{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VKIAEMZ5AQHJBWFCMGNPF2ISHL","short_pith_number":"pith:VKIAEMZ5","canonical_record":{"source":{"id":"2402.11734","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2024-02-18T23:19:21Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"214621887d91f98eeabcda85be1676bd266fa18846d0fe279c49cf1fc45ec54e","abstract_canon_sha256":"44c630ddcd1e91d6a91c666674863182414f5e6097832a5cb1789ed96866720d"},"schema_version":"1.0"},"canonical_sha256":"aa9002333d040e90d8a2619af2e9123ac46c62eee6597cfdbe6989e0179f7c64","source":{"kind":"arxiv","id":"2402.11734","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11734","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11734v2","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11734","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"VKIAEMZ5AQHJ","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"VKIAEMZ5AQHJBWFC","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"VKIAEMZ5","created_at":"2026-07-05T08:00:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VKIAEMZ5AQHJBWFCMGNPF2ISHL","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11734","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2024-02-18T23:19:21Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"214621887d91f98eeabcda85be1676bd266fa18846d0fe279c49cf1fc45ec54e","abstract_canon_sha256":"44c630ddcd1e91d6a91c666674863182414f5e6097832a5cb1789ed96866720d"},"schema_version":"1.0"},"canonical_sha256":"aa9002333d040e90d8a2619af2e9123ac46c62eee6597cfdbe6989e0179f7c64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:01.640395Z","signature_b64":"8tKRme6y6lYmAJ3T6ZgrlDIwQPjrluzIP6aMIR0vaxgzvSVhQrRa0hTUyAJw9tQIPYWn3oX5U4VNsiNgAj1XDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa9002333d040e90d8a2619af2e9123ac46c62eee6597cfdbe6989e0179f7c64","last_reissued_at":"2026-07-05T08:00:01.639971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:01.639971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11734","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G5j7RfIvz/b68kD9Lx8QmuX4j6v4ddpIGQ0t8L9wC0aq1YpzfTYbgapXhdEX+vm2bwinpTbrFKn8tydxTTuvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:45:05.834704Z"},"content_sha256":"ce7557ba8fa7064e14507b7b818e7fa976d6b1987573166ee67580a966047add","schema_version":"1.0","event_id":"sha256:ce7557ba8fa7064e14507b7b818e7fa976d6b1987573166ee67580a966047add"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VKIAEMZ5AQHJBWFCMGNPF2ISHL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Solving Data-centric Tasks using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.PL","authors_text":"Advait Sarkar, Andrew D. Gordon, Benjamin Zorn, Brian Slininger, Carina Suzana Negreanu, Christian Poelitz, Elnaz Nouri, Jack Williams, Jos\\'e Cambronero, Nadia Polikarpova, Neil Toronto, Shraddha Barke, Vu Le","submitted_at":"2024-02-18T23:19:21Z","abstract_excerpt":"Large language models (LLMs) are rapidly replacing help forums like StackOverflow, and are especially helpful for non-professional programmers and end users. These users are often interested in data-centric tasks, such as spreadsheet manipulation and data wrangling, which are hard to solve if the intent is only communicated using a natural-language description, without including the data. But how do we decide how much data and which data to include in the prompt? This paper makes two contributions towards answering this question. First, we create a dataset of real-world NL-to-code tasks manipu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11734","kind":"arxiv","version":2},"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/2402.11734/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":"2026-07-05T08:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/7UfYV8y89cc3bkmxkNFeGIWOzrNpVuDitbQIgBRCT1w7qr5Qau9GR6p25bNW8rKZc93xKuiAliGCspYkV8hDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:45:05.835078Z"},"content_sha256":"d3910688931de45a5fe8276fc231bfb99dbe0260cce92bc6d5ad3886d50e5e4e","schema_version":"1.0","event_id":"sha256:d3910688931de45a5fe8276fc231bfb99dbe0260cce92bc6d5ad3886d50e5e4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VKIAEMZ5AQHJBWFCMGNPF2ISHL/bundle.json","state_url":"https://pith.science/pith/VKIAEMZ5AQHJBWFCMGNPF2ISHL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VKIAEMZ5AQHJBWFCMGNPF2ISHL/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":"2026-07-07T12:45:05Z","links":{"resolver":"https://pith.science/pith/VKIAEMZ5AQHJBWFCMGNPF2ISHL","bundle":"https://pith.science/pith/VKIAEMZ5AQHJBWFCMGNPF2ISHL/bundle.json","state":"https://pith.science/pith/VKIAEMZ5AQHJBWFCMGNPF2ISHL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VKIAEMZ5AQHJBWFCMGNPF2ISHL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VKIAEMZ5AQHJBWFCMGNPF2ISHL","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":"44c630ddcd1e91d6a91c666674863182414f5e6097832a5cb1789ed96866720d","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2024-02-18T23:19:21Z","title_canon_sha256":"214621887d91f98eeabcda85be1676bd266fa18846d0fe279c49cf1fc45ec54e"},"schema_version":"1.0","source":{"id":"2402.11734","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11734","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11734v2","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11734","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"VKIAEMZ5AQHJ","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"VKIAEMZ5AQHJBWFC","created_at":"2026-07-05T08:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"VKIAEMZ5","created_at":"2026-07-05T08:00:01Z"}],"graph_snapshots":[{"event_id":"sha256:d3910688931de45a5fe8276fc231bfb99dbe0260cce92bc6d5ad3886d50e5e4e","target":"graph","created_at":"2026-07-05T08:00:01Z","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/2402.11734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are rapidly replacing help forums like StackOverflow, and are especially helpful for non-professional programmers and end users. These users are often interested in data-centric tasks, such as spreadsheet manipulation and data wrangling, which are hard to solve if the intent is only communicated using a natural-language description, without including the data. But how do we decide how much data and which data to include in the prompt? This paper makes two contributions towards answering this question. First, we create a dataset of real-world NL-to-code tasks manipu","authors_text":"Advait Sarkar, Andrew D. Gordon, Benjamin Zorn, Brian Slininger, Carina Suzana Negreanu, Christian Poelitz, Elnaz Nouri, Jack Williams, Jos\\'e Cambronero, Nadia Polikarpova, Neil Toronto, Shraddha Barke, Vu Le","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2024-02-18T23:19:21Z","title":"Solving Data-centric Tasks using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11734","kind":"arxiv","version":2},"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:ce7557ba8fa7064e14507b7b818e7fa976d6b1987573166ee67580a966047add","target":"record","created_at":"2026-07-05T08:00:01Z","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":"44c630ddcd1e91d6a91c666674863182414f5e6097832a5cb1789ed96866720d","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2024-02-18T23:19:21Z","title_canon_sha256":"214621887d91f98eeabcda85be1676bd266fa18846d0fe279c49cf1fc45ec54e"},"schema_version":"1.0","source":{"id":"2402.11734","kind":"arxiv","version":2}},"canonical_sha256":"aa9002333d040e90d8a2619af2e9123ac46c62eee6597cfdbe6989e0179f7c64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa9002333d040e90d8a2619af2e9123ac46c62eee6597cfdbe6989e0179f7c64","first_computed_at":"2026-07-05T08:00:01.639971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:01.639971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8tKRme6y6lYmAJ3T6ZgrlDIwQPjrluzIP6aMIR0vaxgzvSVhQrRa0hTUyAJw9tQIPYWn3oX5U4VNsiNgAj1XDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:01.640395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11734","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce7557ba8fa7064e14507b7b818e7fa976d6b1987573166ee67580a966047add","sha256:d3910688931de45a5fe8276fc231bfb99dbe0260cce92bc6d5ad3886d50e5e4e"],"state_sha256":"42d1720ec182cd992ac20cd6a3a683e1a32a8362c518efbea260d844457f8b46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EtA74XB39jkgB6ERbyyJuAuh+dziMqFa0iOzq88sLYFTVEl0zwQKb9K7aKmDkMHkasFNxPAZWRNQ/nLDAgdeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:45:05.837094Z","bundle_sha256":"d0a1d84aa726b46e6055efac4469e91b55d040c89135ff7ee8e58732f7cc5485"}}