{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QD4JSZS2F3T5Q7PUNVHAPYIV4H","short_pith_number":"pith:QD4JSZS2","canonical_record":{"source":{"id":"2310.09263","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T17:20:56Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"0abd45aa1eb7cf01be049eeef16d223caea674d1d84e8cbeff9bce09c4e9f289","abstract_canon_sha256":"bace71ce3c0eeabdee3878f9a21490d469dbaa80bf971537dc7db654c2245353"},"schema_version":"1.0"},"canonical_sha256":"80f899665a2ee7d87df46d4e07e115e1f418cef6e6463124ff370cbfc669389a","source":{"kind":"arxiv","id":"2310.09263","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09263","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09263v1","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09263","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"pith_short_12","alias_value":"QD4JSZS2F3T5","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"pith_short_16","alias_value":"QD4JSZS2F3T5Q7PU","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"pith_short_8","alias_value":"QD4JSZS2","created_at":"2026-07-05T07:00:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QD4JSZS2F3T5Q7PUNVHAPYIV4H","target":"record","payload":{"canonical_record":{"source":{"id":"2310.09263","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T17:20:56Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"0abd45aa1eb7cf01be049eeef16d223caea674d1d84e8cbeff9bce09c4e9f289","abstract_canon_sha256":"bace71ce3c0eeabdee3878f9a21490d469dbaa80bf971537dc7db654c2245353"},"schema_version":"1.0"},"canonical_sha256":"80f899665a2ee7d87df46d4e07e115e1f418cef6e6463124ff370cbfc669389a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:42.013267Z","signature_b64":"nay7ERcXwqfxBKhCOPuSKw5aH9WlppOTtcqTlB9lbFRiW6D6yWM+qaQQYztAAakrV/pSOuI+QltQXSxcZJYZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80f899665a2ee7d87df46d4e07e115e1f418cef6e6463124ff370cbfc669389a","last_reissued_at":"2026-07-05T07:00:42.012718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:42.012718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.09263","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":"2026-07-05T07:00:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xi/Oriw72EVt3IpqVeVm6oqmTuvzZizc1rZaNKWx5zLn3C/mtf21uepSEwo0KKBK83rnyRuM5Xr7oMjX+1EsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:12:48.252008Z"},"content_sha256":"a61823ca3c53c6cf3f0cad1d1124e19ad15b4d7349072d7e88d67b625bbe814c","schema_version":"1.0","event_id":"sha256:a61823ca3c53c6cf3f0cad1d1124e19ad15b4d7349072d7e88d67b625bbe814c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QD4JSZS2F3T5Q7PUNVHAPYIV4H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Table-GPT: Table-tuned GPT for Diverse Table Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Danielle Rifinski Fainman, Dongmei Zhang, Dror Yashar, Haidong Zhang, Peng Li, Song Ge, Surajit Chaudhuri, Weiwei Cui, Yeye He","submitted_at":"2023-10-13T17:20:56Z","abstract_excerpt":"Language models, such as GPT-3.5 and ChatGPT, demonstrate remarkable abilities to follow diverse human instructions and perform a wide range of tasks. However, when probing language models using a range of basic table-understanding tasks, we observe that today's language models are still sub-optimal in many table-related tasks, likely because they are pre-trained predominantly on \\emph{one-dimensional} natural-language texts, whereas relational tables are \\emph{two-dimensional} objects.\n  In this work, we propose a new \"\\emph{table-tuning}\" paradigm, where we continue to train/fine-tune langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09263","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/2310.09263/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":"2026-07-05T07:00:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCZSf+H2RxuvT87HkThmKdiZaTz1ZOvFXSYlx9ilcRFAA1KJXc1gv9us/nMiDDB4ytoyg3cYcZIc6ggHheBmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:12:48.252397Z"},"content_sha256":"4c0f72dd72cbd21f7edb22a59408319767e5c71362a5754467d304a251edccfb","schema_version":"1.0","event_id":"sha256:4c0f72dd72cbd21f7edb22a59408319767e5c71362a5754467d304a251edccfb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QD4JSZS2F3T5Q7PUNVHAPYIV4H/bundle.json","state_url":"https://pith.science/pith/QD4JSZS2F3T5Q7PUNVHAPYIV4H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QD4JSZS2F3T5Q7PUNVHAPYIV4H/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":"2026-07-06T23:12:48Z","links":{"resolver":"https://pith.science/pith/QD4JSZS2F3T5Q7PUNVHAPYIV4H","bundle":"https://pith.science/pith/QD4JSZS2F3T5Q7PUNVHAPYIV4H/bundle.json","state":"https://pith.science/pith/QD4JSZS2F3T5Q7PUNVHAPYIV4H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QD4JSZS2F3T5Q7PUNVHAPYIV4H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QD4JSZS2F3T5Q7PUNVHAPYIV4H","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":"bace71ce3c0eeabdee3878f9a21490d469dbaa80bf971537dc7db654c2245353","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T17:20:56Z","title_canon_sha256":"0abd45aa1eb7cf01be049eeef16d223caea674d1d84e8cbeff9bce09c4e9f289"},"schema_version":"1.0","source":{"id":"2310.09263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09263","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09263v1","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09263","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"pith_short_12","alias_value":"QD4JSZS2F3T5","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"pith_short_16","alias_value":"QD4JSZS2F3T5Q7PU","created_at":"2026-07-05T07:00:42Z"},{"alias_kind":"pith_short_8","alias_value":"QD4JSZS2","created_at":"2026-07-05T07:00:42Z"}],"graph_snapshots":[{"event_id":"sha256:4c0f72dd72cbd21f7edb22a59408319767e5c71362a5754467d304a251edccfb","target":"graph","created_at":"2026-07-05T07:00:42Z","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/2310.09263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models, such as GPT-3.5 and ChatGPT, demonstrate remarkable abilities to follow diverse human instructions and perform a wide range of tasks. However, when probing language models using a range of basic table-understanding tasks, we observe that today's language models are still sub-optimal in many table-related tasks, likely because they are pre-trained predominantly on \\emph{one-dimensional} natural-language texts, whereas relational tables are \\emph{two-dimensional} objects.\n  In this work, we propose a new \"\\emph{table-tuning}\" paradigm, where we continue to train/fine-tune langua","authors_text":"Danielle Rifinski Fainman, Dongmei Zhang, Dror Yashar, Haidong Zhang, Peng Li, Song Ge, Surajit Chaudhuri, Weiwei Cui, Yeye He","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T17:20:56Z","title":"Table-GPT: Table-tuned GPT for Diverse Table Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09263","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:a61823ca3c53c6cf3f0cad1d1124e19ad15b4d7349072d7e88d67b625bbe814c","target":"record","created_at":"2026-07-05T07:00:42Z","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":"bace71ce3c0eeabdee3878f9a21490d469dbaa80bf971537dc7db654c2245353","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T17:20:56Z","title_canon_sha256":"0abd45aa1eb7cf01be049eeef16d223caea674d1d84e8cbeff9bce09c4e9f289"},"schema_version":"1.0","source":{"id":"2310.09263","kind":"arxiv","version":1}},"canonical_sha256":"80f899665a2ee7d87df46d4e07e115e1f418cef6e6463124ff370cbfc669389a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80f899665a2ee7d87df46d4e07e115e1f418cef6e6463124ff370cbfc669389a","first_computed_at":"2026-07-05T07:00:42.012718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:42.012718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nay7ERcXwqfxBKhCOPuSKw5aH9WlppOTtcqTlB9lbFRiW6D6yWM+qaQQYztAAakrV/pSOuI+QltQXSxcZJYZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:42.013267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.09263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a61823ca3c53c6cf3f0cad1d1124e19ad15b4d7349072d7e88d67b625bbe814c","sha256:4c0f72dd72cbd21f7edb22a59408319767e5c71362a5754467d304a251edccfb"],"state_sha256":"9824495866836ff9b58799d968c09fef464f40e9ea535e428f5cd14e55440b93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LKBZwaXCeq60GYTIltYo7GzhpkoFv7JRoeohwxSnY4EolhsvOQgUWm1QmqZ4nAFJeBhtxDvr9w7QXGFNOuzIBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:12:48.254362Z","bundle_sha256":"174395794745c607be42b24c85cac5f10ed6f50b32dcc0a1da153f458410f2f0"}}