{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XBEAMTAW7BIAEMD3RHOZIMWR2X","short_pith_number":"pith:XBEAMTAW","schema_version":"1.0","canonical_sha256":"b848064c16f85002307b89dd9432d1d5c7fe57240be039f13beb9dfd22adc9fe","source":{"kind":"arxiv","id":"2401.00690","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benfeng Xu, Quan Wang, Yihan Chen, Yi Liu, Zhendong Mao","submitted_at":"2024-01-01T07:35:31Z","abstract_excerpt":"While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. As a significant aspect of LLM alignment, it is thus important to formulate such a specialized set of instructions as well as investigate the resulting behavior of LLMs. To address this vacancy, we propose a new benchmark CoDI-Eval to systematically and comprehensively evaluate LLMs' responses to instructions with various constraints. We construct a large collectio"},"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":"2401.00690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T07:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"b9436076b9f4774b47d3e43e449d4b7bbe57f229789e45820ba32ae61880e598","abstract_canon_sha256":"e079c62abb22c6992863556693756d9d089f98231eef706c3fb314a9ad5a1fb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:21.997995Z","signature_b64":"UYVYW8107LqC4qqLArVH/hB8K+1YP/IV/+IlUltCJ0IAgWh6X0DJbKFPuirrmMnYsyXJuRUnmsvPuxlTFFHzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b848064c16f85002307b89dd9432d1d5c7fe57240be039f13beb9dfd22adc9fe","last_reissued_at":"2026-07-05T07:29:21.997522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:21.997522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benfeng Xu, Quan Wang, Yihan Chen, Yi Liu, Zhendong Mao","submitted_at":"2024-01-01T07:35:31Z","abstract_excerpt":"While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. As a significant aspect of LLM alignment, it is thus important to formulate such a specialized set of instructions as well as investigate the resulting behavior of LLMs. To address this vacancy, we propose a new benchmark CoDI-Eval to systematically and comprehensively evaluate LLMs' responses to instructions with various constraints. We construct a large collectio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00690","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/2401.00690/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":"2401.00690","created_at":"2026-07-05T07:29:21.997588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00690v1","created_at":"2026-07-05T07:29:21.997588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00690","created_at":"2026-07-05T07:29:21.997588+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBEAMTAW7BIA","created_at":"2026-07-05T07:29:21.997588+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBEAMTAW7BIAEMD3","created_at":"2026-07-05T07:29:21.997588+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBEAMTAW","created_at":"2026-07-05T07:29:21.997588+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08972","citing_title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBEAMTAW7BIAEMD3RHOZIMWR2X","json":"https://pith.science/pith/XBEAMTAW7BIAEMD3RHOZIMWR2X.json","graph_json":"https://pith.science/api/pith-number/XBEAMTAW7BIAEMD3RHOZIMWR2X/graph.json","events_json":"https://pith.science/api/pith-number/XBEAMTAW7BIAEMD3RHOZIMWR2X/events.json","paper":"https://pith.science/paper/XBEAMTAW"},"agent_actions":{"view_html":"https://pith.science/pith/XBEAMTAW7BIAEMD3RHOZIMWR2X","download_json":"https://pith.science/pith/XBEAMTAW7BIAEMD3RHOZIMWR2X.json","view_paper":"https://pith.science/paper/XBEAMTAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00690&json=true","fetch_graph":"https://pith.science/api/pith-number/XBEAMTAW7BIAEMD3RHOZIMWR2X/graph.json","fetch_events":"https://pith.science/api/pith-number/XBEAMTAW7BIAEMD3RHOZIMWR2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBEAMTAW7BIAEMD3RHOZIMWR2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBEAMTAW7BIAEMD3RHOZIMWR2X/action/storage_attestation","attest_author":"https://pith.science/pith/XBEAMTAW7BIAEMD3RHOZIMWR2X/action/author_attestation","sign_citation":"https://pith.science/pith/XBEAMTAW7BIAEMD3RHOZIMWR2X/action/citation_signature","submit_replication":"https://pith.science/pith/XBEAMTAW7BIAEMD3RHOZIMWR2X/action/replication_record"}},"created_at":"2026-07-05T07:29:21.997588+00:00","updated_at":"2026-07-05T07:29:21.997588+00:00"}