{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MESO4A3UEIKGPUMXDR5SI52MWN","short_pith_number":"pith:MESO4A3U","canonical_record":{"source":{"id":"2509.13196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-16T16:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"4bd134d4913765052d886f1ba82ccf6791e59c86cf61db35661055574851bd2c","abstract_canon_sha256":"fe27444e42e2545cc6abe859c949c7f8712f9c3a6774aa475b0ba4d14a71e3fe"},"schema_version":"1.0"},"canonical_sha256":"6124ee0374221467d1971c7b24774cb35e2e2ad3a12f6671432e4646116be2ab","source":{"kind":"arxiv","id":"2509.13196","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.13196","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2509.13196v1","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.13196","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"MESO4A3UEIKG","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"MESO4A3UEIKGPUMX","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"MESO4A3U","created_at":"2026-06-03T01:05:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MESO4A3UEIKGPUMXDR5SI52MWN","target":"record","payload":{"canonical_record":{"source":{"id":"2509.13196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-16T16:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"4bd134d4913765052d886f1ba82ccf6791e59c86cf61db35661055574851bd2c","abstract_canon_sha256":"fe27444e42e2545cc6abe859c949c7f8712f9c3a6774aa475b0ba4d14a71e3fe"},"schema_version":"1.0"},"canonical_sha256":"6124ee0374221467d1971c7b24774cb35e2e2ad3a12f6671432e4646116be2ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:06.050975Z","signature_b64":"jdvQ9OqbhMh/aC6s2ZchtjhUimbPh/6ZozlrnmhRNQWu84xT0jKl4BihK3my6OunQf8LfQBMYQjPMmQsOB13Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6124ee0374221467d1971c7b24774cb35e2e2ad3a12f6671432e4646116be2ab","last_reissued_at":"2026-06-03T01:05:06.047439Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:06.047439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.13196","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":"2026-06-03T01:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Ssthmm/QFGvWjokgWJ2Ib4uVqItudfNA9b4n+AbK+Db8nOO4bcKUKzim3NKaJ/zLIhgns8PCbwlUQOI2oiWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:29:11.144473Z"},"content_sha256":"752ef69499c5a2ac8dc0f875edd51b7e1e760b7016152b0185274aa686c86511","schema_version":"1.0","event_id":"sha256:752ef69499c5a2ac8dc0f875edd51b7e1e760b7016152b0185274aa686c86511"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MESO4A3UEIKGPUMXDR5SI52MWN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Few-shot Dilemma: Over-prompting Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Koerner, Doruk Tuncel, Thomas Runkler, Yongjian Tang","submitted_at":"2025-09-16T16:00:06Z","abstract_excerpt":"Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we outline a prompting framework that leverages three standard few-shot selection methods - random sampling, semantic embedding, and TF-IDF vectors - and evaluate these methods across multiple LLMs, including GPT-4o, GPT-3.5-turbo, DeepSeek-V3, Gemma-3, LLaMA-3.1, LLaMA-3.2, and Mistral. Our experimental results reveal that incorporating excessive domain-speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.13196","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/2509.13196/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":"2026-06-03T01:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlwCO14aGWKT03DgT6///kU7fYaHP+s6QXpLJyXk7GRQDmrGqAdjDJoPhTfQ+i4PVr2oCdLzHhbuakFqXOByDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:29:11.145217Z"},"content_sha256":"5c7bbef7fbe1d97d7bfa515a12acf28301f42fba4e02ef2532736ad19659bd80","schema_version":"1.0","event_id":"sha256:5c7bbef7fbe1d97d7bfa515a12acf28301f42fba4e02ef2532736ad19659bd80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MESO4A3UEIKGPUMXDR5SI52MWN/bundle.json","state_url":"https://pith.science/pith/MESO4A3UEIKGPUMXDR5SI52MWN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MESO4A3UEIKGPUMXDR5SI52MWN/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":"2026-06-08T15:29:11Z","links":{"resolver":"https://pith.science/pith/MESO4A3UEIKGPUMXDR5SI52MWN","bundle":"https://pith.science/pith/MESO4A3UEIKGPUMXDR5SI52MWN/bundle.json","state":"https://pith.science/pith/MESO4A3UEIKGPUMXDR5SI52MWN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MESO4A3UEIKGPUMXDR5SI52MWN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MESO4A3UEIKGPUMXDR5SI52MWN","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":"fe27444e42e2545cc6abe859c949c7f8712f9c3a6774aa475b0ba4d14a71e3fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-16T16:00:06Z","title_canon_sha256":"4bd134d4913765052d886f1ba82ccf6791e59c86cf61db35661055574851bd2c"},"schema_version":"1.0","source":{"id":"2509.13196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.13196","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2509.13196v1","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.13196","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"MESO4A3UEIKG","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"MESO4A3UEIKGPUMX","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"MESO4A3U","created_at":"2026-06-03T01:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:5c7bbef7fbe1d97d7bfa515a12acf28301f42fba4e02ef2532736ad19659bd80","target":"graph","created_at":"2026-06-03T01:05:06Z","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/2509.13196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we outline a prompting framework that leverages three standard few-shot selection methods - random sampling, semantic embedding, and TF-IDF vectors - and evaluate these methods across multiple LLMs, including GPT-4o, GPT-3.5-turbo, DeepSeek-V3, Gemma-3, LLaMA-3.1, LLaMA-3.2, and Mistral. Our experimental results reveal that incorporating excessive domain-speci","authors_text":"Christian Koerner, Doruk Tuncel, Thomas Runkler, Yongjian Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-16T16:00:06Z","title":"The Few-shot Dilemma: Over-prompting Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.13196","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":"sha256:752ef69499c5a2ac8dc0f875edd51b7e1e760b7016152b0185274aa686c86511","target":"record","created_at":"2026-06-03T01:05:06Z","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":"fe27444e42e2545cc6abe859c949c7f8712f9c3a6774aa475b0ba4d14a71e3fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-16T16:00:06Z","title_canon_sha256":"4bd134d4913765052d886f1ba82ccf6791e59c86cf61db35661055574851bd2c"},"schema_version":"1.0","source":{"id":"2509.13196","kind":"arxiv","version":1}},"canonical_sha256":"6124ee0374221467d1971c7b24774cb35e2e2ad3a12f6671432e4646116be2ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6124ee0374221467d1971c7b24774cb35e2e2ad3a12f6671432e4646116be2ab","first_computed_at":"2026-06-03T01:05:06.047439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:06.047439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jdvQ9OqbhMh/aC6s2ZchtjhUimbPh/6ZozlrnmhRNQWu84xT0jKl4BihK3my6OunQf8LfQBMYQjPMmQsOB13Ag==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:06.050975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.13196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:752ef69499c5a2ac8dc0f875edd51b7e1e760b7016152b0185274aa686c86511","sha256:5c7bbef7fbe1d97d7bfa515a12acf28301f42fba4e02ef2532736ad19659bd80"],"state_sha256":"fb08b8a35b2a4494a2e7878330173e0f9318a3ed5ac48b79c45e5b2039d1b059"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AepUWGYXuuPgT5tTVSlS6NPO479K+ZBOr64CsqOAAbFaVfoOSMfXB2+YXPjs71ZVVw484bR6eTPXO9DxMSoOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T15:29:11.149171Z","bundle_sha256":"eaa213aa51239afd6c912847852b834516303eabccabad6ed1881cc708e82732"}}