{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ROQYYI6QCC42EYXUXWQRMTPHUY","short_pith_number":"pith:ROQYYI6Q","canonical_record":{"source":{"id":"2505.18485","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T03:19:36Z","cross_cats_sorted":[],"title_canon_sha256":"505029a1a1de94286f09f79aab61cbc2f58e1877af122ffc3de6e6ce0e796bb6","abstract_canon_sha256":"078a6e36411fa7da7e101f74edf95adb300054c22a96a886a591dce31fa09b00"},"schema_version":"1.0"},"canonical_sha256":"8ba18c23d010b9a262f4bda1164de7a6031ef1676f73b4f68c8b07594e0fa7e3","source":{"kind":"arxiv","id":"2505.18485","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18485","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18485v1","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18485","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"pith_short_12","alias_value":"ROQYYI6QCC42","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"pith_short_16","alias_value":"ROQYYI6QCC42EYXU","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"pith_short_8","alias_value":"ROQYYI6Q","created_at":"2026-07-05T11:08:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ROQYYI6QCC42EYXUXWQRMTPHUY","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18485","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T03:19:36Z","cross_cats_sorted":[],"title_canon_sha256":"505029a1a1de94286f09f79aab61cbc2f58e1877af122ffc3de6e6ce0e796bb6","abstract_canon_sha256":"078a6e36411fa7da7e101f74edf95adb300054c22a96a886a591dce31fa09b00"},"schema_version":"1.0"},"canonical_sha256":"8ba18c23d010b9a262f4bda1164de7a6031ef1676f73b4f68c8b07594e0fa7e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:47.149117Z","signature_b64":"kDBpnuzXXgNJqi+PavPzRHAi8edr7G8R2Jn5z7ZDTrKaTV4xAj83u7SE9heF68PyUyxGWa0domJdT4v8ifiQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ba18c23d010b9a262f4bda1164de7a6031ef1676f73b4f68c8b07594e0fa7e3","last_reissued_at":"2026-07-05T11:08:47.148692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:47.148692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18485","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":"2026-07-05T11:08:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sPL0zqwniydVeeidDZwxzOMgYesIjx7pzwLkhe0NkwSJAtQnheepKO4mfd9B15frBhBH/GQcQtlN1Ea5QfXqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T14:41:43.136526Z"},"content_sha256":"2cb0989e7afdb3b33cba6ffd435fbb7a04ceb76ecf9b54496b79c5edd61e2c5d","schema_version":"1.0","event_id":"sha256:2cb0989e7afdb3b33cba6ffd435fbb7a04ceb76ecf9b54496b79c5edd61e2c5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ROQYYI6QCC42EYXUXWQRMTPHUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Prompt is Mightier than the Example","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Naren Ramakrishnan, Nikhil Muralidhar, Shengzhe Xu","submitted_at":"2025-05-24T03:19:36Z","abstract_excerpt":"Numerous recent prompt optimization approaches like chain-of-thought, have been demonstrated to significantly improve the quality of content generated by large language models (LLMs). In-context learning (ICL), a recent paradigm where a few representative examples guide content generation has also led to strong improvements in generation quality of LLM generated content. This idea has been applied to great effect in synthetic tabular data generation, where LLMs, through effective use of ICL and prompt optimization, can generate data that approximate samples from complex, heterogeneous distribu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18485","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/2505.18485/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":"2026-07-05T11:08:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EXml7fSkmio0Ox4gjhB9OdyKNoXPwDJsp2rteaQojvYGOOy6O+uHGEAr2MScait3DIpaHea5pnT0g8l/icgdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T14:41:43.137175Z"},"content_sha256":"2bd5b289effa1c37547aae398aad8f51fe0f128f32216481f25ce31b5adceeac","schema_version":"1.0","event_id":"sha256:2bd5b289effa1c37547aae398aad8f51fe0f128f32216481f25ce31b5adceeac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ROQYYI6QCC42EYXUXWQRMTPHUY/bundle.json","state_url":"https://pith.science/pith/ROQYYI6QCC42EYXUXWQRMTPHUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ROQYYI6QCC42EYXUXWQRMTPHUY/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":"2026-07-12T14:41:43Z","links":{"resolver":"https://pith.science/pith/ROQYYI6QCC42EYXUXWQRMTPHUY","bundle":"https://pith.science/pith/ROQYYI6QCC42EYXUXWQRMTPHUY/bundle.json","state":"https://pith.science/pith/ROQYYI6QCC42EYXUXWQRMTPHUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ROQYYI6QCC42EYXUXWQRMTPHUY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ROQYYI6QCC42EYXUXWQRMTPHUY","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":"078a6e36411fa7da7e101f74edf95adb300054c22a96a886a591dce31fa09b00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T03:19:36Z","title_canon_sha256":"505029a1a1de94286f09f79aab61cbc2f58e1877af122ffc3de6e6ce0e796bb6"},"schema_version":"1.0","source":{"id":"2505.18485","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18485","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18485v1","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18485","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"pith_short_12","alias_value":"ROQYYI6QCC42","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"pith_short_16","alias_value":"ROQYYI6QCC42EYXU","created_at":"2026-07-05T11:08:47Z"},{"alias_kind":"pith_short_8","alias_value":"ROQYYI6Q","created_at":"2026-07-05T11:08:47Z"}],"graph_snapshots":[{"event_id":"sha256:2bd5b289effa1c37547aae398aad8f51fe0f128f32216481f25ce31b5adceeac","target":"graph","created_at":"2026-07-05T11:08:47Z","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/2505.18485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous recent prompt optimization approaches like chain-of-thought, have been demonstrated to significantly improve the quality of content generated by large language models (LLMs). In-context learning (ICL), a recent paradigm where a few representative examples guide content generation has also led to strong improvements in generation quality of LLM generated content. This idea has been applied to great effect in synthetic tabular data generation, where LLMs, through effective use of ICL and prompt optimization, can generate data that approximate samples from complex, heterogeneous distribu","authors_text":"Naren Ramakrishnan, Nikhil Muralidhar, Shengzhe Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T03:19:36Z","title":"The Prompt is Mightier than the Example"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18485","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":"sha256:2cb0989e7afdb3b33cba6ffd435fbb7a04ceb76ecf9b54496b79c5edd61e2c5d","target":"record","created_at":"2026-07-05T11:08:47Z","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":"078a6e36411fa7da7e101f74edf95adb300054c22a96a886a591dce31fa09b00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T03:19:36Z","title_canon_sha256":"505029a1a1de94286f09f79aab61cbc2f58e1877af122ffc3de6e6ce0e796bb6"},"schema_version":"1.0","source":{"id":"2505.18485","kind":"arxiv","version":1}},"canonical_sha256":"8ba18c23d010b9a262f4bda1164de7a6031ef1676f73b4f68c8b07594e0fa7e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ba18c23d010b9a262f4bda1164de7a6031ef1676f73b4f68c8b07594e0fa7e3","first_computed_at":"2026-07-05T11:08:47.148692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:47.148692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kDBpnuzXXgNJqi+PavPzRHAi8edr7G8R2Jn5z7ZDTrKaTV4xAj83u7SE9heF68PyUyxGWa0domJdT4v8ifiQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:47.149117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18485","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cb0989e7afdb3b33cba6ffd435fbb7a04ceb76ecf9b54496b79c5edd61e2c5d","sha256:2bd5b289effa1c37547aae398aad8f51fe0f128f32216481f25ce31b5adceeac"],"state_sha256":"22a9d0c3618420883e8cb03458451d846403559a219993d2fdea4f36707b771c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzcUHyzcX9fYMXHph+vZA2cSwOMHvYuo/X+dXDedL4dKc4GaudzaBoQyTJqoR6A8m+oqcq06u6O00lZCM+lWBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T14:41:43.140797Z","bundle_sha256":"2043a8c42e7e1110cd94aa133518de0654d8b42d7fc65c844f9e7caa4ed4d31e"}}