{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WZNX5HFSZHY3ZRSDIWPAL7HARO","short_pith_number":"pith:WZNX5HFS","schema_version":"1.0","canonical_sha256":"b65b7e9cb2c9f1bcc643459e05fce08b928a908048a04d5b020ad59f844ded9b","source":{"kind":"arxiv","id":"2503.07395","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Noise in Natural Language Processing for Computational Social Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nadav Borenstein","submitted_at":"2025-03-10T14:42:42Z","abstract_excerpt":"Computational Social Science (CSS) is an emerging field driven by the unprecedented availability of human-generated content for researchers. This field, however, presents a unique set of challenges due to the nature of the theories and datasets it explores, including highly subjective tasks and complex, unstructured textual corpora. Among these challenges, one of the less well-studied topics is the pervasive presence of noise. This thesis aims to address this gap in the literature by presenting a series of interconnected case studies that examine different manifestations of noise in CSS. These"},"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":"2503.07395","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T14:42:42Z","cross_cats_sorted":[],"title_canon_sha256":"6baaac0146fc97a0b1651b6fed317191cb401d0c156d584bcc030412ccb1ab34","abstract_canon_sha256":"2213563d0945c5b9a2d74cbf5399b88133592f5abe392f7e28dc3f2c5badc473"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:55.097336Z","signature_b64":"LuDAG1GEuHDTTXU6qcWz9tQ+Iwma3ZoETijr+EkZ8pIaB8MkX9UqYtI1hXOjtLklm/GL39XTMq4+vA3fZYXGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b65b7e9cb2c9f1bcc643459e05fce08b928a908048a04d5b020ad59f844ded9b","last_reissued_at":"2026-07-05T10:27:55.096831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:55.096831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Noise in Natural Language Processing for Computational Social Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nadav Borenstein","submitted_at":"2025-03-10T14:42:42Z","abstract_excerpt":"Computational Social Science (CSS) is an emerging field driven by the unprecedented availability of human-generated content for researchers. This field, however, presents a unique set of challenges due to the nature of the theories and datasets it explores, including highly subjective tasks and complex, unstructured textual corpora. Among these challenges, one of the less well-studied topics is the pervasive presence of noise. This thesis aims to address this gap in the literature by presenting a series of interconnected case studies that examine different manifestations of noise in CSS. These"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07395","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/2503.07395/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":"2503.07395","created_at":"2026-07-05T10:27:55.096897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07395v1","created_at":"2026-07-05T10:27:55.096897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07395","created_at":"2026-07-05T10:27:55.096897+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZNX5HFSZHY3","created_at":"2026-07-05T10:27:55.096897+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZNX5HFSZHY3ZRSD","created_at":"2026-07-05T10:27:55.096897+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZNX5HFS","created_at":"2026-07-05T10:27:55.096897+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/WZNX5HFSZHY3ZRSDIWPAL7HARO","json":"https://pith.science/pith/WZNX5HFSZHY3ZRSDIWPAL7HARO.json","graph_json":"https://pith.science/api/pith-number/WZNX5HFSZHY3ZRSDIWPAL7HARO/graph.json","events_json":"https://pith.science/api/pith-number/WZNX5HFSZHY3ZRSDIWPAL7HARO/events.json","paper":"https://pith.science/paper/WZNX5HFS"},"agent_actions":{"view_html":"https://pith.science/pith/WZNX5HFSZHY3ZRSDIWPAL7HARO","download_json":"https://pith.science/pith/WZNX5HFSZHY3ZRSDIWPAL7HARO.json","view_paper":"https://pith.science/paper/WZNX5HFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07395&json=true","fetch_graph":"https://pith.science/api/pith-number/WZNX5HFSZHY3ZRSDIWPAL7HARO/graph.json","fetch_events":"https://pith.science/api/pith-number/WZNX5HFSZHY3ZRSDIWPAL7HARO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZNX5HFSZHY3ZRSDIWPAL7HARO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZNX5HFSZHY3ZRSDIWPAL7HARO/action/storage_attestation","attest_author":"https://pith.science/pith/WZNX5HFSZHY3ZRSDIWPAL7HARO/action/author_attestation","sign_citation":"https://pith.science/pith/WZNX5HFSZHY3ZRSDIWPAL7HARO/action/citation_signature","submit_replication":"https://pith.science/pith/WZNX5HFSZHY3ZRSDIWPAL7HARO/action/replication_record"}},"created_at":"2026-07-05T10:27:55.096897+00:00","updated_at":"2026-07-05T10:27:55.096897+00:00"}