{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CVJ3ODNB6V7DMTFUZS7TSPQ7D3","short_pith_number":"pith:CVJ3ODNB","schema_version":"1.0","canonical_sha256":"1553b70da1f57e364cb4ccbf393e1f1edb2e60d2772af3f76afb0fc4053234d9","source":{"kind":"arxiv","id":"2311.09538","version":3},"attestation_state":"computed","paper":{"title":"Reducing Privacy Risks in Online Self-Disclosures with Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Alan Ritter, Anubha Kabra, Isadora Krsek, Sauvik Das, Tarek Naous, Wei Xu, Yao Dou","submitted_at":"2023-11-16T03:28:43Z","abstract_excerpt":"Self-disclosure, while being common and rewarding in social media interaction, also poses privacy risks. In this paper, we take the initiative to protect the user-side privacy associated with online self-disclosure through detection and abstraction. We develop a taxonomy of 19 self-disclosure categories and curate a large corpus consisting of 4.8K annotated disclosure spans. We then fine-tune a language model for detection, achieving over 65% partial span F$_1$. We further conduct an HCI user study, with 82% of participants viewing the model positively, highlighting its real-world applicabilit"},"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":"2311.09538","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T03:28:43Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"d25a8979904876a3b317dc98768344c487214cbb3678dc90f4dca759d9cf4243","abstract_canon_sha256":"7af44f74fe7e17ecd0ca40ca0d0bb6e392865a7c84b0fa2d198aec242afc903f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:39.381847Z","signature_b64":"VoAWN6qTVR159kLhEuGNv+k/6mGbbJ0YIa7/a32vLVmpq+ANsGidpjSq4NvqypCrKJNYaYIt0tz4ylgf6MczCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1553b70da1f57e364cb4ccbf393e1f1edb2e60d2772af3f76afb0fc4053234d9","last_reissued_at":"2026-07-05T08:35:39.381385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:39.381385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reducing Privacy Risks in Online Self-Disclosures with Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Alan Ritter, Anubha Kabra, Isadora Krsek, Sauvik Das, Tarek Naous, Wei Xu, Yao Dou","submitted_at":"2023-11-16T03:28:43Z","abstract_excerpt":"Self-disclosure, while being common and rewarding in social media interaction, also poses privacy risks. In this paper, we take the initiative to protect the user-side privacy associated with online self-disclosure through detection and abstraction. We develop a taxonomy of 19 self-disclosure categories and curate a large corpus consisting of 4.8K annotated disclosure spans. We then fine-tune a language model for detection, achieving over 65% partial span F$_1$. We further conduct an HCI user study, with 82% of participants viewing the model positively, highlighting its real-world applicabilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09538","kind":"arxiv","version":3},"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/2311.09538/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":"2311.09538","created_at":"2026-07-05T08:35:39.381444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09538v3","created_at":"2026-07-05T08:35:39.381444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09538","created_at":"2026-07-05T08:35:39.381444+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVJ3ODNB6V7D","created_at":"2026-07-05T08:35:39.381444+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVJ3ODNB6V7DMTFU","created_at":"2026-07-05T08:35:39.381444+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVJ3ODNB","created_at":"2026-07-05T08:35:39.381444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.17185","citing_title":"A Common Pool of Privacy Problems: Legal and Technical Lessons from a Large-Scale Web-Scraped Machine Learning Dataset","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CVJ3ODNB6V7DMTFUZS7TSPQ7D3","json":"https://pith.science/pith/CVJ3ODNB6V7DMTFUZS7TSPQ7D3.json","graph_json":"https://pith.science/api/pith-number/CVJ3ODNB6V7DMTFUZS7TSPQ7D3/graph.json","events_json":"https://pith.science/api/pith-number/CVJ3ODNB6V7DMTFUZS7TSPQ7D3/events.json","paper":"https://pith.science/paper/CVJ3ODNB"},"agent_actions":{"view_html":"https://pith.science/pith/CVJ3ODNB6V7DMTFUZS7TSPQ7D3","download_json":"https://pith.science/pith/CVJ3ODNB6V7DMTFUZS7TSPQ7D3.json","view_paper":"https://pith.science/paper/CVJ3ODNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09538&json=true","fetch_graph":"https://pith.science/api/pith-number/CVJ3ODNB6V7DMTFUZS7TSPQ7D3/graph.json","fetch_events":"https://pith.science/api/pith-number/CVJ3ODNB6V7DMTFUZS7TSPQ7D3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVJ3ODNB6V7DMTFUZS7TSPQ7D3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVJ3ODNB6V7DMTFUZS7TSPQ7D3/action/storage_attestation","attest_author":"https://pith.science/pith/CVJ3ODNB6V7DMTFUZS7TSPQ7D3/action/author_attestation","sign_citation":"https://pith.science/pith/CVJ3ODNB6V7DMTFUZS7TSPQ7D3/action/citation_signature","submit_replication":"https://pith.science/pith/CVJ3ODNB6V7DMTFUZS7TSPQ7D3/action/replication_record"}},"created_at":"2026-07-05T08:35:39.381444+00:00","updated_at":"2026-07-05T08:35:39.381444+00:00"}