{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UI73PMUTQZ6HQWAUDOXXRRLDBG","short_pith_number":"pith:UI73PMUT","schema_version":"1.0","canonical_sha256":"a23fb7b293867c7858141baf78c5630997f95d9cad0a99d9a23b107a1162f0e3","source":{"kind":"arxiv","id":"2608.12574","version":1},"attestation_state":"computed","paper":{"title":"Trie Automata for Constrained Decoding over Large Finite Sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.AI","authors_text":"Karim Bouyarmane, Xingzi Xu","submitted_at":"2026-08-12T20:38:51Z","abstract_excerpt":"Large language models increasingly need to generate structured outputs that conform to predefined schemas, with one common constraint being selection from a finite set of valid strings. Current constrained decoding systems handle this through general-purpose grammar compilation, which becomes prohibitively slow as the number of valid values grows into the thousands, a cardinality wall. We introduce the trie automaton, a specialized mechanism that exploits finite-set structure (shared prefixes, bounded depth, known cardinality) via Aho-Corasick multi-pattern matching to precompute per-node toke"},"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":"2608.12574","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T20:38:51Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"97bbc9d6e40fe378f56905886dea911734a1652892d795457b1e9a67748b7648","abstract_canon_sha256":"0e4d2d375799e0d5f49554f0cf4f9b164f38061e47ecadfeb85519eb648dfa8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:45:16.724291Z","signature_b64":"0Bn7aCt746FqzmnolEHTSnmd5RYEaCPpA6cZ7cdKiWHBPhJrXILLerqA7zPjFRW0Vidr1e1rcqb3nG/UCA1LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a23fb7b293867c7858141baf78c5630997f95d9cad0a99d9a23b107a1162f0e3","last_reissued_at":"2026-08-14T00:45:16.715686Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:45:16.715686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trie Automata for Constrained Decoding over Large Finite Sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.AI","authors_text":"Karim Bouyarmane, Xingzi Xu","submitted_at":"2026-08-12T20:38:51Z","abstract_excerpt":"Large language models increasingly need to generate structured outputs that conform to predefined schemas, with one common constraint being selection from a finite set of valid strings. Current constrained decoding systems handle this through general-purpose grammar compilation, which becomes prohibitively slow as the number of valid values grows into the thousands, a cardinality wall. We introduce the trie automaton, a specialized mechanism that exploits finite-set structure (shared prefixes, bounded depth, known cardinality) via Aho-Corasick multi-pattern matching to precompute per-node toke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12574","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/2608.12574/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":"2608.12574","created_at":"2026-08-14T00:45:16.721444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12574v1","created_at":"2026-08-14T00:45:16.721444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12574","created_at":"2026-08-14T00:45:16.721444+00:00"},{"alias_kind":"pith_short_12","alias_value":"UI73PMUTQZ6H","created_at":"2026-08-14T00:45:16.721444+00:00"},{"alias_kind":"pith_short_16","alias_value":"UI73PMUTQZ6HQWAU","created_at":"2026-08-14T00:45:16.721444+00:00"},{"alias_kind":"pith_short_8","alias_value":"UI73PMUT","created_at":"2026-08-14T00:45:16.721444+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/UI73PMUTQZ6HQWAUDOXXRRLDBG","json":"https://pith.science/pith/UI73PMUTQZ6HQWAUDOXXRRLDBG.json","graph_json":"https://pith.science/api/pith-number/UI73PMUTQZ6HQWAUDOXXRRLDBG/graph.json","events_json":"https://pith.science/api/pith-number/UI73PMUTQZ6HQWAUDOXXRRLDBG/events.json","paper":"https://pith.science/paper/UI73PMUT"},"agent_actions":{"view_html":"https://pith.science/pith/UI73PMUTQZ6HQWAUDOXXRRLDBG","download_json":"https://pith.science/pith/UI73PMUTQZ6HQWAUDOXXRRLDBG.json","view_paper":"https://pith.science/paper/UI73PMUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12574&json=true","fetch_graph":"https://pith.science/api/pith-number/UI73PMUTQZ6HQWAUDOXXRRLDBG/graph.json","fetch_events":"https://pith.science/api/pith-number/UI73PMUTQZ6HQWAUDOXXRRLDBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UI73PMUTQZ6HQWAUDOXXRRLDBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UI73PMUTQZ6HQWAUDOXXRRLDBG/action/storage_attestation","attest_author":"https://pith.science/pith/UI73PMUTQZ6HQWAUDOXXRRLDBG/action/author_attestation","sign_citation":"https://pith.science/pith/UI73PMUTQZ6HQWAUDOXXRRLDBG/action/citation_signature","submit_replication":"https://pith.science/pith/UI73PMUTQZ6HQWAUDOXXRRLDBG/action/replication_record"}},"created_at":"2026-08-14T00:45:16.721444+00:00","updated_at":"2026-08-14T00:45:16.721444+00:00"}