{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GE3EM4GJW3NCRREM5P3KFZ7XVY","short_pith_number":"pith:GE3EM4GJ","canonical_record":{"source":{"id":"2407.02750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T01:51:50Z","cross_cats_sorted":[],"title_canon_sha256":"624d0af1691823a734f47f7501bf85e79fc3af354d9934e295a50d2fc666f5ce","abstract_canon_sha256":"7eb1a4806254c5f519c1a114b90bcee9106555e80573671c75225f65cbfa2281"},"schema_version":"1.0"},"canonical_sha256":"31364670c9b6da28c48cebf6a2e7f7ae202e909cfc01c0a303f16c235c6ebc05","source":{"kind":"arxiv","id":"2407.02750","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02750","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02750v1","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02750","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"pith_short_12","alias_value":"GE3EM4GJW3NC","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"pith_short_16","alias_value":"GE3EM4GJW3NCRREM","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"pith_short_8","alias_value":"GE3EM4GJ","created_at":"2026-07-05T08:39:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GE3EM4GJW3NCRREM5P3KFZ7XVY","target":"record","payload":{"canonical_record":{"source":{"id":"2407.02750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T01:51:50Z","cross_cats_sorted":[],"title_canon_sha256":"624d0af1691823a734f47f7501bf85e79fc3af354d9934e295a50d2fc666f5ce","abstract_canon_sha256":"7eb1a4806254c5f519c1a114b90bcee9106555e80573671c75225f65cbfa2281"},"schema_version":"1.0"},"canonical_sha256":"31364670c9b6da28c48cebf6a2e7f7ae202e909cfc01c0a303f16c235c6ebc05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:41.116895Z","signature_b64":"Ce3mAmRaSQZ/fFdRUl8Ox9UzAVYjWt+72Q2JKQuiv72cbboH1yHkanQWIfZ8vZtZ9Lj+UveDpoI1gmVVzQ8pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31364670c9b6da28c48cebf6a2e7f7ae202e909cfc01c0a303f16c235c6ebc05","last_reissued_at":"2026-07-05T08:39:41.116487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:41.116487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.02750","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":"2026-07-05T08:39:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8r+eWIc9uwBVgecGeQYhNMQEjekeHPvhkLtee8mAB/LWmjG3V+fyyQUE8AB1e1Ywk/vUEgjQdQyMDmP2s81dBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:48:22.495065Z"},"content_sha256":"0955b5fb097d5da033f93d49097e17cd2993da981fbf490e925c667fe6f898d7","schema_version":"1.0","event_id":"sha256:0955b5fb097d5da033f93d49097e17cd2993da981fbf490e925c667fe6f898d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GE3EM4GJW3NCRREM5P3KFZ7XVY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Reduce: Towards Improving Performance of Large Language Models on Structured Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ryan A. Rossi, Sungchul Kim, Tong Yu, Xiang Chen, Younghun Lee","submitted_at":"2024-07-03T01:51:50Z","abstract_excerpt":"Large Language Models (LLMs) have been achieving competent performance on a wide range of downstream tasks, yet existing work shows that inference on structured data is challenging for LLMs. This is because LLMs need to either understand long structured data or select the most relevant evidence before inference, and both approaches are not trivial. This paper proposes a framework, Learning to Reduce, that fine-tunes a language model with On-Policy Learning to generate a reduced version of an input structured data. When compared to state-of-the-art LLMs like GPT-4, Learning to Reduce not only a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02750","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/2407.02750/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":"2026-07-05T08:39:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KgvUm1BAEUdrsk3ZF2Q7epb90JAPPJ2LYzIcY2NGzbWmMlmq2/EE9nnQXZQVQnr/ncHyo1nfGhqI0CMa8rdsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:48:22.495563Z"},"content_sha256":"cf00097fe876332d6bc6fc65b61fab213d22b248089b40d8bfecdae044f8697e","schema_version":"1.0","event_id":"sha256:cf00097fe876332d6bc6fc65b61fab213d22b248089b40d8bfecdae044f8697e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GE3EM4GJW3NCRREM5P3KFZ7XVY/bundle.json","state_url":"https://pith.science/pith/GE3EM4GJW3NCRREM5P3KFZ7XVY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GE3EM4GJW3NCRREM5P3KFZ7XVY/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":"2026-08-10T09:48:22Z","links":{"resolver":"https://pith.science/pith/GE3EM4GJW3NCRREM5P3KFZ7XVY","bundle":"https://pith.science/pith/GE3EM4GJW3NCRREM5P3KFZ7XVY/bundle.json","state":"https://pith.science/pith/GE3EM4GJW3NCRREM5P3KFZ7XVY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GE3EM4GJW3NCRREM5P3KFZ7XVY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GE3EM4GJW3NCRREM5P3KFZ7XVY","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":"7eb1a4806254c5f519c1a114b90bcee9106555e80573671c75225f65cbfa2281","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T01:51:50Z","title_canon_sha256":"624d0af1691823a734f47f7501bf85e79fc3af354d9934e295a50d2fc666f5ce"},"schema_version":"1.0","source":{"id":"2407.02750","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02750","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02750v1","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02750","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"pith_short_12","alias_value":"GE3EM4GJW3NC","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"pith_short_16","alias_value":"GE3EM4GJW3NCRREM","created_at":"2026-07-05T08:39:41Z"},{"alias_kind":"pith_short_8","alias_value":"GE3EM4GJ","created_at":"2026-07-05T08:39:41Z"}],"graph_snapshots":[{"event_id":"sha256:cf00097fe876332d6bc6fc65b61fab213d22b248089b40d8bfecdae044f8697e","target":"graph","created_at":"2026-07-05T08:39:41Z","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/2407.02750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have been achieving competent performance on a wide range of downstream tasks, yet existing work shows that inference on structured data is challenging for LLMs. This is because LLMs need to either understand long structured data or select the most relevant evidence before inference, and both approaches are not trivial. This paper proposes a framework, Learning to Reduce, that fine-tunes a language model with On-Policy Learning to generate a reduced version of an input structured data. When compared to state-of-the-art LLMs like GPT-4, Learning to Reduce not only a","authors_text":"Ryan A. Rossi, Sungchul Kim, Tong Yu, Xiang Chen, Younghun Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T01:51:50Z","title":"Learning to Reduce: Towards Improving Performance of Large Language Models on Structured Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02750","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":"sha256:0955b5fb097d5da033f93d49097e17cd2993da981fbf490e925c667fe6f898d7","target":"record","created_at":"2026-07-05T08:39:41Z","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":"7eb1a4806254c5f519c1a114b90bcee9106555e80573671c75225f65cbfa2281","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T01:51:50Z","title_canon_sha256":"624d0af1691823a734f47f7501bf85e79fc3af354d9934e295a50d2fc666f5ce"},"schema_version":"1.0","source":{"id":"2407.02750","kind":"arxiv","version":1}},"canonical_sha256":"31364670c9b6da28c48cebf6a2e7f7ae202e909cfc01c0a303f16c235c6ebc05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31364670c9b6da28c48cebf6a2e7f7ae202e909cfc01c0a303f16c235c6ebc05","first_computed_at":"2026-07-05T08:39:41.116487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:41.116487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ce3mAmRaSQZ/fFdRUl8Ox9UzAVYjWt+72Q2JKQuiv72cbboH1yHkanQWIfZ8vZtZ9Lj+UveDpoI1gmVVzQ8pAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:41.116895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02750","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0955b5fb097d5da033f93d49097e17cd2993da981fbf490e925c667fe6f898d7","sha256:cf00097fe876332d6bc6fc65b61fab213d22b248089b40d8bfecdae044f8697e"],"state_sha256":"bc5e7ad21e0e19dedd17f041251a87347aa60b12280dd42992ed05fdebde9928"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+nW7eK2ZxKw2q7A2EzFiQEoTyiMzmyYin2jbHxpNwbk4J2h4MEBzVEdtgrnJw5i4PdAUMRIH/ySVzrwq/QuAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:48:22.498921Z","bundle_sha256":"4c812f771b2c51b2b71d3c97bfa096727dc2ab8cc1af78915772b276c5858f70"}}