{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXHETCSV6TSHHQLGLOAJKGRTCO","short_pith_number":"pith:MXHETCSV","schema_version":"1.0","canonical_sha256":"65ce498a55f4e473c1665b80951a3313baf41f605fc9e5f9466b30f82f0d6f22","source":{"kind":"arxiv","id":"2505.04016","version":1},"attestation_state":"computed","paper":{"title":"SLOT: Structuring the Output of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Darren Yow-Bang Wang, Haibo Ding, Soumya Smruti Mishra, Yifei Teng, Zhengyuan Shen, Zhichao Xu","submitted_at":"2025-05-06T23:29:43Z","abstract_excerpt":"Structured outputs are essential for large language models (LLMs) in critical applications like agents and information extraction. Despite their capabilities, LLMs often generate outputs that deviate from predefined schemas, significantly hampering reliable application development. We present SLOT (Structured LLM Output Transformer), a model-agnostic approach that transforms unstructured LLM outputs into precise structured formats. While existing solutions predominantly rely on constrained decoding techniques or are tightly coupled with specific models, SLOT employs a fine-tuned lightweight la"},"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":"2505.04016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T23:29:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"215da445f74ed29dfa35d02c0c94c2fb2d29dc9706614ff4b3957976ea47ac50","abstract_canon_sha256":"459881f445ad32487c9b9bc668b830916d26e512118f418e304532bed3500783"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:35.163618Z","signature_b64":"K8wZExA5c4/9lAu/wNNbMefW35LiskMTcthX6pGoLyDrUfuykO7UfSzHKMp6AH8FT4/h4p4Ym6BVcmLDshe2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65ce498a55f4e473c1665b80951a3313baf41f605fc9e5f9466b30f82f0d6f22","last_reissued_at":"2026-07-05T10:59:35.163125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:35.163125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLOT: Structuring the Output of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Darren Yow-Bang Wang, Haibo Ding, Soumya Smruti Mishra, Yifei Teng, Zhengyuan Shen, Zhichao Xu","submitted_at":"2025-05-06T23:29:43Z","abstract_excerpt":"Structured outputs are essential for large language models (LLMs) in critical applications like agents and information extraction. Despite their capabilities, LLMs often generate outputs that deviate from predefined schemas, significantly hampering reliable application development. We present SLOT (Structured LLM Output Transformer), a model-agnostic approach that transforms unstructured LLM outputs into precise structured formats. While existing solutions predominantly rely on constrained decoding techniques or are tightly coupled with specific models, SLOT employs a fine-tuned lightweight la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04016","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/2505.04016/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":"2505.04016","created_at":"2026-07-05T10:59:35.163183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04016v1","created_at":"2026-07-05T10:59:35.163183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04016","created_at":"2026-07-05T10:59:35.163183+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXHETCSV6TSH","created_at":"2026-07-05T10:59:35.163183+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXHETCSV6TSHHQLG","created_at":"2026-07-05T10:59:35.163183+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXHETCSV","created_at":"2026-07-05T10:59:35.163183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20072","citing_title":"Source-Grounded Data Generation for Text-to-JSON Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09395","citing_title":"Empirical Study for Structured Output Control in LLMs for Software Engineering","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08715","citing_title":"Operationalizing Linguistic Methods through Prompt-Engineering Skills: An Automatic Chinese Web Neologism Detection Pipeline","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03367","citing_title":"Automating Information Extraction and Retrieval for Industrial Spare Parts Pooling","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31808","citing_title":"Large Databases Need Small, Open-Weight Language Models","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2602.15189","citing_title":"ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10389","citing_title":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14862","citing_title":"Schema Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXHETCSV6TSHHQLGLOAJKGRTCO","json":"https://pith.science/pith/MXHETCSV6TSHHQLGLOAJKGRTCO.json","graph_json":"https://pith.science/api/pith-number/MXHETCSV6TSHHQLGLOAJKGRTCO/graph.json","events_json":"https://pith.science/api/pith-number/MXHETCSV6TSHHQLGLOAJKGRTCO/events.json","paper":"https://pith.science/paper/MXHETCSV"},"agent_actions":{"view_html":"https://pith.science/pith/MXHETCSV6TSHHQLGLOAJKGRTCO","download_json":"https://pith.science/pith/MXHETCSV6TSHHQLGLOAJKGRTCO.json","view_paper":"https://pith.science/paper/MXHETCSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04016&json=true","fetch_graph":"https://pith.science/api/pith-number/MXHETCSV6TSHHQLGLOAJKGRTCO/graph.json","fetch_events":"https://pith.science/api/pith-number/MXHETCSV6TSHHQLGLOAJKGRTCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXHETCSV6TSHHQLGLOAJKGRTCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXHETCSV6TSHHQLGLOAJKGRTCO/action/storage_attestation","attest_author":"https://pith.science/pith/MXHETCSV6TSHHQLGLOAJKGRTCO/action/author_attestation","sign_citation":"https://pith.science/pith/MXHETCSV6TSHHQLGLOAJKGRTCO/action/citation_signature","submit_replication":"https://pith.science/pith/MXHETCSV6TSHHQLGLOAJKGRTCO/action/replication_record"}},"created_at":"2026-07-05T10:59:35.163183+00:00","updated_at":"2026-07-05T10:59:35.163183+00:00"}