{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GSNQCFME4BZ2JU2O3ANHWDSVNR","short_pith_number":"pith:GSNQCFME","canonical_record":{"source":{"id":"2306.13986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-24T14:42:43Z","cross_cats_sorted":[],"title_canon_sha256":"aa68e417dbb4f4375142d3435e804f2299982ff074acfe6e69890b08bf96ca31","abstract_canon_sha256":"738274398cf512a0bf31469db04577109c583fb937436114f54bce8bb0942b18"},"schema_version":"1.0"},"canonical_sha256":"349b011584e073a4d34ed81a7b0e556c69a278a2f22ff13d0283d2bcb71265f9","source":{"kind":"arxiv","id":"2306.13986","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13986","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13986v1","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13986","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"GSNQCFME4BZ2","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"GSNQCFME4BZ2JU2O","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"GSNQCFME","created_at":"2026-07-05T06:24:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GSNQCFME4BZ2JU2O3ANHWDSVNR","target":"record","payload":{"canonical_record":{"source":{"id":"2306.13986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-24T14:42:43Z","cross_cats_sorted":[],"title_canon_sha256":"aa68e417dbb4f4375142d3435e804f2299982ff074acfe6e69890b08bf96ca31","abstract_canon_sha256":"738274398cf512a0bf31469db04577109c583fb937436114f54bce8bb0942b18"},"schema_version":"1.0"},"canonical_sha256":"349b011584e073a4d34ed81a7b0e556c69a278a2f22ff13d0283d2bcb71265f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:18.665710Z","signature_b64":"rGbRs1RNsRi2rAnQKKjPwB+WYzXJ7NzRQXQ3XYE9c8AdX2GNPn0LClPiVrgzBrW5cIJbxjqdIukw33aAbFUOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"349b011584e073a4d34ed81a7b0e556c69a278a2f22ff13d0283d2bcb71265f9","last_reissued_at":"2026-07-05T06:24:18.665321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:18.665321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.13986","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":"2026-07-05T06:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"918IHUYopD2UVS+94/QdkkgQdtyMe1rOPCX3dNq/ePi5ANmduGOnCG5/fSa51JUPlWXz/oI5qfUCGC6uDIKsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:38:48.057869Z"},"content_sha256":"c82b9f99acff9853aaf78e86944697567e474f0483699a60c200494ef2047bcc","schema_version":"1.0","event_id":"sha256:c82b9f99acff9853aaf78e86944697567e474f0483699a60c200494ef2047bcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GSNQCFME4BZ2JU2O3ANHWDSVNR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models as Sous Chefs: Revising Recipes with GPT-3","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alyssa Hwang, Bryan Li, Dan Roth, Zhaoyi Hou","submitted_at":"2023-06-24T14:42:43Z","abstract_excerpt":"With their remarkably improved text generation and prompting capabilities, large language models can adapt existing written information into forms that are easier to use and understand. In our work, we focus on recipes as an example of complex, diverse, and widely used instructions. We develop a prompt grounded in the original recipe and ingredients list that breaks recipes down into simpler steps. We apply this prompt to recipes from various world cuisines, and experiment with several large language models (LLMs), finding best results with GPT-3.5. We also contribute an Amazon Mechanical Turk"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13986","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/2306.13986/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":"2026-07-05T06:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nlhv6fF82tMGkMTZOT3VR7KWZyeniVnATWzjkcea4QenoyDHhEV7wQX6ayixuE0qU9RLSH8UtPSgBBc1MGhzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:38:48.058735Z"},"content_sha256":"ade3527de6422fade9f3b15d0244e37b137bdcb559c798f99c6c86781f34da83","schema_version":"1.0","event_id":"sha256:ade3527de6422fade9f3b15d0244e37b137bdcb559c798f99c6c86781f34da83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GSNQCFME4BZ2JU2O3ANHWDSVNR/bundle.json","state_url":"https://pith.science/pith/GSNQCFME4BZ2JU2O3ANHWDSVNR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GSNQCFME4BZ2JU2O3ANHWDSVNR/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":"2026-08-08T13:38:48Z","links":{"resolver":"https://pith.science/pith/GSNQCFME4BZ2JU2O3ANHWDSVNR","bundle":"https://pith.science/pith/GSNQCFME4BZ2JU2O3ANHWDSVNR/bundle.json","state":"https://pith.science/pith/GSNQCFME4BZ2JU2O3ANHWDSVNR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GSNQCFME4BZ2JU2O3ANHWDSVNR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GSNQCFME4BZ2JU2O3ANHWDSVNR","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":"738274398cf512a0bf31469db04577109c583fb937436114f54bce8bb0942b18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-24T14:42:43Z","title_canon_sha256":"aa68e417dbb4f4375142d3435e804f2299982ff074acfe6e69890b08bf96ca31"},"schema_version":"1.0","source":{"id":"2306.13986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13986","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13986v1","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13986","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"GSNQCFME4BZ2","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"GSNQCFME4BZ2JU2O","created_at":"2026-07-05T06:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"GSNQCFME","created_at":"2026-07-05T06:24:18Z"}],"graph_snapshots":[{"event_id":"sha256:ade3527de6422fade9f3b15d0244e37b137bdcb559c798f99c6c86781f34da83","target":"graph","created_at":"2026-07-05T06:24:18Z","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/2306.13986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With their remarkably improved text generation and prompting capabilities, large language models can adapt existing written information into forms that are easier to use and understand. In our work, we focus on recipes as an example of complex, diverse, and widely used instructions. We develop a prompt grounded in the original recipe and ingredients list that breaks recipes down into simpler steps. We apply this prompt to recipes from various world cuisines, and experiment with several large language models (LLMs), finding best results with GPT-3.5. We also contribute an Amazon Mechanical Turk","authors_text":"Alyssa Hwang, Bryan Li, Dan Roth, Zhaoyi Hou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-24T14:42:43Z","title":"Large Language Models as Sous Chefs: Revising Recipes with GPT-3"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13986","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:c82b9f99acff9853aaf78e86944697567e474f0483699a60c200494ef2047bcc","target":"record","created_at":"2026-07-05T06:24:18Z","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":"738274398cf512a0bf31469db04577109c583fb937436114f54bce8bb0942b18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-24T14:42:43Z","title_canon_sha256":"aa68e417dbb4f4375142d3435e804f2299982ff074acfe6e69890b08bf96ca31"},"schema_version":"1.0","source":{"id":"2306.13986","kind":"arxiv","version":1}},"canonical_sha256":"349b011584e073a4d34ed81a7b0e556c69a278a2f22ff13d0283d2bcb71265f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"349b011584e073a4d34ed81a7b0e556c69a278a2f22ff13d0283d2bcb71265f9","first_computed_at":"2026-07-05T06:24:18.665321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:18.665321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rGbRs1RNsRi2rAnQKKjPwB+WYzXJ7NzRQXQ3XYE9c8AdX2GNPn0LClPiVrgzBrW5cIJbxjqdIukw33aAbFUOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:18.665710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.13986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c82b9f99acff9853aaf78e86944697567e474f0483699a60c200494ef2047bcc","sha256:ade3527de6422fade9f3b15d0244e37b137bdcb559c798f99c6c86781f34da83"],"state_sha256":"27dee9c91aef394ccb1b103dd12bb7065f26f3d59d4b388564c7fc1e500bcff7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xFCixxE6ixW2S+HHfreuKuKH8KgkvmZgFdgzO4SvDa2FcNrT8o5QH7xdQuharq6TOldhAjblYZuQaIySMtCZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:38:48.071553Z","bundle_sha256":"a0c63771bc80951e1f7de31c85b1d219f9a6617595c8af7800ecb92bac3211b7"}}