{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:63PMY45UWEKZNAZPOIZLJFZBOU","short_pith_number":"pith:63PMY45U","canonical_record":{"source":{"id":"2504.08300","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-11T07:04:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d84f198908c44edb0972a52a6491c39eb2aef41474fd732c7a6bf47d809900df","abstract_canon_sha256":"35147cbf37c6f35d85cd0ea24ca8dd4d71f48229852595a42a3d80a1e8f0376a"},"schema_version":"1.0"},"canonical_sha256":"f6decc73b4b11596832f7232b49721751124dbb68901389158025506ae17b373","source":{"kind":"arxiv","id":"2504.08300","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08300","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08300v5","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08300","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"63PMY45UWEKZ","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"63PMY45UWEKZNAZP","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"63PMY45U","created_at":"2026-05-20T00:00:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:63PMY45UWEKZNAZPOIZLJFZBOU","target":"record","payload":{"canonical_record":{"source":{"id":"2504.08300","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-11T07:04:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d84f198908c44edb0972a52a6491c39eb2aef41474fd732c7a6bf47d809900df","abstract_canon_sha256":"35147cbf37c6f35d85cd0ea24ca8dd4d71f48229852595a42a3d80a1e8f0376a"},"schema_version":"1.0"},"canonical_sha256":"f6decc73b4b11596832f7232b49721751124dbb68901389158025506ae17b373","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:19.151490Z","signature_b64":"JM2+lkuTUGF4EWJwpwq0GOQlvRYoN79XxGvtV+idsrGSNbzo5tPaaYtV4fQsZduTVI7v5lmOQX9tRi4Huy8yDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6decc73b4b11596832f7232b49721751124dbb68901389158025506ae17b373","last_reissued_at":"2026-05-20T00:00:19.150759Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:19.150759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.08300","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71xTaAo7+7ONMC7pwFGhc/t6QjhtFCTj4I1IlgAAR8ABNYJHaptaVD0ZRCxaqq6lWyze+xcOU+9JM9WZd/y/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:22:10.912104Z"},"content_sha256":"154ecbec06528afff3401da0d2a40d1bcd1fd84e191da742554117e48e63c6d3","schema_version":"1.0","event_id":"sha256:154ecbec06528afff3401da0d2a40d1bcd1fd84e191da742554117e48e63c6d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:63PMY45UWEKZNAZPOIZLJFZBOU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models Could Be Rote Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haochao Ying, Jian Wu, Renjun Hu, Wei Lin, Xing Shi, Yuyang Xu","submitted_at":"2025-04-11T07:04:44Z","abstract_excerpt":"Benchmark-based evaluation, e.g., multiple-choice questions (MCQs) and open-ended questions (OEQs), is widely used for evaluating Large Language Models (LLMs), yet their reliability is undermined by benchmark contamination. When pre-exposed to the testing benchmark during training, less capable LLMs have been found to achieve inflated performance, thereby yielding erroneous results in LLM evaluation. In this study, we reframe contamination as an inherent aspect of learning and seek to disentangle and expose genuine capability acquisition from superficial memorization in LLM evaluation. Followi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08300","kind":"arxiv","version":5},"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/2504.08300/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":"2026-05-20T00:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c1Es0YwUsxFThmAHW2Eje/apb8Pmlf6kAe1s9SoieALdWAc4umVGQ3KGUmgANolql8xgWM1ErkR1Osqw5nsBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:22:10.912842Z"},"content_sha256":"63289042f33218455ff022583cbd9290f95791bb04ecb410568e22deff0fe72e","schema_version":"1.0","event_id":"sha256:63289042f33218455ff022583cbd9290f95791bb04ecb410568e22deff0fe72e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/63PMY45UWEKZNAZPOIZLJFZBOU/bundle.json","state_url":"https://pith.science/pith/63PMY45UWEKZNAZPOIZLJFZBOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/63PMY45UWEKZNAZPOIZLJFZBOU/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":"2026-05-25T17:22:10Z","links":{"resolver":"https://pith.science/pith/63PMY45UWEKZNAZPOIZLJFZBOU","bundle":"https://pith.science/pith/63PMY45UWEKZNAZPOIZLJFZBOU/bundle.json","state":"https://pith.science/pith/63PMY45UWEKZNAZPOIZLJFZBOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/63PMY45UWEKZNAZPOIZLJFZBOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:63PMY45UWEKZNAZPOIZLJFZBOU","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":"35147cbf37c6f35d85cd0ea24ca8dd4d71f48229852595a42a3d80a1e8f0376a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-11T07:04:44Z","title_canon_sha256":"d84f198908c44edb0972a52a6491c39eb2aef41474fd732c7a6bf47d809900df"},"schema_version":"1.0","source":{"id":"2504.08300","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08300","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08300v5","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08300","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"63PMY45UWEKZ","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"63PMY45UWEKZNAZP","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"63PMY45U","created_at":"2026-05-20T00:00:19Z"}],"graph_snapshots":[{"event_id":"sha256:63289042f33218455ff022583cbd9290f95791bb04ecb410568e22deff0fe72e","target":"graph","created_at":"2026-05-20T00:00:19Z","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/2504.08300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark-based evaluation, e.g., multiple-choice questions (MCQs) and open-ended questions (OEQs), is widely used for evaluating Large Language Models (LLMs), yet their reliability is undermined by benchmark contamination. When pre-exposed to the testing benchmark during training, less capable LLMs have been found to achieve inflated performance, thereby yielding erroneous results in LLM evaluation. In this study, we reframe contamination as an inherent aspect of learning and seek to disentangle and expose genuine capability acquisition from superficial memorization in LLM evaluation. Followi","authors_text":"Haochao Ying, Jian Wu, Renjun Hu, Wei Lin, Xing Shi, Yuyang Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-11T07:04:44Z","title":"Large Language Models Could Be Rote Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08300","kind":"arxiv","version":5},"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":"sha256:154ecbec06528afff3401da0d2a40d1bcd1fd84e191da742554117e48e63c6d3","target":"record","created_at":"2026-05-20T00:00:19Z","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":"35147cbf37c6f35d85cd0ea24ca8dd4d71f48229852595a42a3d80a1e8f0376a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-11T07:04:44Z","title_canon_sha256":"d84f198908c44edb0972a52a6491c39eb2aef41474fd732c7a6bf47d809900df"},"schema_version":"1.0","source":{"id":"2504.08300","kind":"arxiv","version":5}},"canonical_sha256":"f6decc73b4b11596832f7232b49721751124dbb68901389158025506ae17b373","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6decc73b4b11596832f7232b49721751124dbb68901389158025506ae17b373","first_computed_at":"2026-05-20T00:00:19.150759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:19.150759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JM2+lkuTUGF4EWJwpwq0GOQlvRYoN79XxGvtV+idsrGSNbzo5tPaaYtV4fQsZduTVI7v5lmOQX9tRi4Huy8yDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:19.151490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08300","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:154ecbec06528afff3401da0d2a40d1bcd1fd84e191da742554117e48e63c6d3","sha256:63289042f33218455ff022583cbd9290f95791bb04ecb410568e22deff0fe72e"],"state_sha256":"40162f0226ce60898814eb2f5448d014379160883137f4cf8071661df4614dad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BIptHDTfOM7fdhrpasZeXrJgkp53sJs0nC0nO9Kn3hSdpGtF8LzsDZ+Z2XJyRAzb1VB5rc6tOCtTCXNL0TOACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:22:10.916286Z","bundle_sha256":"4e896b718a637038dcb88b4b926bd595060426e50047c3a70a3946a4954f4258"}}