{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KTPI5SLZDUZ6Y5GGSI5GAMYN5L","short_pith_number":"pith:KTPI5SLZ","schema_version":"1.0","canonical_sha256":"54de8ec9791d33ec74c6923a60330deaffa629d8123a26681076b6a9f787bcc1","source":{"kind":"arxiv","id":"2605.25814","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoran Zheng, Hongtao Wang, Renchi Yang, Xiangyu Ke","submitted_at":"2026-05-25T13:11:33Z","abstract_excerpt":"Dirty entity resolution (ER), which identifies records referring to the same real-world entity from a single, messy dataset, is a fundamental task in data management and mining. However, the dominant blocking-matching-clustering paradigm for ER suffers from critical flaws. Its cascaded, decoupled workflow essentially produces a static, sparse graph plagued by missing edges (due to blocking failures) and noisy links (due to matching errors), causing error propagation and yielding suboptimal clusters, particularly when rigid transitivity is imposed in the clustering. We contend that matching and"},"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":"2605.25814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T13:11:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8be95a1e1b8078bc36c793f95d971572c9e05e1e4d9fd4d51c330a9c8a58c24d","abstract_canon_sha256":"6bb05b1252efda6eaad67a37b1ee7667ec083928ed79b20f16f5f52eda12e067"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:12.981584Z","signature_b64":"v9qoVap6YHjMsOh2Kp0Y6gpJ4+zH1jkvx5R3WpD91iV1n40W+jjjabiDbApoML5SZ7E9RZcmZ27FZ06mHxjKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54de8ec9791d33ec74c6923a60330deaffa629d8123a26681076b6a9f787bcc1","last_reissued_at":"2026-05-26T02:05:12.980764Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:12.980764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoran Zheng, Hongtao Wang, Renchi Yang, Xiangyu Ke","submitted_at":"2026-05-25T13:11:33Z","abstract_excerpt":"Dirty entity resolution (ER), which identifies records referring to the same real-world entity from a single, messy dataset, is a fundamental task in data management and mining. However, the dominant blocking-matching-clustering paradigm for ER suffers from critical flaws. Its cascaded, decoupled workflow essentially produces a static, sparse graph plagued by missing edges (due to blocking failures) and noisy links (due to matching errors), causing error propagation and yielding suboptimal clusters, particularly when rigid transitivity is imposed in the clustering. We contend that matching and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25814","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/2605.25814/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":"2605.25814","created_at":"2026-05-26T02:05:12.980904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25814v1","created_at":"2026-05-26T02:05:12.980904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25814","created_at":"2026-05-26T02:05:12.980904+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTPI5SLZDUZ6","created_at":"2026-05-26T02:05:12.980904+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTPI5SLZDUZ6Y5GG","created_at":"2026-05-26T02:05:12.980904+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTPI5SLZ","created_at":"2026-05-26T02:05:12.980904+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/KTPI5SLZDUZ6Y5GGSI5GAMYN5L","json":"https://pith.science/pith/KTPI5SLZDUZ6Y5GGSI5GAMYN5L.json","graph_json":"https://pith.science/api/pith-number/KTPI5SLZDUZ6Y5GGSI5GAMYN5L/graph.json","events_json":"https://pith.science/api/pith-number/KTPI5SLZDUZ6Y5GGSI5GAMYN5L/events.json","paper":"https://pith.science/paper/KTPI5SLZ"},"agent_actions":{"view_html":"https://pith.science/pith/KTPI5SLZDUZ6Y5GGSI5GAMYN5L","download_json":"https://pith.science/pith/KTPI5SLZDUZ6Y5GGSI5GAMYN5L.json","view_paper":"https://pith.science/paper/KTPI5SLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25814&json=true","fetch_graph":"https://pith.science/api/pith-number/KTPI5SLZDUZ6Y5GGSI5GAMYN5L/graph.json","fetch_events":"https://pith.science/api/pith-number/KTPI5SLZDUZ6Y5GGSI5GAMYN5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTPI5SLZDUZ6Y5GGSI5GAMYN5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTPI5SLZDUZ6Y5GGSI5GAMYN5L/action/storage_attestation","attest_author":"https://pith.science/pith/KTPI5SLZDUZ6Y5GGSI5GAMYN5L/action/author_attestation","sign_citation":"https://pith.science/pith/KTPI5SLZDUZ6Y5GGSI5GAMYN5L/action/citation_signature","submit_replication":"https://pith.science/pith/KTPI5SLZDUZ6Y5GGSI5GAMYN5L/action/replication_record"}},"created_at":"2026-05-26T02:05:12.980904+00:00","updated_at":"2026-05-26T02:05:12.980904+00:00"}