{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:W7WQ6TS2CMH4PHFWT36IG7AF6W","short_pith_number":"pith:W7WQ6TS2","canonical_record":{"source":{"id":"2312.09634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-12-15T09:23:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b7c5e93ff68dd2ee57422dcb3b7bfeca97aa6d296b6b88940ee3768acb4597e","abstract_canon_sha256":"3ddc715cd1f7a9719818db39131e78d013c2f3cf23d9b8eb04d3d77bbdce203c"},"schema_version":"1.0"},"canonical_sha256":"b7ed0f4e5a130fc79cb69efc837c05f5a7bf882dd1bfc0a0ef62100899b7d8f7","source":{"kind":"arxiv","id":"2312.09634","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09634","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09634v1","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09634","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"W7WQ6TS2CMH4","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"pith_short_16","alias_value":"W7WQ6TS2CMH4PHFW","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"pith_short_8","alias_value":"W7WQ6TS2","created_at":"2026-07-05T07:24:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:W7WQ6TS2CMH4PHFWT36IG7AF6W","target":"record","payload":{"canonical_record":{"source":{"id":"2312.09634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-12-15T09:23:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b7c5e93ff68dd2ee57422dcb3b7bfeca97aa6d296b6b88940ee3768acb4597e","abstract_canon_sha256":"3ddc715cd1f7a9719818db39131e78d013c2f3cf23d9b8eb04d3d77bbdce203c"},"schema_version":"1.0"},"canonical_sha256":"b7ed0f4e5a130fc79cb69efc837c05f5a7bf882dd1bfc0a0ef62100899b7d8f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:28.488022Z","signature_b64":"lXV8JUmr2YZwYypQwnTBbNOVapeTIZRMJxf/8iEQhfLdHBboM3mjlsDHn/4HP7+I9aV4BMNxMSkNLBmNyDH1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7ed0f4e5a130fc79cb69efc837c05f5a7bf882dd1bfc0a0ef62100899b7d8f7","last_reissued_at":"2026-07-05T07:24:28.487586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:28.487586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.09634","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":"2026-07-05T07:24:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/3qF5J1cHGHH5hka4J/5jiFVobd/rnmAAgglQ0z8kWHC2d7NEIANOseMXLEBzbuaeXcQt/8ovI0ACtmx8QvGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T15:52:07.097656Z"},"content_sha256":"19e2c4c2fb5252acacacc1a140cd8a7d309cebf41188b516aa81546b7e44f5ff","schema_version":"1.0","event_id":"sha256:19e2c4c2fb5252acacacc1a140cd8a7d309cebf41188b516aa81546b7e44f5ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:W7WQ6TS2CMH4PHFWT36IG7AF6W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vectorizing string entries for data processing on tables: when are larger language models better?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"CNRS, Edouard Oyallon (MLIA, Ga\\\"el Varoquaux (SODA), ISIR, ISIR), L\\'eo Grinsztajn (SODA, MLIA, Myung Jun Kim (SODA), SU)","submitted_at":"2023-12-15T09:23:56Z","abstract_excerpt":"There are increasingly efficient data processing pipelines that work on vectors of numbers, for instance most machine learning models, or vector databases for fast similarity search. These require converting the data to numbers. While this conversion is easy for simple numerical and categorical entries, databases are strife with text entries, such as names or descriptions. In the age of large language models, what's the best strategies to vectorize tables entries, baring in mind that larger models entail more operational complexity? We study the benefits of language models in 14 analytical tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09634","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/2312.09634/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":"2026-07-05T07:24:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+3GDq3O0rIRwjI4l98FDbwHPfVR/KtthwYsb21O27UGET09LYBOKLVrioJUjOCr3H4iydhh1gbfKw6+3lwjlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T15:52:07.098121Z"},"content_sha256":"19f05c6f22451683ecccfa3885d2a494e4673154d1836094e75ebe090ac219f6","schema_version":"1.0","event_id":"sha256:19f05c6f22451683ecccfa3885d2a494e4673154d1836094e75ebe090ac219f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W7WQ6TS2CMH4PHFWT36IG7AF6W/bundle.json","state_url":"https://pith.science/pith/W7WQ6TS2CMH4PHFWT36IG7AF6W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W7WQ6TS2CMH4PHFWT36IG7AF6W/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":"2026-08-01T15:52:07Z","links":{"resolver":"https://pith.science/pith/W7WQ6TS2CMH4PHFWT36IG7AF6W","bundle":"https://pith.science/pith/W7WQ6TS2CMH4PHFWT36IG7AF6W/bundle.json","state":"https://pith.science/pith/W7WQ6TS2CMH4PHFWT36IG7AF6W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W7WQ6TS2CMH4PHFWT36IG7AF6W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:W7WQ6TS2CMH4PHFWT36IG7AF6W","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":"3ddc715cd1f7a9719818db39131e78d013c2f3cf23d9b8eb04d3d77bbdce203c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-12-15T09:23:56Z","title_canon_sha256":"3b7c5e93ff68dd2ee57422dcb3b7bfeca97aa6d296b6b88940ee3768acb4597e"},"schema_version":"1.0","source":{"id":"2312.09634","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09634","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09634v1","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09634","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"W7WQ6TS2CMH4","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"pith_short_16","alias_value":"W7WQ6TS2CMH4PHFW","created_at":"2026-07-05T07:24:28Z"},{"alias_kind":"pith_short_8","alias_value":"W7WQ6TS2","created_at":"2026-07-05T07:24:28Z"}],"graph_snapshots":[{"event_id":"sha256:19f05c6f22451683ecccfa3885d2a494e4673154d1836094e75ebe090ac219f6","target":"graph","created_at":"2026-07-05T07:24:28Z","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/2312.09634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There are increasingly efficient data processing pipelines that work on vectors of numbers, for instance most machine learning models, or vector databases for fast similarity search. These require converting the data to numbers. While this conversion is easy for simple numerical and categorical entries, databases are strife with text entries, such as names or descriptions. In the age of large language models, what's the best strategies to vectorize tables entries, baring in mind that larger models entail more operational complexity? We study the benefits of language models in 14 analytical tas","authors_text":"CNRS, Edouard Oyallon (MLIA, Ga\\\"el Varoquaux (SODA), ISIR, ISIR), L\\'eo Grinsztajn (SODA, MLIA, Myung Jun Kim (SODA), SU)","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-12-15T09:23:56Z","title":"Vectorizing string entries for data processing on tables: when are larger language models better?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09634","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":"sha256:19e2c4c2fb5252acacacc1a140cd8a7d309cebf41188b516aa81546b7e44f5ff","target":"record","created_at":"2026-07-05T07:24:28Z","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":"3ddc715cd1f7a9719818db39131e78d013c2f3cf23d9b8eb04d3d77bbdce203c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-12-15T09:23:56Z","title_canon_sha256":"3b7c5e93ff68dd2ee57422dcb3b7bfeca97aa6d296b6b88940ee3768acb4597e"},"schema_version":"1.0","source":{"id":"2312.09634","kind":"arxiv","version":1}},"canonical_sha256":"b7ed0f4e5a130fc79cb69efc837c05f5a7bf882dd1bfc0a0ef62100899b7d8f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7ed0f4e5a130fc79cb69efc837c05f5a7bf882dd1bfc0a0ef62100899b7d8f7","first_computed_at":"2026-07-05T07:24:28.487586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:28.487586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lXV8JUmr2YZwYypQwnTBbNOVapeTIZRMJxf/8iEQhfLdHBboM3mjlsDHn/4HP7+I9aV4BMNxMSkNLBmNyDH1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:28.488022Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.09634","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19e2c4c2fb5252acacacc1a140cd8a7d309cebf41188b516aa81546b7e44f5ff","sha256:19f05c6f22451683ecccfa3885d2a494e4673154d1836094e75ebe090ac219f6"],"state_sha256":"84571e8b432817db9007da75beaf000b5ac8b20ceecc0bcad6ae08fd8e973777"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lIq9nbp7I8YCW0avq66B45q7uNYq/N34c3G+GmBJYAZTXxOctfAK3DBpmf3Iair2n8/3h3n05s+YXD6uKpVQAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T15:52:07.101224Z","bundle_sha256":"340c27aac98c39ad9d73fc7560ee4a37160c37269ca35fb7066e4f474afd41d0"}}