Metraipolis › archive › dc_27aa41dbe4e8

Adapt Semantics, Not Structure: Few-Instance Schema Calibration for Scientific PDF Extraction — arXiv:2609.34841

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34841
License (as archived): CC0-1.0
Archived: 2026-10-07T21:53:34.093Z
SHA-256 of the archived text: cb40bf9be213edc4e5e77745b194374dc06b90ce627adb28ec41296d1659665a
Stable URL of this page: https://metraipolis.com/documento/dc_27aa41dbe4e8

How to cite

Adapt Semantics, Not Structure: Few-Instance Schema Calibration for Scientific PDF Extraction — arXiv:2609.34841 — arXiv (en), https://arxiv.org/abs/2609.34841 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27aa41dbe4e8 (Metraipolis archive dc_27aa41dbe4e8, sha256 cb40bf9be213edc4e5e77745b194374dc06b90ce627adb28ec41296d1659665a)

BibTeX

@misc{dc27aa41dbe4e8,
  title = {Adapt Semantics, Not Structure: Few-Instance Schema Calibration for Scientific PDF Extraction — arXiv:2609.34841},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34841},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27aa41dbe4e8; sha256 cb40bf9be213edc4e5e77745b194374dc06b90ce627adb28ec41296d1659665a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34841. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A well-designed extraction schema is not necessarily ready for reliable LLM execution. When only limited verified extractions are available, manually tuning hundreds of field definitions through trial and error is costly. We frame this problem as few-instance schema calibration: adapting the operational semantics of an existing schema from a few annotated documents while preserving its structural contract. We introduce CPSE, a contract-preserving semantic extraction framework that jointly calibrates extraction prompts and field-level semantic descriptions from a few gold annotations. CPSE decomposes the schema into an invariant structural contract and mutable field semantics, and further separates identity discovery from record completion using manifest-conditioned resolution. On expert-annotated polymer-science documents, CPSE improves extraction by 9.93 points over an execution-matched baseline, with consistent gains under an independent judge and in a blinded expert audit. These results show that CPSE enables low-resource schema execution while preserving the output structure required downstream.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.34841 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T21:27:08.646Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).