{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T66XBGRLMYLWVSSVDBXXXUZKTV","short_pith_number":"pith:T66XBGRL","schema_version":"1.0","canonical_sha256":"9fbd709a2b66176aca55186f7bd32a9d53cae885f38c995899e0b5499cd5ebde","source":{"kind":"arxiv","id":"2505.17125","version":1},"attestation_state":"computed","paper":{"title":"NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Namhee Kim, Soyeon Kim, Yeonwoo Jeong","submitted_at":"2025-05-21T21:03:37Z","abstract_excerpt":"Effective evaluation of web data record extraction methods is crucial, yet hampered by static, domain-specific benchmarks and opaque scoring practices. This makes fair comparison between traditional algorithmic techniques, which rely on structural heuristics, and Large Language Model (LLM)-based approaches, offering zero-shot extraction across diverse layouts, particularly challenging. To overcome these limitations, we introduce a concrete evaluation framework. Our framework systematically generates evaluation datasets from arbitrary MHTML snapshots, annotates XPath-based supervision labels, a"},"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":"2505.17125","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-21T21:03:37Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"3e14e0b7643d3305d9b8b0cd41f9f9f91e7cf79acc5a55386a91054fc5ed85e0","abstract_canon_sha256":"9128eee295bc8399b938571551e7560566ee731e23b32e3e962d300889cea680"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:47.483018Z","signature_b64":"hVGK+durRWHHoNhnfLY1EpH/Uh8z33c9Bbpvite+Gk6EU4mm+ei+uVlnDe2mcw0TbPftKmX1GWxkKNksVVmRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fbd709a2b66176aca55186f7bd32a9d53cae885f38c995899e0b5499cd5ebde","last_reissued_at":"2026-07-05T11:07:47.482515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:47.482515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Namhee Kim, Soyeon Kim, Yeonwoo Jeong","submitted_at":"2025-05-21T21:03:37Z","abstract_excerpt":"Effective evaluation of web data record extraction methods is crucial, yet hampered by static, domain-specific benchmarks and opaque scoring practices. This makes fair comparison between traditional algorithmic techniques, which rely on structural heuristics, and Large Language Model (LLM)-based approaches, offering zero-shot extraction across diverse layouts, particularly challenging. To overcome these limitations, we introduce a concrete evaluation framework. Our framework systematically generates evaluation datasets from arbitrary MHTML snapshots, annotates XPath-based supervision labels, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17125","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/2505.17125/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":"2505.17125","created_at":"2026-07-05T11:07:47.482584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17125v1","created_at":"2026-07-05T11:07:47.482584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17125","created_at":"2026-07-05T11:07:47.482584+00:00"},{"alias_kind":"pith_short_12","alias_value":"T66XBGRLMYLW","created_at":"2026-07-05T11:07:47.482584+00:00"},{"alias_kind":"pith_short_16","alias_value":"T66XBGRLMYLWVSSV","created_at":"2026-07-05T11:07:47.482584+00:00"},{"alias_kind":"pith_short_8","alias_value":"T66XBGRL","created_at":"2026-07-05T11:07:47.482584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.14447","citing_title":"Do Generative AI Assistants Respect robots.txt? Tracing Web Access Beyond Visible Answers","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T66XBGRLMYLWVSSVDBXXXUZKTV","json":"https://pith.science/pith/T66XBGRLMYLWVSSVDBXXXUZKTV.json","graph_json":"https://pith.science/api/pith-number/T66XBGRLMYLWVSSVDBXXXUZKTV/graph.json","events_json":"https://pith.science/api/pith-number/T66XBGRLMYLWVSSVDBXXXUZKTV/events.json","paper":"https://pith.science/paper/T66XBGRL"},"agent_actions":{"view_html":"https://pith.science/pith/T66XBGRLMYLWVSSVDBXXXUZKTV","download_json":"https://pith.science/pith/T66XBGRLMYLWVSSVDBXXXUZKTV.json","view_paper":"https://pith.science/paper/T66XBGRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17125&json=true","fetch_graph":"https://pith.science/api/pith-number/T66XBGRLMYLWVSSVDBXXXUZKTV/graph.json","fetch_events":"https://pith.science/api/pith-number/T66XBGRLMYLWVSSVDBXXXUZKTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T66XBGRLMYLWVSSVDBXXXUZKTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T66XBGRLMYLWVSSVDBXXXUZKTV/action/storage_attestation","attest_author":"https://pith.science/pith/T66XBGRLMYLWVSSVDBXXXUZKTV/action/author_attestation","sign_citation":"https://pith.science/pith/T66XBGRLMYLWVSSVDBXXXUZKTV/action/citation_signature","submit_replication":"https://pith.science/pith/T66XBGRLMYLWVSSVDBXXXUZKTV/action/replication_record"}},"created_at":"2026-07-05T11:07:47.482584+00:00","updated_at":"2026-07-05T11:07:47.482584+00:00"}