{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LKWS5HYHMCOWKESEIZAFHQMAX2","short_pith_number":"pith:LKWS5HYH","canonical_record":{"source":{"id":"2505.20097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:07:30Z","cross_cats_sorted":[],"title_canon_sha256":"be8b27a7144ccc265ce6373a9935ed4f8aab62f026b9c7ffd29142ea42d8caeb","abstract_canon_sha256":"306c2c3eea06c5ac9a02d5036e4372a12685afdb2d168cc7b7207a61dddbc6bb"},"schema_version":"1.0"},"canonical_sha256":"5aad2e9f07609d651244464053c180be8a91a1cd079ebaeab679c156b8bab1d6","source":{"kind":"arxiv","id":"2505.20097","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20097","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20097v1","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20097","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"pith_short_12","alias_value":"LKWS5HYHMCOW","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"pith_short_16","alias_value":"LKWS5HYHMCOWKESE","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"pith_short_8","alias_value":"LKWS5HYH","created_at":"2026-07-05T11:09:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LKWS5HYHMCOWKESEIZAFHQMAX2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:07:30Z","cross_cats_sorted":[],"title_canon_sha256":"be8b27a7144ccc265ce6373a9935ed4f8aab62f026b9c7ffd29142ea42d8caeb","abstract_canon_sha256":"306c2c3eea06c5ac9a02d5036e4372a12685afdb2d168cc7b7207a61dddbc6bb"},"schema_version":"1.0"},"canonical_sha256":"5aad2e9f07609d651244464053c180be8a91a1cd079ebaeab679c156b8bab1d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:52.669084Z","signature_b64":"gsW+gNbBRjlxxD63EndHkFDRKj5XZTKuJ6fENpwSY2r70QD4Y7X+a5J9ZE8Wwv7S7zLYbOEl+kuc4nKtgaseAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aad2e9f07609d651244464053c180be8a91a1cd079ebaeab679c156b8bab1d6","last_reissued_at":"2026-07-05T11:09:52.668588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:52.668588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20097","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":"2026-07-05T11:09:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aRSYOBPxij3hoh8iBG2CVHNhOzqnNVYhZFHaE2HtuJoSS+BSpVy+voCFDGv0yfvwKzANCqfVa2+/rgphZaILBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:44:49.186686Z"},"content_sha256":"e3699a993db4a442563a64f269f49a078dd585505a1781b7eae577fd64a3276c","schema_version":"1.0","event_id":"sha256:e3699a993db4a442563a64f269f49a078dd585505a1781b7eae577fd64a3276c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LKWS5HYHMCOWKESEIZAFHQMAX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"S2LPP: Small-to-Large Prompt Prediction across LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liang Cheng, Mark Steedman, Tianyi Li, Zhaowei Wang","submitted_at":"2025-05-26T15:07:30Z","abstract_excerpt":"The performance of pre-trained Large Language Models (LLMs) is often sensitive to nuances in prompt templates, requiring careful prompt engineering, adding costs in terms of computing and human effort. In this study, we present experiments encompassing multiple LLMs variants of varying sizes aimed at probing their preference with different prompts. Through experiments on Question Answering, we show prompt preference consistency across LLMs of different sizes. We also show that this consistency extends to other tasks, such as Natural Language Inference. Utilizing this consistency, we propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20097","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/2505.20097/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":"2026-07-05T11:09:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cw5EWbaFzmSGExJvPTTF2QLb0fzDOQpsAc/HrPYF1nZCVDeAJAdE/1kCzn6KFgEcbLlyTCIEXFeAlK7hEwDoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:44:49.187251Z"},"content_sha256":"5f8068fa0dfe1790b6167cd7a289aceffe0bbd0dc151dacb4e848d78dc193f18","schema_version":"1.0","event_id":"sha256:5f8068fa0dfe1790b6167cd7a289aceffe0bbd0dc151dacb4e848d78dc193f18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKWS5HYHMCOWKESEIZAFHQMAX2/bundle.json","state_url":"https://pith.science/pith/LKWS5HYHMCOWKESEIZAFHQMAX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKWS5HYHMCOWKESEIZAFHQMAX2/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":"2026-08-09T08:44:49Z","links":{"resolver":"https://pith.science/pith/LKWS5HYHMCOWKESEIZAFHQMAX2","bundle":"https://pith.science/pith/LKWS5HYHMCOWKESEIZAFHQMAX2/bundle.json","state":"https://pith.science/pith/LKWS5HYHMCOWKESEIZAFHQMAX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKWS5HYHMCOWKESEIZAFHQMAX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LKWS5HYHMCOWKESEIZAFHQMAX2","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":"306c2c3eea06c5ac9a02d5036e4372a12685afdb2d168cc7b7207a61dddbc6bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:07:30Z","title_canon_sha256":"be8b27a7144ccc265ce6373a9935ed4f8aab62f026b9c7ffd29142ea42d8caeb"},"schema_version":"1.0","source":{"id":"2505.20097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20097","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20097v1","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20097","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"pith_short_12","alias_value":"LKWS5HYHMCOW","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"pith_short_16","alias_value":"LKWS5HYHMCOWKESE","created_at":"2026-07-05T11:09:52Z"},{"alias_kind":"pith_short_8","alias_value":"LKWS5HYH","created_at":"2026-07-05T11:09:52Z"}],"graph_snapshots":[{"event_id":"sha256:5f8068fa0dfe1790b6167cd7a289aceffe0bbd0dc151dacb4e848d78dc193f18","target":"graph","created_at":"2026-07-05T11:09:52Z","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/2505.20097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of pre-trained Large Language Models (LLMs) is often sensitive to nuances in prompt templates, requiring careful prompt engineering, adding costs in terms of computing and human effort. In this study, we present experiments encompassing multiple LLMs variants of varying sizes aimed at probing their preference with different prompts. Through experiments on Question Answering, we show prompt preference consistency across LLMs of different sizes. We also show that this consistency extends to other tasks, such as Natural Language Inference. Utilizing this consistency, we propose a ","authors_text":"Liang Cheng, Mark Steedman, Tianyi Li, Zhaowei Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:07:30Z","title":"S2LPP: Small-to-Large Prompt Prediction across LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20097","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:e3699a993db4a442563a64f269f49a078dd585505a1781b7eae577fd64a3276c","target":"record","created_at":"2026-07-05T11:09:52Z","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":"306c2c3eea06c5ac9a02d5036e4372a12685afdb2d168cc7b7207a61dddbc6bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T15:07:30Z","title_canon_sha256":"be8b27a7144ccc265ce6373a9935ed4f8aab62f026b9c7ffd29142ea42d8caeb"},"schema_version":"1.0","source":{"id":"2505.20097","kind":"arxiv","version":1}},"canonical_sha256":"5aad2e9f07609d651244464053c180be8a91a1cd079ebaeab679c156b8bab1d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5aad2e9f07609d651244464053c180be8a91a1cd079ebaeab679c156b8bab1d6","first_computed_at":"2026-07-05T11:09:52.668588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:52.668588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gsW+gNbBRjlxxD63EndHkFDRKj5XZTKuJ6fENpwSY2r70QD4Y7X+a5J9ZE8Wwv7S7zLYbOEl+kuc4nKtgaseAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:52.669084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3699a993db4a442563a64f269f49a078dd585505a1781b7eae577fd64a3276c","sha256:5f8068fa0dfe1790b6167cd7a289aceffe0bbd0dc151dacb4e848d78dc193f18"],"state_sha256":"c4a25a0dd8019e0a9f6c9d8c5d5aeb84930af3b84a1f233f068e622b07f4079c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mf1BAOeOwxoQbAznz35ZXDQIba09rvIG2Kbrmsim6LsWkRdTY3y4EKdOPUR4GRd+WYzpJX7VdQ5ud4OhYMorCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:44:49.192216Z","bundle_sha256":"0caa7bb9fc8800a94b9ed8716c8439d467ca4a90b91d26db3e47777b6d91c730"}}