{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7HSNS7NGBXRIOM4CQRXQGFDLZZ","short_pith_number":"pith:7HSNS7NG","canonical_record":{"source":{"id":"2401.08420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T15:07:09Z","cross_cats_sorted":[],"title_canon_sha256":"57e1d3cb0e223041bff3fd2a19983b56e049b0135c23269f775f6bbf794bf257","abstract_canon_sha256":"793feeed1aceb397abd426f823cf0dee63e9cdac0b38f17ddccfa2966b3014e7"},"schema_version":"1.0"},"canonical_sha256":"f9e4d97da60de2873382846f03146bce5c9d13e31026a0e2cfa07d8c5e1c0e57","source":{"kind":"arxiv","id":"2401.08420","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08420","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08420v1","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08420","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"7HSNS7NGBXRI","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"7HSNS7NGBXRIOM4C","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"7HSNS7NG","created_at":"2026-07-05T07:34:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7HSNS7NGBXRIOM4CQRXQGFDLZZ","target":"record","payload":{"canonical_record":{"source":{"id":"2401.08420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T15:07:09Z","cross_cats_sorted":[],"title_canon_sha256":"57e1d3cb0e223041bff3fd2a19983b56e049b0135c23269f775f6bbf794bf257","abstract_canon_sha256":"793feeed1aceb397abd426f823cf0dee63e9cdac0b38f17ddccfa2966b3014e7"},"schema_version":"1.0"},"canonical_sha256":"f9e4d97da60de2873382846f03146bce5c9d13e31026a0e2cfa07d8c5e1c0e57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:11.774996Z","signature_b64":"FlEy/Ssy5a6caVYIX3eRhW/VFgz5zSnsjOLCsPEPQtQdycm1TpT+KUiVY3OomzLwp5HufubrzpZn5SY11ivgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9e4d97da60de2873382846f03146bce5c9d13e31026a0e2cfa07d8c5e1c0e57","last_reissued_at":"2026-07-05T07:34:11.774632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:11.774632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.08420","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":"2026-07-05T07:34:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4noGAqTP/2XlNcFciQp19tOmInHxFhizsY2weNtqV8tufhBPt6NKAOq5txJVC5SBLBj+e+tH8fCsEIl+uw9XDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:34:15.893156Z"},"content_sha256":"ef03e594d00b545c4c2116cc58897bd518362e25a7c77753de8193484cc25476","schema_version":"1.0","event_id":"sha256:ef03e594d00b545c4c2116cc58897bd518362e25a7c77753de8193484cc25476"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7HSNS7NGBXRIOM4CQRXQGFDLZZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ask the experts: sourcing high-quality datasets for nutritional counselling through Human-AI collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniele Riboni, Diego Reforgiato Recupero, Ehud Reiter, Simone Balloccu, Vivek Kumar","submitted_at":"2024-01-16T15:07:09Z","abstract_excerpt":"Large Language Models (LLMs), with their flexible generation abilities, can be powerful data sources in domains with few or no available corpora. However, problems like hallucinations and biases limit such applications. In this case study, we pick nutrition counselling, a domain lacking any public resource, and show that high-quality datasets can be gathered by combining LLMs, crowd-workers and nutrition experts. We first crowd-source and cluster a novel dataset of diet-related issues, then work with experts to prompt ChatGPT into producing related supportive text. Finally, we let the experts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08420","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/2401.08420/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":"2026-07-05T07:34:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a4niPtaEp0tWQP2OpV+o1Mv45ojrA3WdC3uFhZIsgn63fDFG6Ar1uHSKI6AOMzO2RLAzVNiJfCSG6/y38lnXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:34:15.893659Z"},"content_sha256":"49d07f80b28e3d5313e91de422e135e459701f464c083e0b3b1fb0f8c8d6336a","schema_version":"1.0","event_id":"sha256:49d07f80b28e3d5313e91de422e135e459701f464c083e0b3b1fb0f8c8d6336a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7HSNS7NGBXRIOM4CQRXQGFDLZZ/bundle.json","state_url":"https://pith.science/pith/7HSNS7NGBXRIOM4CQRXQGFDLZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7HSNS7NGBXRIOM4CQRXQGFDLZZ/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":"2026-08-17T02:34:15Z","links":{"resolver":"https://pith.science/pith/7HSNS7NGBXRIOM4CQRXQGFDLZZ","bundle":"https://pith.science/pith/7HSNS7NGBXRIOM4CQRXQGFDLZZ/bundle.json","state":"https://pith.science/pith/7HSNS7NGBXRIOM4CQRXQGFDLZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7HSNS7NGBXRIOM4CQRXQGFDLZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7HSNS7NGBXRIOM4CQRXQGFDLZZ","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":"793feeed1aceb397abd426f823cf0dee63e9cdac0b38f17ddccfa2966b3014e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T15:07:09Z","title_canon_sha256":"57e1d3cb0e223041bff3fd2a19983b56e049b0135c23269f775f6bbf794bf257"},"schema_version":"1.0","source":{"id":"2401.08420","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08420","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08420v1","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08420","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"7HSNS7NGBXRI","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"7HSNS7NGBXRIOM4C","created_at":"2026-07-05T07:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"7HSNS7NG","created_at":"2026-07-05T07:34:11Z"}],"graph_snapshots":[{"event_id":"sha256:49d07f80b28e3d5313e91de422e135e459701f464c083e0b3b1fb0f8c8d6336a","target":"graph","created_at":"2026-07-05T07:34:11Z","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/2401.08420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), with their flexible generation abilities, can be powerful data sources in domains with few or no available corpora. However, problems like hallucinations and biases limit such applications. In this case study, we pick nutrition counselling, a domain lacking any public resource, and show that high-quality datasets can be gathered by combining LLMs, crowd-workers and nutrition experts. We first crowd-source and cluster a novel dataset of diet-related issues, then work with experts to prompt ChatGPT into producing related supportive text. Finally, we let the experts ","authors_text":"Daniele Riboni, Diego Reforgiato Recupero, Ehud Reiter, Simone Balloccu, Vivek Kumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T15:07:09Z","title":"Ask the experts: sourcing high-quality datasets for nutritional counselling through Human-AI collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08420","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:ef03e594d00b545c4c2116cc58897bd518362e25a7c77753de8193484cc25476","target":"record","created_at":"2026-07-05T07:34:11Z","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":"793feeed1aceb397abd426f823cf0dee63e9cdac0b38f17ddccfa2966b3014e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T15:07:09Z","title_canon_sha256":"57e1d3cb0e223041bff3fd2a19983b56e049b0135c23269f775f6bbf794bf257"},"schema_version":"1.0","source":{"id":"2401.08420","kind":"arxiv","version":1}},"canonical_sha256":"f9e4d97da60de2873382846f03146bce5c9d13e31026a0e2cfa07d8c5e1c0e57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9e4d97da60de2873382846f03146bce5c9d13e31026a0e2cfa07d8c5e1c0e57","first_computed_at":"2026-07-05T07:34:11.774632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:11.774632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FlEy/Ssy5a6caVYIX3eRhW/VFgz5zSnsjOLCsPEPQtQdycm1TpT+KUiVY3OomzLwp5HufubrzpZn5SY11ivgBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:11.774996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08420","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef03e594d00b545c4c2116cc58897bd518362e25a7c77753de8193484cc25476","sha256:49d07f80b28e3d5313e91de422e135e459701f464c083e0b3b1fb0f8c8d6336a"],"state_sha256":"13e842ce488d759082509b96c241b93914e529ddbdfb7c666b38be5420a2c0be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQn5B/zGQBQfb2OC9K8+KcAxz1tf2vKAGJ0q5NCZ3hB4Sr0L+xPxkHKZMq0wRJUNu1+jZswbKVNP5IDVRksGAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T02:34:15.898506Z","bundle_sha256":"822e4aa78f320dbd4c3bf84d60f2f0e70efa1c0314c6e2f147581fc085d61779"}}