{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FRJYCVG3HJ5BKDSPXUQMBCH5GW","short_pith_number":"pith:FRJYCVG3","canonical_record":{"source":{"id":"2606.08295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T18:31:50Z","cross_cats_sorted":[],"title_canon_sha256":"475ab528ae9806a6e14817abd3e6809d708aaeb3369589224cf07b7cb847edb6","abstract_canon_sha256":"fea3a355f428ca811f14ca82cf888c60d89a69846c14bddb2c11de4f36186c8c"},"schema_version":"1.0"},"canonical_sha256":"2c538154db3a7a150e4fbd20c088fd359e23e05eacbc36c837f465847e7164a0","source":{"kind":"arxiv","id":"2606.08295","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08295","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08295v1","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08295","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"FRJYCVG3HJ5B","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"FRJYCVG3HJ5BKDSP","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"FRJYCVG3","created_at":"2026-06-09T01:05:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FRJYCVG3HJ5BKDSPXUQMBCH5GW","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T18:31:50Z","cross_cats_sorted":[],"title_canon_sha256":"475ab528ae9806a6e14817abd3e6809d708aaeb3369589224cf07b7cb847edb6","abstract_canon_sha256":"fea3a355f428ca811f14ca82cf888c60d89a69846c14bddb2c11de4f36186c8c"},"schema_version":"1.0"},"canonical_sha256":"2c538154db3a7a150e4fbd20c088fd359e23e05eacbc36c837f465847e7164a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:32.886300Z","signature_b64":"MJv04Xe14VqwmwGBDo509pWqCuh/k2w551JJZCxGCNLdnQhbENpM1gRGiXBGB6CgRaKJDPV4R3Fsx3/r7SIRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c538154db3a7a150e4fbd20c088fd359e23e05eacbc36c837f465847e7164a0","last_reissued_at":"2026-06-09T01:05:32.885843Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:32.885843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08295","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":"2026-06-09T01:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bTaa2fP3fKqfO9cdg7etLCdk31e6Jhso9gX+iMwdMZcCq8pcpJBsJAuEe0ZnLJDCPScf3O29N1Hqjo+lChA+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T17:19:25.007111Z"},"content_sha256":"0ebcabc795711ce28d84818b4427602b59daae58dd21c53ed7a2ac4c68271c20","schema_version":"1.0","event_id":"sha256:0ebcabc795711ce28d84818b4427602b59daae58dd21c53ed7a2ac4c68271c20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FRJYCVG3HJ5BKDSPXUQMBCH5GW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junsheng Zhong, Lei Shi, Tian Xie, Tianyuan Liang, Xiaodong Yu, Xueru Zhang, Xuwei Tan, Zhiqun Zuo, Ziyu Hu","submitted_at":"2026-06-06T18:31:50Z","abstract_excerpt":"Tabular data is a primary medium for storing real-world information, driving many industrial applications of machine learning. Traditional predictors achieve strong predictive performance but do not provide readable, case-specific explanations essential for decision-making. Large Language Models (LLMs) can naturally bridge this gap by generating predictions alongside explanations. However, dataset-specific patterns, such as feature distributions and interactions, make tabular data difficult for LLMs to understand and reason over, while label-only fine-tuning improves performance at the cost of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08295","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/2606.08295/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":"2026-06-09T01:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wp1hokOiRAU2BWX5s87keL5qp3oa0lNui4O8vWHV0WgIO9uIraWSOfHR2FmfosSqgG4/oHGJsQSrvTZ+vQG4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T17:19:25.007902Z"},"content_sha256":"2e4463532f4ce3d79783d12515e58b86be7b394e0b2ebdfe380b1795e8ba82c0","schema_version":"1.0","event_id":"sha256:2e4463532f4ce3d79783d12515e58b86be7b394e0b2ebdfe380b1795e8ba82c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRJYCVG3HJ5BKDSPXUQMBCH5GW/bundle.json","state_url":"https://pith.science/pith/FRJYCVG3HJ5BKDSPXUQMBCH5GW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRJYCVG3HJ5BKDSPXUQMBCH5GW/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":"2026-06-09T17:19:25Z","links":{"resolver":"https://pith.science/pith/FRJYCVG3HJ5BKDSPXUQMBCH5GW","bundle":"https://pith.science/pith/FRJYCVG3HJ5BKDSPXUQMBCH5GW/bundle.json","state":"https://pith.science/pith/FRJYCVG3HJ5BKDSPXUQMBCH5GW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRJYCVG3HJ5BKDSPXUQMBCH5GW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FRJYCVG3HJ5BKDSPXUQMBCH5GW","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":"fea3a355f428ca811f14ca82cf888c60d89a69846c14bddb2c11de4f36186c8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T18:31:50Z","title_canon_sha256":"475ab528ae9806a6e14817abd3e6809d708aaeb3369589224cf07b7cb847edb6"},"schema_version":"1.0","source":{"id":"2606.08295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08295","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08295v1","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08295","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"FRJYCVG3HJ5B","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"FRJYCVG3HJ5BKDSP","created_at":"2026-06-09T01:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"FRJYCVG3","created_at":"2026-06-09T01:05:32Z"}],"graph_snapshots":[{"event_id":"sha256:2e4463532f4ce3d79783d12515e58b86be7b394e0b2ebdfe380b1795e8ba82c0","target":"graph","created_at":"2026-06-09T01:05:32Z","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/2606.08295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data is a primary medium for storing real-world information, driving many industrial applications of machine learning. Traditional predictors achieve strong predictive performance but do not provide readable, case-specific explanations essential for decision-making. Large Language Models (LLMs) can naturally bridge this gap by generating predictions alongside explanations. However, dataset-specific patterns, such as feature distributions and interactions, make tabular data difficult for LLMs to understand and reason over, while label-only fine-tuning improves performance at the cost of","authors_text":"Junsheng Zhong, Lei Shi, Tian Xie, Tianyuan Liang, Xiaodong Yu, Xueru Zhang, Xuwei Tan, Zhiqun Zuo, Ziyu Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T18:31:50Z","title":"TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08295","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":"sha256:0ebcabc795711ce28d84818b4427602b59daae58dd21c53ed7a2ac4c68271c20","target":"record","created_at":"2026-06-09T01:05:32Z","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":"fea3a355f428ca811f14ca82cf888c60d89a69846c14bddb2c11de4f36186c8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T18:31:50Z","title_canon_sha256":"475ab528ae9806a6e14817abd3e6809d708aaeb3369589224cf07b7cb847edb6"},"schema_version":"1.0","source":{"id":"2606.08295","kind":"arxiv","version":1}},"canonical_sha256":"2c538154db3a7a150e4fbd20c088fd359e23e05eacbc36c837f465847e7164a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c538154db3a7a150e4fbd20c088fd359e23e05eacbc36c837f465847e7164a0","first_computed_at":"2026-06-09T01:05:32.885843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:32.885843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MJv04Xe14VqwmwGBDo509pWqCuh/k2w551JJZCxGCNLdnQhbENpM1gRGiXBGB6CgRaKJDPV4R3Fsx3/r7SIRDA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:32.886300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ebcabc795711ce28d84818b4427602b59daae58dd21c53ed7a2ac4c68271c20","sha256:2e4463532f4ce3d79783d12515e58b86be7b394e0b2ebdfe380b1795e8ba82c0"],"state_sha256":"9c505afdc765d00637f7ab032a384bcbb06d49608e38a17aaa571d08fd0b75ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7NUSX9QPMBO1/4xt7wx2X53SeY9GmF2MvdHz33uFH++gAYrR/wj8Zt34QTsq+S1UEx7wsRmUKTLO2i9W0CRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T17:19:25.012238Z","bundle_sha256":"cf5b5dd6438607c777740bed303c874096b1ec777da12c6a11ac7e4ef61c20c7"}}