{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KZ2IM3AQ6ERDFREEWLVYGYTEKQ","short_pith_number":"pith:KZ2IM3AQ","schema_version":"1.0","canonical_sha256":"5674866c10f12232c484b2eb836264540b96d14c1a2c6aa3dd96194344e4ffb5","source":{"kind":"arxiv","id":"2210.02875","version":2},"attestation_state":"computed","paper":{"title":"Binding Language Models in Symbolic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Chengzu Li, Dragomir Radev, Luke Zettlemoyer, Mari Ostendorf, Noah A. Smith, Peng Shi, Rahul Nadkarni, Tao Yu, Tianbao Xie, Yushi Hu, Zhoujun Cheng","submitted_at":"2022-10-06T12:55:17Z","abstract_excerpt":"Though end-to-end neural approaches have recently been dominating NLP tasks in both performance and ease-of-use, they lack interpretability and robustness. We propose Binder, a training-free neural-symbolic framework that maps the task input to a program, which (1) allows binding a unified API of language model (LM) functionalities to a programming language (e.g., SQL, Python) to extend its grammar coverage and thus tackle more diverse questions, (2) adopts an LM as both the program parser and the underlying model called by the API during execution, and (3) requires only a few in-context exemp"},"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":"2210.02875","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T12:55:17Z","cross_cats_sorted":[],"title_canon_sha256":"4a5a701566fdbaaf799cc8131fc2721407a2bece80589cf03d2bbc3309a846bf","abstract_canon_sha256":"696ebdc685b57a64cb81e110f1794d1343bf8d7e870136b1403451223d9157e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:52.286049Z","signature_b64":"33McosuzGsdC2PI7M4P0uW+SHI3u92f3ubuUeo5x/6Ku7kE9B6KiUoAFymoXLtbOYsWIrO04LxGFKHzCFSlcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5674866c10f12232c484b2eb836264540b96d14c1a2c6aa3dd96194344e4ffb5","last_reissued_at":"2026-07-05T05:46:52.285626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:52.285626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Binding Language Models in Symbolic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Chengzu Li, Dragomir Radev, Luke Zettlemoyer, Mari Ostendorf, Noah A. Smith, Peng Shi, Rahul Nadkarni, Tao Yu, Tianbao Xie, Yushi Hu, Zhoujun Cheng","submitted_at":"2022-10-06T12:55:17Z","abstract_excerpt":"Though end-to-end neural approaches have recently been dominating NLP tasks in both performance and ease-of-use, they lack interpretability and robustness. We propose Binder, a training-free neural-symbolic framework that maps the task input to a program, which (1) allows binding a unified API of language model (LM) functionalities to a programming language (e.g., SQL, Python) to extend its grammar coverage and thus tackle more diverse questions, (2) adopts an LM as both the program parser and the underlying model called by the API during execution, and (3) requires only a few in-context exemp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02875","kind":"arxiv","version":2},"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/2210.02875/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":"2210.02875","created_at":"2026-07-05T05:46:52.285695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02875v2","created_at":"2026-07-05T05:46:52.285695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02875","created_at":"2026-07-05T05:46:52.285695+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZ2IM3AQ6ERD","created_at":"2026-07-05T05:46:52.285695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZ2IM3AQ6ERDFREE","created_at":"2026-07-05T05:46:52.285695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZ2IM3AQ","created_at":"2026-07-05T05:46:52.285695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10316","citing_title":"TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17680","citing_title":"When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20816","citing_title":"Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2211.10435","citing_title":"PAL: Program-aided Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12975","citing_title":"Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2211.12588","citing_title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00199","citing_title":"RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10973","citing_title":"CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08792","citing_title":"Choose, Don't Label: Multiple-Choice Query Synthesis for Program Disambiguation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2210.09261","citing_title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZ2IM3AQ6ERDFREEWLVYGYTEKQ","json":"https://pith.science/pith/KZ2IM3AQ6ERDFREEWLVYGYTEKQ.json","graph_json":"https://pith.science/api/pith-number/KZ2IM3AQ6ERDFREEWLVYGYTEKQ/graph.json","events_json":"https://pith.science/api/pith-number/KZ2IM3AQ6ERDFREEWLVYGYTEKQ/events.json","paper":"https://pith.science/paper/KZ2IM3AQ"},"agent_actions":{"view_html":"https://pith.science/pith/KZ2IM3AQ6ERDFREEWLVYGYTEKQ","download_json":"https://pith.science/pith/KZ2IM3AQ6ERDFREEWLVYGYTEKQ.json","view_paper":"https://pith.science/paper/KZ2IM3AQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02875&json=true","fetch_graph":"https://pith.science/api/pith-number/KZ2IM3AQ6ERDFREEWLVYGYTEKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KZ2IM3AQ6ERDFREEWLVYGYTEKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZ2IM3AQ6ERDFREEWLVYGYTEKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZ2IM3AQ6ERDFREEWLVYGYTEKQ/action/storage_attestation","attest_author":"https://pith.science/pith/KZ2IM3AQ6ERDFREEWLVYGYTEKQ/action/author_attestation","sign_citation":"https://pith.science/pith/KZ2IM3AQ6ERDFREEWLVYGYTEKQ/action/citation_signature","submit_replication":"https://pith.science/pith/KZ2IM3AQ6ERDFREEWLVYGYTEKQ/action/replication_record"}},"created_at":"2026-07-05T05:46:52.285695+00:00","updated_at":"2026-07-05T05:46:52.285695+00:00"}