{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XBEAMTAW7BIAEMD3RHOZIMWR2X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e079c62abb22c6992863556693756d9d089f98231eef706c3fb314a9ad5a1fb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T07:35:31Z","title_canon_sha256":"b9436076b9f4774b47d3e43e449d4b7bbe57f229789e45820ba32ae61880e598"},"schema_version":"1.0","source":{"id":"2401.00690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00690","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00690v1","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00690","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"pith_short_12","alias_value":"XBEAMTAW7BIA","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"pith_short_16","alias_value":"XBEAMTAW7BIAEMD3","created_at":"2026-07-05T07:29:21Z"},{"alias_kind":"pith_short_8","alias_value":"XBEAMTAW","created_at":"2026-07-05T07:29:21Z"}],"graph_snapshots":[{"event_id":"sha256:e7baba056f23bde3a37c502b6af11bc9801e8fcbe9c420189766b64479f47647","target":"graph","created_at":"2026-07-05T07:29:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.00690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benfeng Xu, Quan Wang, Yihan Chen, Yi Liu, Zhendong Mao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T07:35:31Z","title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00690","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ed07ecb58f3334270852b8decfb7bfce3887d0144658aefb4fafcb130f3c3300","target":"record","created_at":"2026-07-05T07:29:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e079c62abb22c6992863556693756d9d089f98231eef706c3fb314a9ad5a1fb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T07:35:31Z","title_canon_sha256":"b9436076b9f4774b47d3e43e449d4b7bbe57f229789e45820ba32ae61880e598"},"schema_version":"1.0","source":{"id":"2401.00690","kind":"arxiv","version":1}},"canonical_sha256":"b848064c16f85002307b89dd9432d1d5c7fe57240be039f13beb9dfd22adc9fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b848064c16f85002307b89dd9432d1d5c7fe57240be039f13beb9dfd22adc9fe","first_computed_at":"2026-07-05T07:29:21.997522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:21.997522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UYVYW8107LqC4qqLArVH/hB8K+1YP/IV/+IlUltCJ0IAgWh6X0DJbKFPuirrmMnYsyXJuRUnmsvPuxlTFFHzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:21.997995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed07ecb58f3334270852b8decfb7bfce3887d0144658aefb4fafcb130f3c3300","sha256:e7baba056f23bde3a37c502b6af11bc9801e8fcbe9c420189766b64479f47647"],"state_sha256":"e8e7436b54ce1217a12609fb903b2da62d419d549207a969adbacd231fec3acb"}