{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HNSLU5ZXIXVVGC7F73G2ZLPN4T","short_pith_number":"pith:HNSLU5ZX","schema_version":"1.0","canonical_sha256":"3b64ba773745eb530be5fecdacadede4d7da2f7ed672539c38769a2a9c9f26df","source":{"kind":"arxiv","id":"2410.13111","version":1},"attestation_state":"computed","paper":{"title":"Controllable Generation via Locally Constrained Resampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guy Van den Broeck, Kai-Wei Chang, Kareem Ahmed","submitted_at":"2024-10-17T00:49:53Z","abstract_excerpt":"Autoregressive models have demonstrated an unprecedented ability at modeling the intricacies of natural language. However, they continue to struggle with generating complex outputs that adhere to logical constraints. Sampling from a fully-independent distribution subject to a constraint is hard. Sampling from an autoregressive distribution subject to a constraint is doubly hard: We have to contend not only with the hardness of the constraint but also the distribution's lack of structure. We propose a tractable probabilistic approach that performs Bayesian conditioning to draw samples subject t"},"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":"2410.13111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T00:49:53Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"eb68dcfd2a8466cb1e286601f5725374e0443a38b691c00e4262c50cc3a5de85","abstract_canon_sha256":"9b5c70abad0dc86aa4e003fddee47a2f998c9461c5b96ba8d9c622048f656f5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:55.549723Z","signature_b64":"eDi5P3LCTXFXPF2o1F6ZnBETBvTerG48b/3wpIcHVeWxtDBZSXUneWGe/z2P0qBRDiyArhLnSJ492myqVOZpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b64ba773745eb530be5fecdacadede4d7da2f7ed672539c38769a2a9c9f26df","last_reissued_at":"2026-07-05T09:21:55.549229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:55.549229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Generation via Locally Constrained Resampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guy Van den Broeck, Kai-Wei Chang, Kareem Ahmed","submitted_at":"2024-10-17T00:49:53Z","abstract_excerpt":"Autoregressive models have demonstrated an unprecedented ability at modeling the intricacies of natural language. However, they continue to struggle with generating complex outputs that adhere to logical constraints. Sampling from a fully-independent distribution subject to a constraint is hard. Sampling from an autoregressive distribution subject to a constraint is doubly hard: We have to contend not only with the hardness of the constraint but also the distribution's lack of structure. We propose a tractable probabilistic approach that performs Bayesian conditioning to draw samples subject t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13111","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/2410.13111/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":"2410.13111","created_at":"2026-07-05T09:21:55.549287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13111v1","created_at":"2026-07-05T09:21:55.549287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13111","created_at":"2026-07-05T09:21:55.549287+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNSLU5ZXIXVV","created_at":"2026-07-05T09:21:55.549287+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNSLU5ZXIXVVGC7F","created_at":"2026-07-05T09:21:55.549287+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNSLU5ZX","created_at":"2026-07-05T09:21:55.549287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.22277","citing_title":"TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNSLU5ZXIXVVGC7F73G2ZLPN4T","json":"https://pith.science/pith/HNSLU5ZXIXVVGC7F73G2ZLPN4T.json","graph_json":"https://pith.science/api/pith-number/HNSLU5ZXIXVVGC7F73G2ZLPN4T/graph.json","events_json":"https://pith.science/api/pith-number/HNSLU5ZXIXVVGC7F73G2ZLPN4T/events.json","paper":"https://pith.science/paper/HNSLU5ZX"},"agent_actions":{"view_html":"https://pith.science/pith/HNSLU5ZXIXVVGC7F73G2ZLPN4T","download_json":"https://pith.science/pith/HNSLU5ZXIXVVGC7F73G2ZLPN4T.json","view_paper":"https://pith.science/paper/HNSLU5ZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13111&json=true","fetch_graph":"https://pith.science/api/pith-number/HNSLU5ZXIXVVGC7F73G2ZLPN4T/graph.json","fetch_events":"https://pith.science/api/pith-number/HNSLU5ZXIXVVGC7F73G2ZLPN4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNSLU5ZXIXVVGC7F73G2ZLPN4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNSLU5ZXIXVVGC7F73G2ZLPN4T/action/storage_attestation","attest_author":"https://pith.science/pith/HNSLU5ZXIXVVGC7F73G2ZLPN4T/action/author_attestation","sign_citation":"https://pith.science/pith/HNSLU5ZXIXVVGC7F73G2ZLPN4T/action/citation_signature","submit_replication":"https://pith.science/pith/HNSLU5ZXIXVVGC7F73G2ZLPN4T/action/replication_record"}},"created_at":"2026-07-05T09:21:55.549287+00:00","updated_at":"2026-07-05T09:21:55.549287+00:00"}