{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AXCPT52C4R7GNIWDEHJQPHJXTE","short_pith_number":"pith:AXCPT52C","canonical_record":{"source":{"id":"2505.16234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T05:08:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b3881fa668dfdb6b1aaa7805cd79a39df5c9fbb96d9d54f10f003287ad8a575","abstract_canon_sha256":"5d54d0c0e44aae4b71730911322a5513ca457677b85b3f9ae6db6b4dc8cc6c3b"},"schema_version":"1.0"},"canonical_sha256":"05c4f9f742e47e66a2c321d3079d37990f8af89b65270d5b291c3f57db304617","source":{"kind":"arxiv","id":"2505.16234","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16234","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16234v2","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16234","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"AXCPT52C4R7G","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"AXCPT52C4R7GNIWD","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"AXCPT52C","created_at":"2026-07-05T11:19:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AXCPT52C4R7GNIWDEHJQPHJXTE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T05:08:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b3881fa668dfdb6b1aaa7805cd79a39df5c9fbb96d9d54f10f003287ad8a575","abstract_canon_sha256":"5d54d0c0e44aae4b71730911322a5513ca457677b85b3f9ae6db6b4dc8cc6c3b"},"schema_version":"1.0"},"canonical_sha256":"05c4f9f742e47e66a2c321d3079d37990f8af89b65270d5b291c3f57db304617","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:27.215955Z","signature_b64":"59PpM441KbrNm8MWePUbUwAxGE1NDuuasys1WuKfvUL8obShpi0hDhnOeKM+BQkq4YSQTSH1vklgpIfhGLK0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05c4f9f742e47e66a2c321d3079d37990f8af89b65270d5b291c3f57db304617","last_reissued_at":"2026-07-05T11:19:27.215507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:27.215507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16234","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jeRdTurVRVuUiK9RXtNP1/9WYQaUiFcmY0B8upQe+xTwnaO06xWKhNqQXynpquT88pppTexVrmjd/6yC2KtZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:54:20.303166Z"},"content_sha256":"db97adc277e4d89ab246a6cca468478fdea778b49d8b5805f23694809c683589","schema_version":"1.0","event_id":"sha256:db97adc277e4d89ab246a6cca468478fdea778b49d8b5805f23694809c683589"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AXCPT52C4R7GNIWDEHJQPHJXTE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LIFEBench: Evaluating Length Instruction Following in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ge Zhang, Junfeng Fang, Kun Wang, Lingjuan Lyu, Li Sun, Rui Wang, Sen Su, Wei Zhang, Xavier Li, Yang Liu, Yuanhe Zhang, Zhenhong Zhou","submitted_at":"2025-05-22T05:08:27Z","abstract_excerpt":"While large language models (LLMs) can solve PhD-level reasoning problems over long context inputs, they still struggle with a seemingly simpler task: following explicit length instructions-e.g., write a 10,000-word novel. Additionally, models often generate far too short outputs, terminate prematurely, or even refuse the request. Existing benchmarks focus primarily on evaluating generations quality, but often overlook whether the generations meet length constraints. To this end, we introduce Length Instruction Following Evaluation Benchmark (LIFEBench) to comprehensively evaluate LLMs' abilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16234","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/2505.16234/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":"2026-07-05T11:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UBKITM1gJCHQClrJRO91X8LwXO0tclg2v8g5TXLvqKZnKhX0Dwf+qBetpSYRFrnHS3VliNNJbV88WnOTCxJNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:54:20.303713Z"},"content_sha256":"548cf837a964394b1e4ce726712f9db5ddff6a83690022b1facfcac05526d9b7","schema_version":"1.0","event_id":"sha256:548cf837a964394b1e4ce726712f9db5ddff6a83690022b1facfcac05526d9b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AXCPT52C4R7GNIWDEHJQPHJXTE/bundle.json","state_url":"https://pith.science/pith/AXCPT52C4R7GNIWDEHJQPHJXTE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AXCPT52C4R7GNIWDEHJQPHJXTE/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":"2026-08-09T04:54:20Z","links":{"resolver":"https://pith.science/pith/AXCPT52C4R7GNIWDEHJQPHJXTE","bundle":"https://pith.science/pith/AXCPT52C4R7GNIWDEHJQPHJXTE/bundle.json","state":"https://pith.science/pith/AXCPT52C4R7GNIWDEHJQPHJXTE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AXCPT52C4R7GNIWDEHJQPHJXTE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AXCPT52C4R7GNIWDEHJQPHJXTE","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":"5d54d0c0e44aae4b71730911322a5513ca457677b85b3f9ae6db6b4dc8cc6c3b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T05:08:27Z","title_canon_sha256":"0b3881fa668dfdb6b1aaa7805cd79a39df5c9fbb96d9d54f10f003287ad8a575"},"schema_version":"1.0","source":{"id":"2505.16234","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16234","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16234v2","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16234","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"AXCPT52C4R7G","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"AXCPT52C4R7GNIWD","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"AXCPT52C","created_at":"2026-07-05T11:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:548cf837a964394b1e4ce726712f9db5ddff6a83690022b1facfcac05526d9b7","target":"graph","created_at":"2026-07-05T11:19:27Z","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/2505.16234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) can solve PhD-level reasoning problems over long context inputs, they still struggle with a seemingly simpler task: following explicit length instructions-e.g., write a 10,000-word novel. Additionally, models often generate far too short outputs, terminate prematurely, or even refuse the request. Existing benchmarks focus primarily on evaluating generations quality, but often overlook whether the generations meet length constraints. To this end, we introduce Length Instruction Following Evaluation Benchmark (LIFEBench) to comprehensively evaluate LLMs' abilit","authors_text":"Ge Zhang, Junfeng Fang, Kun Wang, Lingjuan Lyu, Li Sun, Rui Wang, Sen Su, Wei Zhang, Xavier Li, Yang Liu, Yuanhe Zhang, Zhenhong Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T05:08:27Z","title":"LIFEBench: Evaluating Length Instruction Following in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16234","kind":"arxiv","version":2},"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:db97adc277e4d89ab246a6cca468478fdea778b49d8b5805f23694809c683589","target":"record","created_at":"2026-07-05T11:19:27Z","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":"5d54d0c0e44aae4b71730911322a5513ca457677b85b3f9ae6db6b4dc8cc6c3b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T05:08:27Z","title_canon_sha256":"0b3881fa668dfdb6b1aaa7805cd79a39df5c9fbb96d9d54f10f003287ad8a575"},"schema_version":"1.0","source":{"id":"2505.16234","kind":"arxiv","version":2}},"canonical_sha256":"05c4f9f742e47e66a2c321d3079d37990f8af89b65270d5b291c3f57db304617","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05c4f9f742e47e66a2c321d3079d37990f8af89b65270d5b291c3f57db304617","first_computed_at":"2026-07-05T11:19:27.215507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:27.215507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"59PpM441KbrNm8MWePUbUwAxGE1NDuuasys1WuKfvUL8obShpi0hDhnOeKM+BQkq4YSQTSH1vklgpIfhGLK0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:27.215955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16234","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db97adc277e4d89ab246a6cca468478fdea778b49d8b5805f23694809c683589","sha256:548cf837a964394b1e4ce726712f9db5ddff6a83690022b1facfcac05526d9b7"],"state_sha256":"8fe94517851c4a400286068fe80a0469feb62a4bcace9f2529cf16cb14293e20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XotXyIX1PPuxEUSV/p+I9AkPQGBoMmD90DYfR9QouxQkIIL3uHKTM1SWj+BEsXybTsxEZ8XcXyh1Ed0jq7bTBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:54:20.307856Z","bundle_sha256":"f4a0dbbe66573451727842923eb952de5340efcf226ee272f8e8cd81b3687a3f"}}