{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UDBRALD47AVPPO7VVCRZIMAJJ2","short_pith_number":"pith:UDBRALD4","canonical_record":{"source":{"id":"2312.16337","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-26T21:17:46Z","cross_cats_sorted":[],"title_canon_sha256":"a2a9916ddf7f159d995b3298d1b7a6bf4d2c1d841b3e819d01f74926804deafa","abstract_canon_sha256":"a75965fed69f63b4451365a177e028ffdf54841eee76acae04b5ff5e36ad1dcf"},"schema_version":"1.0"},"canonical_sha256":"a0c3102c7cf82af7bbf5a8a39430094eab5c6b4f1f94524335f60d470f234bda","source":{"kind":"arxiv","id":"2312.16337","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16337","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16337v1","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16337","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"UDBRALD47AVP","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"UDBRALD47AVPPO7V","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"UDBRALD4","created_at":"2026-07-05T07:28:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UDBRALD47AVPPO7VVCRZIMAJJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2312.16337","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-26T21:17:46Z","cross_cats_sorted":[],"title_canon_sha256":"a2a9916ddf7f159d995b3298d1b7a6bf4d2c1d841b3e819d01f74926804deafa","abstract_canon_sha256":"a75965fed69f63b4451365a177e028ffdf54841eee76acae04b5ff5e36ad1dcf"},"schema_version":"1.0"},"canonical_sha256":"a0c3102c7cf82af7bbf5a8a39430094eab5c6b4f1f94524335f60d470f234bda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:59.342704Z","signature_b64":"ZqV/KHQxaeFJ7lCbNGxKLHNhP31cvVr3IxcZSxIfZxmKkkPYrpWq72UIvyMisgD9kQhePTNKTzNOi2X4X9N/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0c3102c7cf82af7bbf5a8a39430094eab5c6b4f1f94524335f60d470f234bda","last_reissued_at":"2026-07-05T07:28:59.342223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:59.342223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.16337","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":"2026-07-05T07:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xMsnT/zmhfoqOzjUpBl0JnPkaTdjY/6qbaCLS7Zn4WPSYKjJEB6YKyWS9oMagVJo54Hli2Ssf8U1nDM6104Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:51:26.596392Z"},"content_sha256":"9f432d12558161f31f437c2bcec0db607c45b164fddc631f8d08c820189f16ea","schema_version":"1.0","event_id":"sha256:9f432d12558161f31f437c2bcec0db607c45b164fddc631f8d08c820189f16ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UDBRALD47AVPPO7VVCRZIMAJJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task Contamination: Language Models May Not Be Few-Shot Anymore","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changmao Li, Jeffrey Flanigan","submitted_at":"2023-12-26T21:17:46Z","abstract_excerpt":"Large language models (LLMs) offer impressive performance in various zero-shot and few-shot tasks. However, their success in zero-shot and few-shot settings may be affected by task contamination, a potential limitation that has not been thoroughly examined. This paper investigates how zero-shot and few-shot performance of LLMs has changed chronologically over time. Utilizing GPT-3 series models and several other recent open-sourced LLMs, and controlling for dataset difficulty, we find that on datasets released before the LLM training data creation date, LLMs perform surprisingly better than on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16337","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/2312.16337/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":"2026-07-05T07:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T6st3+WKj1IHnJ8RCs6JG7p/n0tvxb+hFChxeppwEQ0PcNoQsAxAM2mfSt+8GV9agp+f02yLG8WSZfd+KiptBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:51:26.597010Z"},"content_sha256":"8193adc80ecf42a0231b340782fd715939d5920d60a2d2c0ac1d712462230b9e","schema_version":"1.0","event_id":"sha256:8193adc80ecf42a0231b340782fd715939d5920d60a2d2c0ac1d712462230b9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDBRALD47AVPPO7VVCRZIMAJJ2/bundle.json","state_url":"https://pith.science/pith/UDBRALD47AVPPO7VVCRZIMAJJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDBRALD47AVPPO7VVCRZIMAJJ2/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":"2026-08-14T00:51:26Z","links":{"resolver":"https://pith.science/pith/UDBRALD47AVPPO7VVCRZIMAJJ2","bundle":"https://pith.science/pith/UDBRALD47AVPPO7VVCRZIMAJJ2/bundle.json","state":"https://pith.science/pith/UDBRALD47AVPPO7VVCRZIMAJJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDBRALD47AVPPO7VVCRZIMAJJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UDBRALD47AVPPO7VVCRZIMAJJ2","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":"a75965fed69f63b4451365a177e028ffdf54841eee76acae04b5ff5e36ad1dcf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-26T21:17:46Z","title_canon_sha256":"a2a9916ddf7f159d995b3298d1b7a6bf4d2c1d841b3e819d01f74926804deafa"},"schema_version":"1.0","source":{"id":"2312.16337","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16337","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16337v1","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16337","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"UDBRALD47AVP","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"UDBRALD47AVPPO7V","created_at":"2026-07-05T07:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"UDBRALD4","created_at":"2026-07-05T07:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:8193adc80ecf42a0231b340782fd715939d5920d60a2d2c0ac1d712462230b9e","target":"graph","created_at":"2026-07-05T07:28:59Z","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/2312.16337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) offer impressive performance in various zero-shot and few-shot tasks. However, their success in zero-shot and few-shot settings may be affected by task contamination, a potential limitation that has not been thoroughly examined. This paper investigates how zero-shot and few-shot performance of LLMs has changed chronologically over time. Utilizing GPT-3 series models and several other recent open-sourced LLMs, and controlling for dataset difficulty, we find that on datasets released before the LLM training data creation date, LLMs perform surprisingly better than on","authors_text":"Changmao Li, Jeffrey Flanigan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-26T21:17:46Z","title":"Task Contamination: Language Models May Not Be Few-Shot Anymore"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16337","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":"sha256:9f432d12558161f31f437c2bcec0db607c45b164fddc631f8d08c820189f16ea","target":"record","created_at":"2026-07-05T07:28:59Z","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":"a75965fed69f63b4451365a177e028ffdf54841eee76acae04b5ff5e36ad1dcf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-26T21:17:46Z","title_canon_sha256":"a2a9916ddf7f159d995b3298d1b7a6bf4d2c1d841b3e819d01f74926804deafa"},"schema_version":"1.0","source":{"id":"2312.16337","kind":"arxiv","version":1}},"canonical_sha256":"a0c3102c7cf82af7bbf5a8a39430094eab5c6b4f1f94524335f60d470f234bda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0c3102c7cf82af7bbf5a8a39430094eab5c6b4f1f94524335f60d470f234bda","first_computed_at":"2026-07-05T07:28:59.342223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:59.342223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZqV/KHQxaeFJ7lCbNGxKLHNhP31cvVr3IxcZSxIfZxmKkkPYrpWq72UIvyMisgD9kQhePTNKTzNOi2X4X9N/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:59.342704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16337","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f432d12558161f31f437c2bcec0db607c45b164fddc631f8d08c820189f16ea","sha256:8193adc80ecf42a0231b340782fd715939d5920d60a2d2c0ac1d712462230b9e"],"state_sha256":"0c88c31172c519189a4eb8c22a8e56675914cedea9e87b901e81d3e4f7a60c5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"esBdfvILZSCCe2N+AdwtkmPpiJIGqlxFGa++Jkv4qupspL+BREu5Fc1TbORBzUROPIBjnL7yhWyzTq0wuxx8BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T00:51:26.611940Z","bundle_sha256":"8a11a0cf83216a149f3cfdbd0c82a7be7b6c4ef0a727c44bf2657ad720c4416f"}}