{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3QDUQG67TXJJXK443CDQBJHEWP","short_pith_number":"pith:3QDUQG67","canonical_record":{"source":{"id":"2502.08745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T19:35:28Z","cross_cats_sorted":[],"title_canon_sha256":"a3458f582dca3916e100d24b19d970e0addbb7459fca88537f8e0d35608c96d7","abstract_canon_sha256":"6151f7390b2670bebf8c40e63107ff92964793092027baf094fb31ed640dad3d"},"schema_version":"1.0"},"canonical_sha256":"dc07481bdf9dd29bab9cd88700a4e4b3eea19bf797d0719b25ec944a23e62883","source":{"kind":"arxiv","id":"2502.08745","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08745","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08745v2","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08745","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"pith_short_12","alias_value":"3QDUQG67TXJJ","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"pith_short_16","alias_value":"3QDUQG67TXJJXK44","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"pith_short_8","alias_value":"3QDUQG67","created_at":"2026-07-05T10:39:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3QDUQG67TXJJXK443CDQBJHEWP","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T19:35:28Z","cross_cats_sorted":[],"title_canon_sha256":"a3458f582dca3916e100d24b19d970e0addbb7459fca88537f8e0d35608c96d7","abstract_canon_sha256":"6151f7390b2670bebf8c40e63107ff92964793092027baf094fb31ed640dad3d"},"schema_version":"1.0"},"canonical_sha256":"dc07481bdf9dd29bab9cd88700a4e4b3eea19bf797d0719b25ec944a23e62883","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:47.245897Z","signature_b64":"nU+3ZeVVyIOUfWESsMubkQ9tni1gusd3YvmnP+NpG91VSF4MK38qJB7k31kLnWK3wS9rPyNqCRFylqCNCvUaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc07481bdf9dd29bab9cd88700a4e4b3eea19bf797d0719b25ec944a23e62883","last_reissued_at":"2026-07-05T10:39:47.244931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:47.244931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08745","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":"2026-07-05T10:39:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QDNpIAwEyzAeKCsRywVShkr2Krqp/0TuMUvUxGFsWt2s4IOumehdTitIUvM20U2EMXYOghYQgs1/xJZNi51bAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:10:53.408234Z"},"content_sha256":"91908fa47687f06c33f92b2d036f588c77fe0edbdbf924e2fe43a08a5ef2031e","schema_version":"1.0","event_id":"sha256:91908fa47687f06c33f92b2d036f588c77fe0edbdbf924e2fe43a08a5ef2031e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3QDUQG67TXJJXK443CDQBJHEWP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IHEval: Evaluating Language Models on Following the Instruction Hierarchy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Yin, Haodong Wang, Haoming Jiang, Meng Jiang, Qingyu Yin, Shiyang Li, Xianfeng Tang, Xin Liu, Yichuan Li, Yifan Gao, Zhaoxuan Tan, Zheng Li, Zhihan Zhang, Zixuan Zhang","submitted_at":"2025-02-12T19:35:28Z","abstract_excerpt":"The instruction hierarchy, which establishes a priority order from system messages to user messages, conversation history, and tool outputs, is essential for ensuring consistent and safe behavior in language models (LMs). Despite its importance, this topic receives limited attention, and there is a lack of comprehensive benchmarks for evaluating models' ability to follow the instruction hierarchy. We bridge this gap by introducing IHEval, a novel benchmark comprising 3,538 examples across nine tasks, covering cases where instructions in different priorities either align or conflict. Our evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08745","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/2502.08745/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":"2026-07-05T10:39:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p/7fmQkCDKH74gGGH1EnwLGBiP/DAbxRuuiLzSCd2cNJXVnNmkT00YEham5g4LvqlIoLIiBXJf7DbbkwdF5tCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:10:53.408856Z"},"content_sha256":"421f0da0f260162e3c9aabc458e14a2fa1d745b811df49b3b618cc7abc6a3d41","schema_version":"1.0","event_id":"sha256:421f0da0f260162e3c9aabc458e14a2fa1d745b811df49b3b618cc7abc6a3d41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3QDUQG67TXJJXK443CDQBJHEWP/bundle.json","state_url":"https://pith.science/pith/3QDUQG67TXJJXK443CDQBJHEWP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3QDUQG67TXJJXK443CDQBJHEWP/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":"2026-08-03T16:10:53Z","links":{"resolver":"https://pith.science/pith/3QDUQG67TXJJXK443CDQBJHEWP","bundle":"https://pith.science/pith/3QDUQG67TXJJXK443CDQBJHEWP/bundle.json","state":"https://pith.science/pith/3QDUQG67TXJJXK443CDQBJHEWP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3QDUQG67TXJJXK443CDQBJHEWP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3QDUQG67TXJJXK443CDQBJHEWP","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":"6151f7390b2670bebf8c40e63107ff92964793092027baf094fb31ed640dad3d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T19:35:28Z","title_canon_sha256":"a3458f582dca3916e100d24b19d970e0addbb7459fca88537f8e0d35608c96d7"},"schema_version":"1.0","source":{"id":"2502.08745","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08745","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08745v2","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08745","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"pith_short_12","alias_value":"3QDUQG67TXJJ","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"pith_short_16","alias_value":"3QDUQG67TXJJXK44","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"pith_short_8","alias_value":"3QDUQG67","created_at":"2026-07-05T10:39:47Z"}],"graph_snapshots":[{"event_id":"sha256:421f0da0f260162e3c9aabc458e14a2fa1d745b811df49b3b618cc7abc6a3d41","target":"graph","created_at":"2026-07-05T10:39:47Z","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/2502.08745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The instruction hierarchy, which establishes a priority order from system messages to user messages, conversation history, and tool outputs, is essential for ensuring consistent and safe behavior in language models (LMs). Despite its importance, this topic receives limited attention, and there is a lack of comprehensive benchmarks for evaluating models' ability to follow the instruction hierarchy. We bridge this gap by introducing IHEval, a novel benchmark comprising 3,538 examples across nine tasks, covering cases where instructions in different priorities either align or conflict. Our evalua","authors_text":"Bing Yin, Haodong Wang, Haoming Jiang, Meng Jiang, Qingyu Yin, Shiyang Li, Xianfeng Tang, Xin Liu, Yichuan Li, Yifan Gao, Zhaoxuan Tan, Zheng Li, Zhihan Zhang, Zixuan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T19:35:28Z","title":"IHEval: Evaluating Language Models on Following the Instruction Hierarchy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08745","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":"sha256:91908fa47687f06c33f92b2d036f588c77fe0edbdbf924e2fe43a08a5ef2031e","target":"record","created_at":"2026-07-05T10:39:47Z","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":"6151f7390b2670bebf8c40e63107ff92964793092027baf094fb31ed640dad3d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T19:35:28Z","title_canon_sha256":"a3458f582dca3916e100d24b19d970e0addbb7459fca88537f8e0d35608c96d7"},"schema_version":"1.0","source":{"id":"2502.08745","kind":"arxiv","version":2}},"canonical_sha256":"dc07481bdf9dd29bab9cd88700a4e4b3eea19bf797d0719b25ec944a23e62883","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc07481bdf9dd29bab9cd88700a4e4b3eea19bf797d0719b25ec944a23e62883","first_computed_at":"2026-07-05T10:39:47.244931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:47.244931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nU+3ZeVVyIOUfWESsMubkQ9tni1gusd3YvmnP+NpG91VSF4MK38qJB7k31kLnWK3wS9rPyNqCRFylqCNCvUaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:47.245897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08745","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91908fa47687f06c33f92b2d036f588c77fe0edbdbf924e2fe43a08a5ef2031e","sha256:421f0da0f260162e3c9aabc458e14a2fa1d745b811df49b3b618cc7abc6a3d41"],"state_sha256":"b59700a483aabaec57ae507a76b181431f27453899b338ba61091477176db0cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EiBpZXTfO/eUZzV/sNXI3wZEK31TrtfeB6mqq6b8sZLsztA6vZLdqNWIQARU77afHeiokZbDp6IPEyjmgpf1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:10:53.412685Z","bundle_sha256":"16742212b730d83a86c6dda7e535a454cb4a78feb741b9bd72608015a567bada"}}