{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DJT4GTDHLTNX2A5CBC7OWSCNDN","short_pith_number":"pith:DJT4GTDH","canonical_record":{"source":{"id":"2310.20410","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T12:32:38Z","cross_cats_sorted":[],"title_canon_sha256":"f31aa1ec9cbf2a2d0cf1b1b3dff202423d987be9afff37ba5b2b14c864be58be","abstract_canon_sha256":"f73a167d8970a4463148eb9ebab411f5e039c85dba90d5678e1e3b7219620231"},"schema_version":"1.0"},"canonical_sha256":"1a67c34c675cdb7d03a208beeb484d1b5d57dd269e8205dc20e2f3aecfaf55dc","source":{"kind":"arxiv","id":"2310.20410","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20410","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20410v3","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20410","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"pith_short_12","alias_value":"DJT4GTDHLTNX","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"pith_short_16","alias_value":"DJT4GTDHLTNX2A5C","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"pith_short_8","alias_value":"DJT4GTDH","created_at":"2026-07-05T08:27:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DJT4GTDHLTNX2A5CBC7OWSCNDN","target":"record","payload":{"canonical_record":{"source":{"id":"2310.20410","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T12:32:38Z","cross_cats_sorted":[],"title_canon_sha256":"f31aa1ec9cbf2a2d0cf1b1b3dff202423d987be9afff37ba5b2b14c864be58be","abstract_canon_sha256":"f73a167d8970a4463148eb9ebab411f5e039c85dba90d5678e1e3b7219620231"},"schema_version":"1.0"},"canonical_sha256":"1a67c34c675cdb7d03a208beeb484d1b5d57dd269e8205dc20e2f3aecfaf55dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:43.534892Z","signature_b64":"W1lTsVS+ng4b2rF/xbUWmXnCkvFJHQGquuPGXQmlm6UPzC1GMH+zJl7BP7cTwtSalEroNQgnnCYdvnr2sKJBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a67c34c675cdb7d03a208beeb484d1b5d57dd269e8205dc20e2f3aecfaf55dc","last_reissued_at":"2026-07-05T08:27:43.534285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:43.534285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.20410","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y7tI1Jqe+dFvolLj3w4BUyjDGaGYf9Nii8XKvpcMFzgtCSWDhlQ7CHbCXaqDJBYryJC39dqeMQpBP73qX2k/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:09:48.021558Z"},"content_sha256":"02765817db9c8345d291a6b703e2d48fa9f37d0df39a321dd37935e1a23ab4c7","schema_version":"1.0","event_id":"sha256:02765817db9c8345d291a6b703e2d48fa9f37d0df39a321dd37935e1a23ab4c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DJT4GTDHLTNX2A5CBC7OWSCNDN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Mi, Liangyou Li, Lifeng Shang, Qun Liu, Wanjun Zhong, Wei Wang, Xingshan Zeng, Xin Jiang, Yufei Wang, Yuxin Jiang","submitted_at":"2023-10-31T12:32:38Z","abstract_excerpt":"The ability to follow instructions is crucial for Large Language Models (LLMs) to handle various real-world applications. Existing benchmarks primarily focus on evaluating pure response quality, rather than assessing whether the response follows constraints stated in the instruction. To fill this research gap, in this paper, we propose FollowBench, a Multi-level Fine-grained Constraints Following Benchmark for LLMs. FollowBench comprehensively includes five different types (i.e., Content, Situation, Style, Format, and Example) of fine-grained constraints. To enable a precise constraint followi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20410","kind":"arxiv","version":3},"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/2310.20410/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":"2026-07-05T08:27:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dxy7RIhM822GL+P4Om+4LTvx0gF1YRKovHTMISi12iBWvH1+rrinLiC+/KFbQ9MvF1DFl0gxu9eXSxSfQ2NFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:09:48.022061Z"},"content_sha256":"24d6a32727af0484df0bdf4817a97913231c3fd76be8557e63e27637ea7eb29e","schema_version":"1.0","event_id":"sha256:24d6a32727af0484df0bdf4817a97913231c3fd76be8557e63e27637ea7eb29e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DJT4GTDHLTNX2A5CBC7OWSCNDN/bundle.json","state_url":"https://pith.science/pith/DJT4GTDHLTNX2A5CBC7OWSCNDN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DJT4GTDHLTNX2A5CBC7OWSCNDN/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":"2026-08-07T17:09:48Z","links":{"resolver":"https://pith.science/pith/DJT4GTDHLTNX2A5CBC7OWSCNDN","bundle":"https://pith.science/pith/DJT4GTDHLTNX2A5CBC7OWSCNDN/bundle.json","state":"https://pith.science/pith/DJT4GTDHLTNX2A5CBC7OWSCNDN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DJT4GTDHLTNX2A5CBC7OWSCNDN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DJT4GTDHLTNX2A5CBC7OWSCNDN","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":"f73a167d8970a4463148eb9ebab411f5e039c85dba90d5678e1e3b7219620231","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T12:32:38Z","title_canon_sha256":"f31aa1ec9cbf2a2d0cf1b1b3dff202423d987be9afff37ba5b2b14c864be58be"},"schema_version":"1.0","source":{"id":"2310.20410","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20410","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20410v3","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20410","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"pith_short_12","alias_value":"DJT4GTDHLTNX","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"pith_short_16","alias_value":"DJT4GTDHLTNX2A5C","created_at":"2026-07-05T08:27:43Z"},{"alias_kind":"pith_short_8","alias_value":"DJT4GTDH","created_at":"2026-07-05T08:27:43Z"}],"graph_snapshots":[{"event_id":"sha256:24d6a32727af0484df0bdf4817a97913231c3fd76be8557e63e27637ea7eb29e","target":"graph","created_at":"2026-07-05T08:27:43Z","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/2310.20410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to follow instructions is crucial for Large Language Models (LLMs) to handle various real-world applications. Existing benchmarks primarily focus on evaluating pure response quality, rather than assessing whether the response follows constraints stated in the instruction. To fill this research gap, in this paper, we propose FollowBench, a Multi-level Fine-grained Constraints Following Benchmark for LLMs. FollowBench comprehensively includes five different types (i.e., Content, Situation, Style, Format, and Example) of fine-grained constraints. To enable a precise constraint followi","authors_text":"Fei Mi, Liangyou Li, Lifeng Shang, Qun Liu, Wanjun Zhong, Wei Wang, Xingshan Zeng, Xin Jiang, Yufei Wang, Yuxin Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T12:32:38Z","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20410","kind":"arxiv","version":3},"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":"sha256:02765817db9c8345d291a6b703e2d48fa9f37d0df39a321dd37935e1a23ab4c7","target":"record","created_at":"2026-07-05T08:27:43Z","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":"f73a167d8970a4463148eb9ebab411f5e039c85dba90d5678e1e3b7219620231","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T12:32:38Z","title_canon_sha256":"f31aa1ec9cbf2a2d0cf1b1b3dff202423d987be9afff37ba5b2b14c864be58be"},"schema_version":"1.0","source":{"id":"2310.20410","kind":"arxiv","version":3}},"canonical_sha256":"1a67c34c675cdb7d03a208beeb484d1b5d57dd269e8205dc20e2f3aecfaf55dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a67c34c675cdb7d03a208beeb484d1b5d57dd269e8205dc20e2f3aecfaf55dc","first_computed_at":"2026-07-05T08:27:43.534285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:43.534285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W1lTsVS+ng4b2rF/xbUWmXnCkvFJHQGquuPGXQmlm6UPzC1GMH+zJl7BP7cTwtSalEroNQgnnCYdvnr2sKJBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:43.534892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.20410","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02765817db9c8345d291a6b703e2d48fa9f37d0df39a321dd37935e1a23ab4c7","sha256:24d6a32727af0484df0bdf4817a97913231c3fd76be8557e63e27637ea7eb29e"],"state_sha256":"2917353d31aca3f6a8e8628b4caf5b57322cfb826900033869cb860689decf1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZdWwrxFKp9ZNk5ryLOs9BC8LBO75N457QDFeIn0uc/ljiMYBwV/eki7r6to3A+apMbEU4wJ8uCLQGhGwW46DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:09:48.025907Z","bundle_sha256":"4700f620f67608787da0bd46f01435331496781c80f805381eaedf9151a5936b"}}