{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3YBR55TCN46HJOIQM64AJOGXWY","short_pith_number":"pith:3YBR55TC","canonical_record":{"source":{"id":"2406.10878","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-16T10:02:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c949c37725b61e4a96abeeaeebbf068645f3de96348ba83e65bf08a122ab0d70","abstract_canon_sha256":"661fc20a43d095dffe6e5c1d3646f53bb84f55bf0e51a829ce29c55e60cbdce5"},"schema_version":"1.0"},"canonical_sha256":"de031ef6626f3c74b91067b804b8d7b6370d53bc84f844318424816cbc0c9b0c","source":{"kind":"arxiv","id":"2406.10878","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10878","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10878v1","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10878","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"pith_short_12","alias_value":"3YBR55TCN46H","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"pith_short_16","alias_value":"3YBR55TCN46HJOIQ","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"pith_short_8","alias_value":"3YBR55TC","created_at":"2026-07-05T08:32:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3YBR55TCN46HJOIQM64AJOGXWY","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10878","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-16T10:02:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c949c37725b61e4a96abeeaeebbf068645f3de96348ba83e65bf08a122ab0d70","abstract_canon_sha256":"661fc20a43d095dffe6e5c1d3646f53bb84f55bf0e51a829ce29c55e60cbdce5"},"schema_version":"1.0"},"canonical_sha256":"de031ef6626f3c74b91067b804b8d7b6370d53bc84f844318424816cbc0c9b0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:45.630000Z","signature_b64":"RKsHWWVm5nVtjgekibxWKk7HXq77WJo+9NMXl6DpYjFa9tEgGx+b9nvJFWHl6liIF0rGXkMY4AOMdsMISb+eCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de031ef6626f3c74b91067b804b8d7b6370d53bc84f844318424816cbc0c9b0c","last_reissued_at":"2026-07-05T08:32:45.629506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:45.629506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10878","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":"2026-07-05T08:32:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZI5tEMToc9yXTZxjcFtjDnYbKKpHCqRkCxk8FKUktDZdIsGrXld6maaghjfh5i/0xyz5ruqSQt8+6pbLp4SRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:57:05.293194Z"},"content_sha256":"4f891aa4b9c5944e27e9f02bb25d07edf050f109e2b94d995d840fa26e5bf065","schema_version":"1.0","event_id":"sha256:4f891aa4b9c5944e27e9f02bb25d07edf050f109e2b94d995d840fa26e5bf065"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3YBR55TCN46HJOIQM64AJOGXWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bin Dong, Yiming Tang","submitted_at":"2024-06-16T10:02:20Z","abstract_excerpt":"Large language models (LLMs) benefit greatly from prompt engineering, with in-context learning standing as a pivital technique. While former approaches have provided various ways to construct the demonstrations used for in-context learning, they often ignore the inherent heterogeneity within datasets, applying the same demonstrations to all reasoning questions. We observed that the effectiveness of demonstrations varies depending on the specific question. This motivates our exploration of using prompt engineering to select appropriate demonstrations. To address the challenge of automatically c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10878","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/2406.10878/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":"2026-07-05T08:32:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBAH2TipKE9npOZbfLAkXY+mXGHHVtjdn/mQLlaDBaRwH+s/5tm2jpCPG1DJPfTYl/w+NrIAzjnXGgpb1g73AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:57:05.293713Z"},"content_sha256":"04bcb348617a3402945dde3495e33c4befd1c7609f6f1ae1c767b167721c84e4","schema_version":"1.0","event_id":"sha256:04bcb348617a3402945dde3495e33c4befd1c7609f6f1ae1c767b167721c84e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YBR55TCN46HJOIQM64AJOGXWY/bundle.json","state_url":"https://pith.science/pith/3YBR55TCN46HJOIQM64AJOGXWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YBR55TCN46HJOIQM64AJOGXWY/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":"2026-08-09T04:57:05Z","links":{"resolver":"https://pith.science/pith/3YBR55TCN46HJOIQM64AJOGXWY","bundle":"https://pith.science/pith/3YBR55TCN46HJOIQM64AJOGXWY/bundle.json","state":"https://pith.science/pith/3YBR55TCN46HJOIQM64AJOGXWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YBR55TCN46HJOIQM64AJOGXWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3YBR55TCN46HJOIQM64AJOGXWY","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":"661fc20a43d095dffe6e5c1d3646f53bb84f55bf0e51a829ce29c55e60cbdce5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-16T10:02:20Z","title_canon_sha256":"c949c37725b61e4a96abeeaeebbf068645f3de96348ba83e65bf08a122ab0d70"},"schema_version":"1.0","source":{"id":"2406.10878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10878","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10878v1","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10878","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"pith_short_12","alias_value":"3YBR55TCN46H","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"pith_short_16","alias_value":"3YBR55TCN46HJOIQ","created_at":"2026-07-05T08:32:45Z"},{"alias_kind":"pith_short_8","alias_value":"3YBR55TC","created_at":"2026-07-05T08:32:45Z"}],"graph_snapshots":[{"event_id":"sha256:04bcb348617a3402945dde3495e33c4befd1c7609f6f1ae1c767b167721c84e4","target":"graph","created_at":"2026-07-05T08:32:45Z","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/2406.10878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) benefit greatly from prompt engineering, with in-context learning standing as a pivital technique. While former approaches have provided various ways to construct the demonstrations used for in-context learning, they often ignore the inherent heterogeneity within datasets, applying the same demonstrations to all reasoning questions. We observed that the effectiveness of demonstrations varies depending on the specific question. This motivates our exploration of using prompt engineering to select appropriate demonstrations. To address the challenge of automatically c","authors_text":"Bin Dong, Yiming Tang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-16T10:02:20Z","title":"Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10878","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":"sha256:4f891aa4b9c5944e27e9f02bb25d07edf050f109e2b94d995d840fa26e5bf065","target":"record","created_at":"2026-07-05T08:32:45Z","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":"661fc20a43d095dffe6e5c1d3646f53bb84f55bf0e51a829ce29c55e60cbdce5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-16T10:02:20Z","title_canon_sha256":"c949c37725b61e4a96abeeaeebbf068645f3de96348ba83e65bf08a122ab0d70"},"schema_version":"1.0","source":{"id":"2406.10878","kind":"arxiv","version":1}},"canonical_sha256":"de031ef6626f3c74b91067b804b8d7b6370d53bc84f844318424816cbc0c9b0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de031ef6626f3c74b91067b804b8d7b6370d53bc84f844318424816cbc0c9b0c","first_computed_at":"2026-07-05T08:32:45.629506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:45.629506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RKsHWWVm5nVtjgekibxWKk7HXq77WJo+9NMXl6DpYjFa9tEgGx+b9nvJFWHl6liIF0rGXkMY4AOMdsMISb+eCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:45.630000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f891aa4b9c5944e27e9f02bb25d07edf050f109e2b94d995d840fa26e5bf065","sha256:04bcb348617a3402945dde3495e33c4befd1c7609f6f1ae1c767b167721c84e4"],"state_sha256":"8a083a1d7c1929a892660a7bf1d5a27e577697d38cbe82322184d09576a079bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5GDPn04V7xTBYGebcLQ0dQ/rmS8HV5nBnjzS8++KhPyckt0GioALb53ygWoNhhkxNWc4Ax9b9UkrOi9cny7Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:57:05.303078Z","bundle_sha256":"8bad7d5da5b9d7f77bdf541152392a67f01179362b80b61269257fa4c27993e5"}}