{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GWYACGRDUFECP5OSY47EICBORG","short_pith_number":"pith:GWYACGRD","canonical_record":{"source":{"id":"2411.15560","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-23T13:34:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9a03824001c3bb73b29e0dab38216c0145b12a1d47847d2e3e7e31545c3b3a2","abstract_canon_sha256":"935ab68c455553e781b78b4d4994ae7b16dd225d27027d78f0f79c14c36ffaf7"},"schema_version":"1.0"},"canonical_sha256":"35b0011a23a14827f5d2c73e44082e89a17d6f2cf0892ee69d28db857bc5fe16","source":{"kind":"arxiv","id":"2411.15560","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15560","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15560v2","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15560","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"pith_short_12","alias_value":"GWYACGRDUFEC","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"pith_short_16","alias_value":"GWYACGRDUFECP5OS","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"pith_short_8","alias_value":"GWYACGRD","created_at":"2026-07-05T09:40:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GWYACGRDUFECP5OSY47EICBORG","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15560","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-23T13:34:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9a03824001c3bb73b29e0dab38216c0145b12a1d47847d2e3e7e31545c3b3a2","abstract_canon_sha256":"935ab68c455553e781b78b4d4994ae7b16dd225d27027d78f0f79c14c36ffaf7"},"schema_version":"1.0"},"canonical_sha256":"35b0011a23a14827f5d2c73e44082e89a17d6f2cf0892ee69d28db857bc5fe16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:21.698538Z","signature_b64":"xpovHAPqtPe3HhCdp+GIxW9iT6DtEoqBk0JPmhbYwfixv+a9b2d+nM+AHihO9tVlTXfImnNNt7X4lWwpvMsdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35b0011a23a14827f5d2c73e44082e89a17d6f2cf0892ee69d28db857bc5fe16","last_reissued_at":"2026-07-05T09:40:21.698011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:21.698011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15560","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":"2026-07-05T09:40:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9PhvJDbFCryYHeVWnX8ixsen+R/o4yOq5wmpktZM/vPKL5budADVKgVG1KKB6Zbb6Owk9LoBBPse/62/BAiyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:45:07.334921Z"},"content_sha256":"f18166d8bbbb48db01b102a4f5307720f551155b538dba91c677a35e17f79cc3","schema_version":"1.0","event_id":"sha256:f18166d8bbbb48db01b102a4f5307720f551155b538dba91c677a35e17f79cc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GWYACGRDUFECP5OSY47EICBORG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do LLMs Agree on the Creativity Evaluation of Alternative Uses?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Abdullah Al Rabeyah, Fabr\\'icio G\\'oes, Marco Volpe, Talles Medeiros","submitted_at":"2024-11-23T13:34:50Z","abstract_excerpt":"This paper investigates whether large language models (LLMs) show agreement in assessing creativity in responses to the Alternative Uses Test (AUT). While LLMs are increasingly used to evaluate creative content, previous studies have primarily focused on a single model assessing responses generated by the same model or humans. This paper explores whether LLMs can impartially and accurately evaluate creativity in outputs generated by both themselves and other models. Using an oracle benchmark set of AUT responses, categorized by creativity level (common, creative, and highly creative), we exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15560","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/2411.15560/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":"2026-07-05T09:40:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l5LrFUH7imU44XLjiFMQ52lrK1CbLuEzHHRuSbkoTjA/9qP2hzohYW1G7h2TsslDxW6rDXUc2UMnORZUUiGUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:45:07.335513Z"},"content_sha256":"3111cd62b9a86692005fa11eecb003c67d63f300cd537fde977b877f1cc86f14","schema_version":"1.0","event_id":"sha256:3111cd62b9a86692005fa11eecb003c67d63f300cd537fde977b877f1cc86f14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GWYACGRDUFECP5OSY47EICBORG/bundle.json","state_url":"https://pith.science/pith/GWYACGRDUFECP5OSY47EICBORG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GWYACGRDUFECP5OSY47EICBORG/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":"2026-08-10T12:45:07Z","links":{"resolver":"https://pith.science/pith/GWYACGRDUFECP5OSY47EICBORG","bundle":"https://pith.science/pith/GWYACGRDUFECP5OSY47EICBORG/bundle.json","state":"https://pith.science/pith/GWYACGRDUFECP5OSY47EICBORG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GWYACGRDUFECP5OSY47EICBORG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GWYACGRDUFECP5OSY47EICBORG","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":"935ab68c455553e781b78b4d4994ae7b16dd225d27027d78f0f79c14c36ffaf7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-23T13:34:50Z","title_canon_sha256":"e9a03824001c3bb73b29e0dab38216c0145b12a1d47847d2e3e7e31545c3b3a2"},"schema_version":"1.0","source":{"id":"2411.15560","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15560","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15560v2","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15560","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"pith_short_12","alias_value":"GWYACGRDUFEC","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"pith_short_16","alias_value":"GWYACGRDUFECP5OS","created_at":"2026-07-05T09:40:21Z"},{"alias_kind":"pith_short_8","alias_value":"GWYACGRD","created_at":"2026-07-05T09:40:21Z"}],"graph_snapshots":[{"event_id":"sha256:3111cd62b9a86692005fa11eecb003c67d63f300cd537fde977b877f1cc86f14","target":"graph","created_at":"2026-07-05T09:40:21Z","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/2411.15560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates whether large language models (LLMs) show agreement in assessing creativity in responses to the Alternative Uses Test (AUT). While LLMs are increasingly used to evaluate creative content, previous studies have primarily focused on a single model assessing responses generated by the same model or humans. This paper explores whether LLMs can impartially and accurately evaluate creativity in outputs generated by both themselves and other models. Using an oracle benchmark set of AUT responses, categorized by creativity level (common, creative, and highly creative), we exper","authors_text":"Abdullah Al Rabeyah, Fabr\\'icio G\\'oes, Marco Volpe, Talles Medeiros","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-23T13:34:50Z","title":"Do LLMs Agree on the Creativity Evaluation of Alternative Uses?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15560","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:f18166d8bbbb48db01b102a4f5307720f551155b538dba91c677a35e17f79cc3","target":"record","created_at":"2026-07-05T09:40:21Z","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":"935ab68c455553e781b78b4d4994ae7b16dd225d27027d78f0f79c14c36ffaf7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-23T13:34:50Z","title_canon_sha256":"e9a03824001c3bb73b29e0dab38216c0145b12a1d47847d2e3e7e31545c3b3a2"},"schema_version":"1.0","source":{"id":"2411.15560","kind":"arxiv","version":2}},"canonical_sha256":"35b0011a23a14827f5d2c73e44082e89a17d6f2cf0892ee69d28db857bc5fe16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35b0011a23a14827f5d2c73e44082e89a17d6f2cf0892ee69d28db857bc5fe16","first_computed_at":"2026-07-05T09:40:21.698011Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:21.698011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xpovHAPqtPe3HhCdp+GIxW9iT6DtEoqBk0JPmhbYwfixv+a9b2d+nM+AHihO9tVlTXfImnNNt7X4lWwpvMsdAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:21.698538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15560","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f18166d8bbbb48db01b102a4f5307720f551155b538dba91c677a35e17f79cc3","sha256:3111cd62b9a86692005fa11eecb003c67d63f300cd537fde977b877f1cc86f14"],"state_sha256":"996803d08ff47c484f359edcacabf78940035324211e823bf484448012fa85ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+TayyBxiiGkYh2ehhxgst8MorqDsyXst2DjiCoXeuDOzhEYQLbe5n4UJwh+cXJ2lmnLExLHSaC4QerArNpnBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:45:07.340781Z","bundle_sha256":"4fa931949e1e8e771d7f3122f87952db9ed0ed35491e312be1c703da0b574dc8"}}