{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H7LU2CIO3FEWA3Q2BNUHM2UL5R","short_pith_number":"pith:H7LU2CIO","schema_version":"1.0","canonical_sha256":"3fd74d090ed949606e1a0b68766a8bec5d56def2529b2cf11a8db38dcdde4da6","source":{"kind":"arxiv","id":"2502.18480","version":1},"attestation_state":"computed","paper":{"title":"QExplorer: Large Language Model Based Query Extraction for Toxic Content Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Dehong Gao, Hui Xue, Li Ke, Longtao Huang, Shaola Ren","submitted_at":"2025-02-06T06:11:58Z","abstract_excerpt":"Automatically extracting effective queries is challenging in information retrieval, especially in toxic content exploration, as such content is likely to be disguised. With the recent achievements in generative Large Language Model (LLM), we are able to leverage the capabilities of LLMs to extract effective queries for similar content exploration directly. This study proposes QExplorer, an approach of large language model based Query Extraction for toxic content Exploration. The QExplorer approach involves a 2-stage training process: instruction Supervised FineTuning (SFT) and preference align"},"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":"2502.18480","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-02-06T06:11:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"904801aaef7b601c1f42ce5bde17c04d700750adaf120e006bea3a2f855bfc8f","abstract_canon_sha256":"8bfbf18b8f0f64af8507cc8176a8e44435e57f19d39f2391bf568608f088d286"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:58.531613Z","signature_b64":"6jUMLWf6IFSuGKFNnimDUkwyGlsmU9/L1EQzHRx7fujDOlDvcawWfqIkos6FuiQUi2j4joAWXwCuwY6uaX6SBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fd74d090ed949606e1a0b68766a8bec5d56def2529b2cf11a8db38dcdde4da6","last_reissued_at":"2026-07-05T10:19:58.530885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:58.530885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QExplorer: Large Language Model Based Query Extraction for Toxic Content Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Dehong Gao, Hui Xue, Li Ke, Longtao Huang, Shaola Ren","submitted_at":"2025-02-06T06:11:58Z","abstract_excerpt":"Automatically extracting effective queries is challenging in information retrieval, especially in toxic content exploration, as such content is likely to be disguised. With the recent achievements in generative Large Language Model (LLM), we are able to leverage the capabilities of LLMs to extract effective queries for similar content exploration directly. This study proposes QExplorer, an approach of large language model based Query Extraction for toxic content Exploration. The QExplorer approach involves a 2-stage training process: instruction Supervised FineTuning (SFT) and preference align"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18480","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/2502.18480/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":"2502.18480","created_at":"2026-07-05T10:19:58.530942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18480v1","created_at":"2026-07-05T10:19:58.530942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18480","created_at":"2026-07-05T10:19:58.530942+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7LU2CIO3FEW","created_at":"2026-07-05T10:19:58.530942+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7LU2CIO3FEWA3Q2","created_at":"2026-07-05T10:19:58.530942+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7LU2CIO","created_at":"2026-07-05T10:19:58.530942+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/H7LU2CIO3FEWA3Q2BNUHM2UL5R","json":"https://pith.science/pith/H7LU2CIO3FEWA3Q2BNUHM2UL5R.json","graph_json":"https://pith.science/api/pith-number/H7LU2CIO3FEWA3Q2BNUHM2UL5R/graph.json","events_json":"https://pith.science/api/pith-number/H7LU2CIO3FEWA3Q2BNUHM2UL5R/events.json","paper":"https://pith.science/paper/H7LU2CIO"},"agent_actions":{"view_html":"https://pith.science/pith/H7LU2CIO3FEWA3Q2BNUHM2UL5R","download_json":"https://pith.science/pith/H7LU2CIO3FEWA3Q2BNUHM2UL5R.json","view_paper":"https://pith.science/paper/H7LU2CIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18480&json=true","fetch_graph":"https://pith.science/api/pith-number/H7LU2CIO3FEWA3Q2BNUHM2UL5R/graph.json","fetch_events":"https://pith.science/api/pith-number/H7LU2CIO3FEWA3Q2BNUHM2UL5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7LU2CIO3FEWA3Q2BNUHM2UL5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7LU2CIO3FEWA3Q2BNUHM2UL5R/action/storage_attestation","attest_author":"https://pith.science/pith/H7LU2CIO3FEWA3Q2BNUHM2UL5R/action/author_attestation","sign_citation":"https://pith.science/pith/H7LU2CIO3FEWA3Q2BNUHM2UL5R/action/citation_signature","submit_replication":"https://pith.science/pith/H7LU2CIO3FEWA3Q2BNUHM2UL5R/action/replication_record"}},"created_at":"2026-07-05T10:19:58.530942+00:00","updated_at":"2026-07-05T10:19:58.530942+00:00"}