{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4W6NLENT4AMJEABSJFC3XN76XA","short_pith_number":"pith:4W6NLENT","canonical_record":{"source":{"id":"2502.03147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T13:16:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8961e45a60fba6f2d0d9b847682db9491d9dc94db8325fe6401cab48875af3be","abstract_canon_sha256":"a07592e1e6a84d18f4f62d84307f99dc62bc9a4e11f67f29f87345ef798c7050"},"schema_version":"1.0"},"canonical_sha256":"e5bcd591b3e0189200324945bbb7feb838414fd546c5b381a84741def87d2f9e","source":{"kind":"arxiv","id":"2502.03147","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03147","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03147v1","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03147","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"4W6NLENT4AMJ","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"4W6NLENT4AMJEABS","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"4W6NLENT","created_at":"2026-07-05T10:10:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4W6NLENT4AMJEABSJFC3XN76XA","target":"record","payload":{"canonical_record":{"source":{"id":"2502.03147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T13:16:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8961e45a60fba6f2d0d9b847682db9491d9dc94db8325fe6401cab48875af3be","abstract_canon_sha256":"a07592e1e6a84d18f4f62d84307f99dc62bc9a4e11f67f29f87345ef798c7050"},"schema_version":"1.0"},"canonical_sha256":"e5bcd591b3e0189200324945bbb7feb838414fd546c5b381a84741def87d2f9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:00.445377Z","signature_b64":"lZA1L/9fkL+z4f8P61XS5nc20djMBvbB9QNPbezHCoIS9dyac1kN2gYFwijv01T3JsY8QntBH2J2NJO2aYxMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5bcd591b3e0189200324945bbb7feb838414fd546c5b381a84741def87d2f9e","last_reissued_at":"2026-07-05T10:10:00.445000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:00.445000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.03147","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":"2026-07-05T10:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"twNfbVt6ZF2IUANC2P4fjcV/zVte46nlWfstRxIw0IA4X34598/YXa2DyKfucN6tci0zUQtZEwbSAVi89MLOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:36:41.590803Z"},"content_sha256":"e72f5412a33d0fff8758e5ba13489b2901056d7f5e935fafd94aab44bec59df5","schema_version":"1.0","event_id":"sha256:e72f5412a33d0fff8758e5ba13489b2901056d7f5e935fafd94aab44bec59df5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4W6NLENT4AMJEABSJFC3XN76XA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiang Bian, Shun Zheng, Xumeng Wen, Yiming Sun, Zhen Xu","submitted_at":"2025-02-05T13:16:41Z","abstract_excerpt":"Recent studies have shown that large language models (LLMs), when customized with post-training on tabular data, can acquire general tabular in-context learning (TabICL) capabilities. These models are able to transfer effectively across diverse data schemas and different task domains. However, existing LLM-based TabICL approaches are constrained to few-shot scenarios due to the sequence length limitations of LLMs, as tabular instances represented in plain text consume substantial tokens. To address this limitation and enable scalable TabICL for any data size, we propose retrieval-augmented LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03147","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/2502.03147/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":"2026-07-05T10:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YucUp05hB3+2ERpwCdPEIe3CIUPYpEw/CqyFftHHYhV4TmiqIqYkFWjZzc+FcsxAtLCE3REIdzg/AKjNvHjoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:36:41.591336Z"},"content_sha256":"5a14d646b64b1160817120bfea83b6b8ffe8e274b8719f1017df630a5c6077f2","schema_version":"1.0","event_id":"sha256:5a14d646b64b1160817120bfea83b6b8ffe8e274b8719f1017df630a5c6077f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4W6NLENT4AMJEABSJFC3XN76XA/bundle.json","state_url":"https://pith.science/pith/4W6NLENT4AMJEABSJFC3XN76XA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4W6NLENT4AMJEABSJFC3XN76XA/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":"2026-08-05T18:36:41Z","links":{"resolver":"https://pith.science/pith/4W6NLENT4AMJEABSJFC3XN76XA","bundle":"https://pith.science/pith/4W6NLENT4AMJEABSJFC3XN76XA/bundle.json","state":"https://pith.science/pith/4W6NLENT4AMJEABSJFC3XN76XA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4W6NLENT4AMJEABSJFC3XN76XA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4W6NLENT4AMJEABSJFC3XN76XA","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":"a07592e1e6a84d18f4f62d84307f99dc62bc9a4e11f67f29f87345ef798c7050","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T13:16:41Z","title_canon_sha256":"8961e45a60fba6f2d0d9b847682db9491d9dc94db8325fe6401cab48875af3be"},"schema_version":"1.0","source":{"id":"2502.03147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03147","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03147v1","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03147","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"4W6NLENT4AMJ","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"4W6NLENT4AMJEABS","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"4W6NLENT","created_at":"2026-07-05T10:10:00Z"}],"graph_snapshots":[{"event_id":"sha256:5a14d646b64b1160817120bfea83b6b8ffe8e274b8719f1017df630a5c6077f2","target":"graph","created_at":"2026-07-05T10:10:00Z","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/2502.03147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have shown that large language models (LLMs), when customized with post-training on tabular data, can acquire general tabular in-context learning (TabICL) capabilities. These models are able to transfer effectively across diverse data schemas and different task domains. However, existing LLM-based TabICL approaches are constrained to few-shot scenarios due to the sequence length limitations of LLMs, as tabular instances represented in plain text consume substantial tokens. To address this limitation and enable scalable TabICL for any data size, we propose retrieval-augmented LLM","authors_text":"Jiang Bian, Shun Zheng, Xumeng Wen, Yiming Sun, Zhen Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T13:16:41Z","title":"Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03147","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:e72f5412a33d0fff8758e5ba13489b2901056d7f5e935fafd94aab44bec59df5","target":"record","created_at":"2026-07-05T10:10:00Z","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":"a07592e1e6a84d18f4f62d84307f99dc62bc9a4e11f67f29f87345ef798c7050","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T13:16:41Z","title_canon_sha256":"8961e45a60fba6f2d0d9b847682db9491d9dc94db8325fe6401cab48875af3be"},"schema_version":"1.0","source":{"id":"2502.03147","kind":"arxiv","version":1}},"canonical_sha256":"e5bcd591b3e0189200324945bbb7feb838414fd546c5b381a84741def87d2f9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5bcd591b3e0189200324945bbb7feb838414fd546c5b381a84741def87d2f9e","first_computed_at":"2026-07-05T10:10:00.445000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:00.445000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lZA1L/9fkL+z4f8P61XS5nc20djMBvbB9QNPbezHCoIS9dyac1kN2gYFwijv01T3JsY8QntBH2J2NJO2aYxMBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:00.445377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e72f5412a33d0fff8758e5ba13489b2901056d7f5e935fafd94aab44bec59df5","sha256:5a14d646b64b1160817120bfea83b6b8ffe8e274b8719f1017df630a5c6077f2"],"state_sha256":"4855e39244156151341763a59e224edef4498b5da4558b9dd97c898126a0eaeb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"USRu7WrcMzn/NrzHkIpmgO+90Lx9TSO51C7XkLdnjJP7XunY/lZK5Y9Qd00hc+Ihjyuh0JE/EOaD7QNGVnN3BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:36:41.595504Z","bundle_sha256":"85bb48778a3b96dca6df03879fcd1bd95e6ab1c3f90b2a518326dc2ecf4c2575"}}