{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EQQWFIHVPY6KLAFGU4UDSKZMM7","short_pith_number":"pith:EQQWFIHV","canonical_record":{"source":{"id":"2506.20451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T13:57:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b82e2031faebf0b9dd9da7d49654a84841d65a323e7b206b8f6c05be4512d6e6","abstract_canon_sha256":"dbbd57276ccedc98dcb551702fe56ade04d13728aa88ebc649cf0c80bad17615"},"schema_version":"1.0"},"canonical_sha256":"242162a0f57e3ca580a6a728392b2c67f36a96beb48f29c0bd5539c84a09c897","source":{"kind":"arxiv","id":"2506.20451","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20451","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20451v1","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20451","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"pith_short_12","alias_value":"EQQWFIHVPY6K","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"pith_short_16","alias_value":"EQQWFIHVPY6KLAFG","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"pith_short_8","alias_value":"EQQWFIHV","created_at":"2026-07-05T11:27:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EQQWFIHVPY6KLAFGU4UDSKZMM7","target":"record","payload":{"canonical_record":{"source":{"id":"2506.20451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T13:57:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b82e2031faebf0b9dd9da7d49654a84841d65a323e7b206b8f6c05be4512d6e6","abstract_canon_sha256":"dbbd57276ccedc98dcb551702fe56ade04d13728aa88ebc649cf0c80bad17615"},"schema_version":"1.0"},"canonical_sha256":"242162a0f57e3ca580a6a728392b2c67f36a96beb48f29c0bd5539c84a09c897","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:05.916828Z","signature_b64":"85orpXjzbTl+WwHaeTrrvoZ8h5TNyJzO/wVvAbplUXgHHtkTKvAlAaDrqGWEP0AvSTrSoJdb6lMvcPTAyUVqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"242162a0f57e3ca580a6a728392b2c67f36a96beb48f29c0bd5539c84a09c897","last_reissued_at":"2026-07-05T11:27:05.916352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:05.916352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.20451","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":"2026-07-05T11:27:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLn+6nbWia55EYs6PG6/zLX0TEP3W9Zs1FGt63qJ+JDnGAPnsZWtXd5ognjcAs0+29Msw99hCiwxzRJjGJDHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:16:35.352769Z"},"content_sha256":"439a823235c4ba5632a71d5d1a0248f89f9aaf211d4026d1413a777d86813bda","schema_version":"1.0","event_id":"sha256:439a823235c4ba5632a71d5d1a0248f89f9aaf211d4026d1413a777d86813bda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EQQWFIHVPY6KLAFGU4UDSKZMM7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Demonstration Selection for LLM-based Tabular Data Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shuchu Han, Wolfgang Bruckner","submitted_at":"2025-06-25T13:57:54Z","abstract_excerpt":"A fundamental question in applying In-Context Learning (ICL) for tabular data classification is how to determine the ideal number of demonstrations in the prompt. This work addresses this challenge by presenting an algorithm to automatically select a reasonable number of required demonstrations. Our method distinguishes itself by integrating not only the tabular data's distribution but also the user's selected prompt template and the specific Large Language Model (LLM) into its estimation. Rooted in Spectral Graph Theory, our proposed algorithm defines a novel metric to quantify the similariti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20451","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/2506.20451/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":"2026-07-05T11:27:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wu4yPvaauvDSzonf5i8DGoF73timF5aI5qWF999XKuO6HhvMVvvIBigvdRj+G6/0YihAqQjJiK4LNTsIlNzEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:16:35.353268Z"},"content_sha256":"b777c1cf425f396695c4d6ffd630d6de02d54f95ad01bb5856d0a097b22e3162","schema_version":"1.0","event_id":"sha256:b777c1cf425f396695c4d6ffd630d6de02d54f95ad01bb5856d0a097b22e3162"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQQWFIHVPY6KLAFGU4UDSKZMM7/bundle.json","state_url":"https://pith.science/pith/EQQWFIHVPY6KLAFGU4UDSKZMM7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQQWFIHVPY6KLAFGU4UDSKZMM7/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":"2026-08-09T04:16:35Z","links":{"resolver":"https://pith.science/pith/EQQWFIHVPY6KLAFGU4UDSKZMM7","bundle":"https://pith.science/pith/EQQWFIHVPY6KLAFGU4UDSKZMM7/bundle.json","state":"https://pith.science/pith/EQQWFIHVPY6KLAFGU4UDSKZMM7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQQWFIHVPY6KLAFGU4UDSKZMM7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EQQWFIHVPY6KLAFGU4UDSKZMM7","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":"dbbd57276ccedc98dcb551702fe56ade04d13728aa88ebc649cf0c80bad17615","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T13:57:54Z","title_canon_sha256":"b82e2031faebf0b9dd9da7d49654a84841d65a323e7b206b8f6c05be4512d6e6"},"schema_version":"1.0","source":{"id":"2506.20451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20451","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20451v1","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20451","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"pith_short_12","alias_value":"EQQWFIHVPY6K","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"pith_short_16","alias_value":"EQQWFIHVPY6KLAFG","created_at":"2026-07-05T11:27:05Z"},{"alias_kind":"pith_short_8","alias_value":"EQQWFIHV","created_at":"2026-07-05T11:27:05Z"}],"graph_snapshots":[{"event_id":"sha256:b777c1cf425f396695c4d6ffd630d6de02d54f95ad01bb5856d0a097b22e3162","target":"graph","created_at":"2026-07-05T11:27:05Z","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/2506.20451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fundamental question in applying In-Context Learning (ICL) for tabular data classification is how to determine the ideal number of demonstrations in the prompt. This work addresses this challenge by presenting an algorithm to automatically select a reasonable number of required demonstrations. Our method distinguishes itself by integrating not only the tabular data's distribution but also the user's selected prompt template and the specific Large Language Model (LLM) into its estimation. Rooted in Spectral Graph Theory, our proposed algorithm defines a novel metric to quantify the similariti","authors_text":"Shuchu Han, Wolfgang Bruckner","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T13:57:54Z","title":"Automatic Demonstration Selection for LLM-based Tabular Data Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20451","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":"sha256:439a823235c4ba5632a71d5d1a0248f89f9aaf211d4026d1413a777d86813bda","target":"record","created_at":"2026-07-05T11:27:05Z","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":"dbbd57276ccedc98dcb551702fe56ade04d13728aa88ebc649cf0c80bad17615","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T13:57:54Z","title_canon_sha256":"b82e2031faebf0b9dd9da7d49654a84841d65a323e7b206b8f6c05be4512d6e6"},"schema_version":"1.0","source":{"id":"2506.20451","kind":"arxiv","version":1}},"canonical_sha256":"242162a0f57e3ca580a6a728392b2c67f36a96beb48f29c0bd5539c84a09c897","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"242162a0f57e3ca580a6a728392b2c67f36a96beb48f29c0bd5539c84a09c897","first_computed_at":"2026-07-05T11:27:05.916352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:05.916352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"85orpXjzbTl+WwHaeTrrvoZ8h5TNyJzO/wVvAbplUXgHHtkTKvAlAaDrqGWEP0AvSTrSoJdb6lMvcPTAyUVqBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:05.916828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:439a823235c4ba5632a71d5d1a0248f89f9aaf211d4026d1413a777d86813bda","sha256:b777c1cf425f396695c4d6ffd630d6de02d54f95ad01bb5856d0a097b22e3162"],"state_sha256":"98f6b7f4f0e6f5c6f397693e4596e0e536da4661bb779f6cae1bedf4c1f248d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/mirFz4ZE8YOj4DtTxyAir0jwTKqPq7mw9oE5Ql4mNtpDu85ynO1Iv06te2WT/R2oTo6zeTL6TGRVerAgiHMDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:16:35.358181Z","bundle_sha256":"aae9ba9d4ec6d54dffbc0cabbec60f99229273faddb4cbbcd11337e4dfd7bfa0"}}