{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PPDZ3QJCYLPQ5BQZBYOVIBVYEM","short_pith_number":"pith:PPDZ3QJC","schema_version":"1.0","canonical_sha256":"7bc79dc122c2df0e86190e1d5406b8233f6b60329151764cc9a53d226dda794e","source":{"kind":"arxiv","id":"2409.03247","version":2},"attestation_state":"computed","paper":{"title":"End User Authoring of Personalized Content Classifiers: Comparing Example Labeling, Rule Writing, and LLM Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Amy X. Zhang, Kathryn Yurechko, Leijie Wang, Pranati Dani, Quan Ze Chen","submitted_at":"2024-09-05T04:51:18Z","abstract_excerpt":"Existing tools for laypeople to create personal classifiers often assume a motivated user working uninterrupted in a single, lengthy session. However, users tend to engage with social media casually, with many short sessions on an ongoing, daily basis. To make creating personal classifiers for content curation easier for such users, tools should support rapid initialization and iterative refinement. In this work, we compare three strategies -- (1) example labeling, (2) rule writing, and (3) large language model (LLM) prompting -- for end users to build personal content classifiers. From an exp"},"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":"2409.03247","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-09-05T04:51:18Z","cross_cats_sorted":[],"title_canon_sha256":"408601f7f37fbaf62fb96a782dd57c23dceb23c3abc2fabbc05e03ef35b97e80","abstract_canon_sha256":"18851249198f4b4edc07f9a1f7559a01a5afa22a94378d34605a9bc7fe13c3e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:04.829453Z","signature_b64":"G4K15yLSItY3Oc94NOWZyIp1HW02TrWL2r84nhQCUL42tE4yp7Jh5KTTOdFeJyVNCe5vypqlZ0Yj416VbIlaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bc79dc122c2df0e86190e1d5406b8233f6b60329151764cc9a53d226dda794e","last_reissued_at":"2026-07-05T11:20:04.828967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:04.828967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End User Authoring of Personalized Content Classifiers: Comparing Example Labeling, Rule Writing, and LLM Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Amy X. Zhang, Kathryn Yurechko, Leijie Wang, Pranati Dani, Quan Ze Chen","submitted_at":"2024-09-05T04:51:18Z","abstract_excerpt":"Existing tools for laypeople to create personal classifiers often assume a motivated user working uninterrupted in a single, lengthy session. However, users tend to engage with social media casually, with many short sessions on an ongoing, daily basis. To make creating personal classifiers for content curation easier for such users, tools should support rapid initialization and iterative refinement. In this work, we compare three strategies -- (1) example labeling, (2) rule writing, and (3) large language model (LLM) prompting -- for end users to build personal content classifiers. From an exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03247","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/2409.03247/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":"2409.03247","created_at":"2026-07-05T11:20:04.829028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03247v2","created_at":"2026-07-05T11:20:04.829028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03247","created_at":"2026-07-05T11:20:04.829028+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPDZ3QJCYLPQ","created_at":"2026-07-05T11:20:04.829028+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPDZ3QJCYLPQ5BQZ","created_at":"2026-07-05T11:20:04.829028+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPDZ3QJC","created_at":"2026-07-05T11:20:04.829028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09099","citing_title":"Drama Llama: An LLM-Powered Storylets Framework for Authorable Responsiveness in Interactive Narrative","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPDZ3QJCYLPQ5BQZBYOVIBVYEM","json":"https://pith.science/pith/PPDZ3QJCYLPQ5BQZBYOVIBVYEM.json","graph_json":"https://pith.science/api/pith-number/PPDZ3QJCYLPQ5BQZBYOVIBVYEM/graph.json","events_json":"https://pith.science/api/pith-number/PPDZ3QJCYLPQ5BQZBYOVIBVYEM/events.json","paper":"https://pith.science/paper/PPDZ3QJC"},"agent_actions":{"view_html":"https://pith.science/pith/PPDZ3QJCYLPQ5BQZBYOVIBVYEM","download_json":"https://pith.science/pith/PPDZ3QJCYLPQ5BQZBYOVIBVYEM.json","view_paper":"https://pith.science/paper/PPDZ3QJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03247&json=true","fetch_graph":"https://pith.science/api/pith-number/PPDZ3QJCYLPQ5BQZBYOVIBVYEM/graph.json","fetch_events":"https://pith.science/api/pith-number/PPDZ3QJCYLPQ5BQZBYOVIBVYEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPDZ3QJCYLPQ5BQZBYOVIBVYEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPDZ3QJCYLPQ5BQZBYOVIBVYEM/action/storage_attestation","attest_author":"https://pith.science/pith/PPDZ3QJCYLPQ5BQZBYOVIBVYEM/action/author_attestation","sign_citation":"https://pith.science/pith/PPDZ3QJCYLPQ5BQZBYOVIBVYEM/action/citation_signature","submit_replication":"https://pith.science/pith/PPDZ3QJCYLPQ5BQZBYOVIBVYEM/action/replication_record"}},"created_at":"2026-07-05T11:20:04.829028+00:00","updated_at":"2026-07-05T11:20:04.829028+00:00"}