{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ON6BM3RJOG5MCXYQQJCGWTJDTU","short_pith_number":"pith:ON6BM3RJ","canonical_record":{"source":{"id":"2410.06458","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T01:25:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"16e2ca556d9aa7b9b5522073cf43edffca2b035276cdc68432d2462e5b17b9aa","abstract_canon_sha256":"bbfbfc0f38e989c1743234cccd75341f515b09bb884fe96e99970c022447c525"},"schema_version":"1.0"},"canonical_sha256":"737c166e2971bac15f1082446b4d239d2959605dfd4174b0d623d48b8467c931","source":{"kind":"arxiv","id":"2410.06458","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06458","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06458v1","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06458","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"ON6BM3RJOG5M","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"ON6BM3RJOG5MCXYQ","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"ON6BM3RJ","created_at":"2026-07-05T09:18:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ON6BM3RJOG5MCXYQQJCGWTJDTU","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06458","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T01:25:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"16e2ca556d9aa7b9b5522073cf43edffca2b035276cdc68432d2462e5b17b9aa","abstract_canon_sha256":"bbfbfc0f38e989c1743234cccd75341f515b09bb884fe96e99970c022447c525"},"schema_version":"1.0"},"canonical_sha256":"737c166e2971bac15f1082446b4d239d2959605dfd4174b0d623d48b8467c931","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:02.014649Z","signature_b64":"V3UbbyOdwkAvkXghVuEPa2P9haHQScM+Px2FmcSVsT/D8jfiAGYIkJSiSDkPH2UXUYTTAc6qprEZUgkRJPS5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"737c166e2971bac15f1082446b4d239d2959605dfd4174b0d623d48b8467c931","last_reissued_at":"2026-07-05T09:18:02.014095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:02.014095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06458","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PcTIXuz5H0uT2zKm5HhUErgPbRHxIZr4mQL0xYwxb9NuBlTosYBWXGibDj9ZVb0S9T4cdriUiE6+iM+AYrivAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:01:39.642352Z"},"content_sha256":"7fe55913b8accdc8e66f0403624f01f3373d4c8a413d430c0b2a804bcedfdc9f","schema_version":"1.0","event_id":"sha256:7fe55913b8accdc8e66f0403624f01f3373d4c8a413d430c0b2a804bcedfdc9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ON6BM3RJOG5MCXYQQJCGWTJDTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haw-Shiuan Chang, Kartik Mehta, Mohit Bansal, Nanyun Peng, Shereen Oraby, Sijia Liu, Tagyoung Chung, Thomas Palmeira Ferraz, Vivek Subramanian, Yu-Hsiang Lin","submitted_at":"2024-10-09T01:25:10Z","abstract_excerpt":"Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to create a social media post \"in a funny tone\" with \"no hashtag\"). Despite this, most evaluations focus solely on synthetic data. To address this, we introduce RealInstruct, the first benchmark designed to evaluate LLMs' ability to follow real-world multi-constrained instructions by leveraging queries real users asked AI assistants. We also investigate model-based evaluation as a cost-effective alternative to human an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06458","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/2410.06458/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQxWo/iso86dNVBw9I4AgpQqDg7rmHkWkMfbw+4ThIs8lJHMpnhvn2ZbRzzvCOo9EKaD/9/3disc3BNltlavCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:01:39.643287Z"},"content_sha256":"d6d8eca0367c7ca74ac25b4f03f5d1265abaebb7a3b6c434cda101bebabbb210","schema_version":"1.0","event_id":"sha256:d6d8eca0367c7ca74ac25b4f03f5d1265abaebb7a3b6c434cda101bebabbb210"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ON6BM3RJOG5MCXYQQJCGWTJDTU/bundle.json","state_url":"https://pith.science/pith/ON6BM3RJOG5MCXYQQJCGWTJDTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ON6BM3RJOG5MCXYQQJCGWTJDTU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T21:01:39Z","links":{"resolver":"https://pith.science/pith/ON6BM3RJOG5MCXYQQJCGWTJDTU","bundle":"https://pith.science/pith/ON6BM3RJOG5MCXYQQJCGWTJDTU/bundle.json","state":"https://pith.science/pith/ON6BM3RJOG5MCXYQQJCGWTJDTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ON6BM3RJOG5MCXYQQJCGWTJDTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ON6BM3RJOG5MCXYQQJCGWTJDTU","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":"bbfbfc0f38e989c1743234cccd75341f515b09bb884fe96e99970c022447c525","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T01:25:10Z","title_canon_sha256":"16e2ca556d9aa7b9b5522073cf43edffca2b035276cdc68432d2462e5b17b9aa"},"schema_version":"1.0","source":{"id":"2410.06458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06458","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06458v1","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06458","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"ON6BM3RJOG5M","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"ON6BM3RJOG5MCXYQ","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"ON6BM3RJ","created_at":"2026-07-05T09:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:d6d8eca0367c7ca74ac25b4f03f5d1265abaebb7a3b6c434cda101bebabbb210","target":"graph","created_at":"2026-07-05T09:18:02Z","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/2410.06458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to create a social media post \"in a funny tone\" with \"no hashtag\"). Despite this, most evaluations focus solely on synthetic data. To address this, we introduce RealInstruct, the first benchmark designed to evaluate LLMs' ability to follow real-world multi-constrained instructions by leveraging queries real users asked AI assistants. We also investigate model-based evaluation as a cost-effective alternative to human an","authors_text":"Haw-Shiuan Chang, Kartik Mehta, Mohit Bansal, Nanyun Peng, Shereen Oraby, Sijia Liu, Tagyoung Chung, Thomas Palmeira Ferraz, Vivek Subramanian, Yu-Hsiang Lin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T01:25:10Z","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06458","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":"sha256:7fe55913b8accdc8e66f0403624f01f3373d4c8a413d430c0b2a804bcedfdc9f","target":"record","created_at":"2026-07-05T09:18:02Z","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":"bbfbfc0f38e989c1743234cccd75341f515b09bb884fe96e99970c022447c525","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T01:25:10Z","title_canon_sha256":"16e2ca556d9aa7b9b5522073cf43edffca2b035276cdc68432d2462e5b17b9aa"},"schema_version":"1.0","source":{"id":"2410.06458","kind":"arxiv","version":1}},"canonical_sha256":"737c166e2971bac15f1082446b4d239d2959605dfd4174b0d623d48b8467c931","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"737c166e2971bac15f1082446b4d239d2959605dfd4174b0d623d48b8467c931","first_computed_at":"2026-07-05T09:18:02.014095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:02.014095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V3UbbyOdwkAvkXghVuEPa2P9haHQScM+Px2FmcSVsT/D8jfiAGYIkJSiSDkPH2UXUYTTAc6qprEZUgkRJPS5Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:02.014649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fe55913b8accdc8e66f0403624f01f3373d4c8a413d430c0b2a804bcedfdc9f","sha256:d6d8eca0367c7ca74ac25b4f03f5d1265abaebb7a3b6c434cda101bebabbb210"],"state_sha256":"560b13ebecacf710cb73d9de991b6c761f05631b91a47bbaf37f8f8b51b0f546"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OADTwVhyX9MDgKbGOux2bgdGpcFZIqoi0SJy+HH1pJoGZ6iKRcBh7i4wSk2xOb06G0NudI+mke5CytllEcISCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T21:01:39.648883Z","bundle_sha256":"64da600e50072a0d0dff0ab5439792febac86ae1a333ee99999f941ad960c41b"}}