{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6KUUS66NZUSUED2LUSETONR5CM","short_pith_number":"pith:6KUUS66N","canonical_record":{"source":{"id":"2606.24381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T10:13:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"79127a250cb24b6d26472e7a8fb253cbe44b82e480fb8462014c6845023bb422","abstract_canon_sha256":"1a5a9fee48b3dc335b61e04fb91f2a6b46dda6eb21167e63d6ea597a235c908f"},"schema_version":"1.0"},"canonical_sha256":"f2a9497bcdcd25420f4ba48937363d13253b00bb41f8c667bb2257681f1df0ff","source":{"kind":"arxiv","id":"2606.24381","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24381","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24381v1","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24381","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"6KUUS66NZUSU","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"6KUUS66NZUSUED2L","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"6KUUS66N","created_at":"2026-06-24T01:15:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6KUUS66NZUSUED2LUSETONR5CM","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T10:13:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"79127a250cb24b6d26472e7a8fb253cbe44b82e480fb8462014c6845023bb422","abstract_canon_sha256":"1a5a9fee48b3dc335b61e04fb91f2a6b46dda6eb21167e63d6ea597a235c908f"},"schema_version":"1.0"},"canonical_sha256":"f2a9497bcdcd25420f4ba48937363d13253b00bb41f8c667bb2257681f1df0ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:29.031776Z","signature_b64":"TMz/Fp0lictv8PT7J7QovK6QjB3hzfKf9N15tt/aQCN2lIsRI1cJJScfh9TAsxY22oFZKTrhyCU/rFkVA/DhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2a9497bcdcd25420f4ba48937363d13253b00bb41f8c667bb2257681f1df0ff","last_reissued_at":"2026-06-24T01:15:29.031435Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:29.031435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24381","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":"2026-06-24T01:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s23VPjiH20FSl00BmvGf2o4OSAg4uH6H9DOgfIij4vLfmVmUtCSb7WMW8ru3SQLf/WEbHwi/sub91EzbgucTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:28:22.851098Z"},"content_sha256":"7211d3d239accb4065e8906048a572cd5e777bbccab6fdd291890c66a93f88c2","schema_version":"1.0","event_id":"sha256:7211d3d239accb4065e8906048a572cd5e777bbccab6fdd291890c66a93f88c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6KUUS66NZUSUED2LUSETONR5CM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Stability of Prompt Ranking in Large Language Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuanqi Shi, Hang Zhang, Lun Wang, Penghao Liang, Shaoshuai Du, Yixian Shen","submitted_at":"2026-06-23T10:13:47Z","abstract_excerpt":"Prompt-based interaction has become a dominant paradigm for using large language models (LLMs), where multiple candidate prompts are evaluated and the top-ranked one is selected for downstream use. This workflow implicitly assumes that prompt rankings are stable under minor variations in evaluation conditions. In this paper, we systematically study prompt ranking stability under common sources of variability, including random seeds and limited evaluation subsets. Across three open-weight LLMs and two benchmark tasks, we find that while overall rank correlations are often moderate to high, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24381","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/2606.24381/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":"2026-06-24T01:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fyx9u5qeKYAeefT/FySFfxYhBMV0TFEpTy3qRxLBRAHRjCtS9AZjhROAqdZwY3UgTSyo8JQsQNdEJsrdZLSmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:28:22.851517Z"},"content_sha256":"a9cf66bf9a4cf3023f682dfea1b07d96fc4a51565b9d43d838507f5f4e12e736","schema_version":"1.0","event_id":"sha256:a9cf66bf9a4cf3023f682dfea1b07d96fc4a51565b9d43d838507f5f4e12e736"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KUUS66NZUSUED2LUSETONR5CM/bundle.json","state_url":"https://pith.science/pith/6KUUS66NZUSUED2LUSETONR5CM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KUUS66NZUSUED2LUSETONR5CM/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":"2026-07-07T10:28:22Z","links":{"resolver":"https://pith.science/pith/6KUUS66NZUSUED2LUSETONR5CM","bundle":"https://pith.science/pith/6KUUS66NZUSUED2LUSETONR5CM/bundle.json","state":"https://pith.science/pith/6KUUS66NZUSUED2LUSETONR5CM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KUUS66NZUSUED2LUSETONR5CM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6KUUS66NZUSUED2LUSETONR5CM","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":"1a5a9fee48b3dc335b61e04fb91f2a6b46dda6eb21167e63d6ea597a235c908f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T10:13:47Z","title_canon_sha256":"79127a250cb24b6d26472e7a8fb253cbe44b82e480fb8462014c6845023bb422"},"schema_version":"1.0","source":{"id":"2606.24381","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24381","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24381v1","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24381","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"6KUUS66NZUSU","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"6KUUS66NZUSUED2L","created_at":"2026-06-24T01:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"6KUUS66N","created_at":"2026-06-24T01:15:29Z"}],"graph_snapshots":[{"event_id":"sha256:a9cf66bf9a4cf3023f682dfea1b07d96fc4a51565b9d43d838507f5f4e12e736","target":"graph","created_at":"2026-06-24T01:15:29Z","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/2606.24381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt-based interaction has become a dominant paradigm for using large language models (LLMs), where multiple candidate prompts are evaluated and the top-ranked one is selected for downstream use. This workflow implicitly assumes that prompt rankings are stable under minor variations in evaluation conditions. In this paper, we systematically study prompt ranking stability under common sources of variability, including random seeds and limited evaluation subsets. Across three open-weight LLMs and two benchmark tasks, we find that while overall rank correlations are often moderate to high, the ","authors_text":"Chuanqi Shi, Hang Zhang, Lun Wang, Penghao Liang, Shaoshuai Du, Yixian Shen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T10:13:47Z","title":"On the Stability of Prompt Ranking in Large Language Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24381","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":"sha256:7211d3d239accb4065e8906048a572cd5e777bbccab6fdd291890c66a93f88c2","target":"record","created_at":"2026-06-24T01:15:29Z","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":"1a5a9fee48b3dc335b61e04fb91f2a6b46dda6eb21167e63d6ea597a235c908f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T10:13:47Z","title_canon_sha256":"79127a250cb24b6d26472e7a8fb253cbe44b82e480fb8462014c6845023bb422"},"schema_version":"1.0","source":{"id":"2606.24381","kind":"arxiv","version":1}},"canonical_sha256":"f2a9497bcdcd25420f4ba48937363d13253b00bb41f8c667bb2257681f1df0ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2a9497bcdcd25420f4ba48937363d13253b00bb41f8c667bb2257681f1df0ff","first_computed_at":"2026-06-24T01:15:29.031435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:29.031435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TMz/Fp0lictv8PT7J7QovK6QjB3hzfKf9N15tt/aQCN2lIsRI1cJJScfh9TAsxY22oFZKTrhyCU/rFkVA/DhAw==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:29.031776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24381","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7211d3d239accb4065e8906048a572cd5e777bbccab6fdd291890c66a93f88c2","sha256:a9cf66bf9a4cf3023f682dfea1b07d96fc4a51565b9d43d838507f5f4e12e736"],"state_sha256":"fbf543d0fe12cc8a28dad4a70841ba4044f75daa975f198512db79552bbe791b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n5vpulzxdYpG5doR82RHwVcBHQXiD2kXadsT7MHq7OChA3VlNb5s1C3oMBhg0qG4j5eNNd9/v3o5eHHtBX+oBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:28:22.853506Z","bundle_sha256":"634074893896b082f18972923ddad946a6889d27f3434c5efe9c8cd13977f249"}}