{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4TUWPCCL6GBR7OAOGY6HWGHZAQ","short_pith_number":"pith:4TUWPCCL","canonical_record":{"source":{"id":"2508.18676","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T04:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"de096b5e101271a67ee96d1c4cc12b4f24b37a476e7140914da42073599606ed","abstract_canon_sha256":"1937d840a0093c6ef669e1e1fe2096e31fdb716b708617175a80c8851b2956be"},"schema_version":"1.0"},"canonical_sha256":"e4e967884bf1831fb80e363c7b18f9043008dfe38066affea6ecb61585d030a4","source":{"kind":"arxiv","id":"2508.18676","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18676","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18676v1","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18676","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"pith_short_12","alias_value":"4TUWPCCL6GBR","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"pith_short_16","alias_value":"4TUWPCCL6GBR7OAO","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"pith_short_8","alias_value":"4TUWPCCL","created_at":"2026-07-05T11:59:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4TUWPCCL6GBR7OAOGY6HWGHZAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2508.18676","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T04:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"de096b5e101271a67ee96d1c4cc12b4f24b37a476e7140914da42073599606ed","abstract_canon_sha256":"1937d840a0093c6ef669e1e1fe2096e31fdb716b708617175a80c8851b2956be"},"schema_version":"1.0"},"canonical_sha256":"e4e967884bf1831fb80e363c7b18f9043008dfe38066affea6ecb61585d030a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:29.160140Z","signature_b64":"5Nf7WvbpSZPlZex41EZM5CzdxeiYYG81HSf5xe39lvQCiJ08ZHJwNKM4hMAHIllUmruglisjfT4VqhvV9opgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4e967884bf1831fb80e363c7b18f9043008dfe38066affea6ecb61585d030a4","last_reissued_at":"2026-07-05T11:59:29.159729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:29.159729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.18676","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":"2026-07-05T11:59:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GQxXYTPNNy23qF68CoOUPucT6OXZDvvBhmNOeYUe0MWZI/jHzMu3J2yG7FUp4vFPDZYZOVUJ8ovc+H6kziifDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:17:09.180446Z"},"content_sha256":"09f8ec3ef9d9329c970d26b0babbddb7d20e576dabae8667bff4694f795b9212","schema_version":"1.0","event_id":"sha256:09f8ec3ef9d9329c970d26b0babbddb7d20e576dabae8667bff4694f795b9212"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4TUWPCCL6GBR7OAOGY6HWGHZAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chufan Gao, Jimeng Sun, Jintai Chen","submitted_at":"2025-08-26T04:46:54Z","abstract_excerpt":"Automated tabular understanding and reasoning are essential tasks for data scientists. Recently, Large language models (LLMs) have become increasingly prevalent in tabular reasoning tasks. Previous work focuses on (1) finetuning LLMs using labeled data or (2) Training-free prompting LLM agents using chain-of-thought (CoT). Finetuning offers dataset-specific learning at the cost of generalizability. Training-free prompting is highly generalizable but does not take full advantage of training data. In this paper, we propose a novel prompting-based reasoning approach, Learn then Retrieve: LRTab, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18676","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/2508.18676/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":"2026-07-05T11:59:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FpfEGNMG8XH0fA+qjFYbumnHU57+DprHBk2N6mLEH73VByIy8vI40hk2FW1BESPjyZQUhMxvc1c6qJlSbHx5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:17:09.181032Z"},"content_sha256":"53de098611b313c638894435a9cfc59d7268dac5a67c6f3744367fade511bf3c","schema_version":"1.0","event_id":"sha256:53de098611b313c638894435a9cfc59d7268dac5a67c6f3744367fade511bf3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4TUWPCCL6GBR7OAOGY6HWGHZAQ/bundle.json","state_url":"https://pith.science/pith/4TUWPCCL6GBR7OAOGY6HWGHZAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4TUWPCCL6GBR7OAOGY6HWGHZAQ/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":"2026-08-18T12:17:09Z","links":{"resolver":"https://pith.science/pith/4TUWPCCL6GBR7OAOGY6HWGHZAQ","bundle":"https://pith.science/pith/4TUWPCCL6GBR7OAOGY6HWGHZAQ/bundle.json","state":"https://pith.science/pith/4TUWPCCL6GBR7OAOGY6HWGHZAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4TUWPCCL6GBR7OAOGY6HWGHZAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4TUWPCCL6GBR7OAOGY6HWGHZAQ","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":"1937d840a0093c6ef669e1e1fe2096e31fdb716b708617175a80c8851b2956be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T04:46:54Z","title_canon_sha256":"de096b5e101271a67ee96d1c4cc12b4f24b37a476e7140914da42073599606ed"},"schema_version":"1.0","source":{"id":"2508.18676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18676","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18676v1","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18676","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"pith_short_12","alias_value":"4TUWPCCL6GBR","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"pith_short_16","alias_value":"4TUWPCCL6GBR7OAO","created_at":"2026-07-05T11:59:29Z"},{"alias_kind":"pith_short_8","alias_value":"4TUWPCCL","created_at":"2026-07-05T11:59:29Z"}],"graph_snapshots":[{"event_id":"sha256:53de098611b313c638894435a9cfc59d7268dac5a67c6f3744367fade511bf3c","target":"graph","created_at":"2026-07-05T11:59:29Z","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/2508.18676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated tabular understanding and reasoning are essential tasks for data scientists. Recently, Large language models (LLMs) have become increasingly prevalent in tabular reasoning tasks. Previous work focuses on (1) finetuning LLMs using labeled data or (2) Training-free prompting LLM agents using chain-of-thought (CoT). Finetuning offers dataset-specific learning at the cost of generalizability. Training-free prompting is highly generalizable but does not take full advantage of training data. In this paper, we propose a novel prompting-based reasoning approach, Learn then Retrieve: LRTab, w","authors_text":"Chufan Gao, Jimeng Sun, Jintai Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T04:46:54Z","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18676","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":"sha256:09f8ec3ef9d9329c970d26b0babbddb7d20e576dabae8667bff4694f795b9212","target":"record","created_at":"2026-07-05T11:59:29Z","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":"1937d840a0093c6ef669e1e1fe2096e31fdb716b708617175a80c8851b2956be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T04:46:54Z","title_canon_sha256":"de096b5e101271a67ee96d1c4cc12b4f24b37a476e7140914da42073599606ed"},"schema_version":"1.0","source":{"id":"2508.18676","kind":"arxiv","version":1}},"canonical_sha256":"e4e967884bf1831fb80e363c7b18f9043008dfe38066affea6ecb61585d030a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4e967884bf1831fb80e363c7b18f9043008dfe38066affea6ecb61585d030a4","first_computed_at":"2026-07-05T11:59:29.159729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:29.159729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Nf7WvbpSZPlZex41EZM5CzdxeiYYG81HSf5xe39lvQCiJ08ZHJwNKM4hMAHIllUmruglisjfT4VqhvV9opgAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:29.160140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.18676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09f8ec3ef9d9329c970d26b0babbddb7d20e576dabae8667bff4694f795b9212","sha256:53de098611b313c638894435a9cfc59d7268dac5a67c6f3744367fade511bf3c"],"state_sha256":"c29c1edf294fca96717459f39c2f6d64a39ac5f4abe07f434feb4df1aaa45828"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGhGmc7X8zWKgqO97S8OzvjigYWug6BFA8l7rGZt06CfW7q3Ele3A/xYRRbwvKHwtSDcc2AtB2LBDWwGA1HMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:17:09.186786Z","bundle_sha256":"312312300322a383b27ef82453b7d8e1d2f5fbd3c531caf4bd31c5fa0a8dcdf0"}}