WIKYI4Y3EFSRFMMPIVKCT742/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6WIKYI4Y3EFSRFMMPIVKCT742/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6WIKYI4Y3EFSRFMMPIVKCT742/action/storage_attestation","attest_author":"https://pith.science/pith/J6WIKYI4Y3EFSRFMMPIVKCT742/action/author_attestation","sign_citation":"https://pith.science/pith/J6WIKYI4Y3EFSRFMMPIVKCT742/action/citation_signature","submit_replication":"https://pith.science/pith/J6WIKYI4Y3EFSRFMMPIVKCT742/action/replication_record"}},"created_at":"2026-07-05T07:01:39.595508+00:00","updated_at":"2026-07-05T07:01:39.595508+00:00"}