{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UMBJWU2RYZTSBD7UJSSOYXSXM6","short_pith_number":"pith:UMBJWU2R","canonical_record":{"source":{"id":"2605.15213","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-11T03:40:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a453835240ef2fd95c34db836682ecfb05e8fab3e5d707b3bc1359e26a681d51","abstract_canon_sha256":"7d01138732b9ab22260880abb929db8c8ca59cdf6e20688e27b2faa34252ca40"},"schema_version":"1.0"},"canonical_sha256":"a3029b5351c667208ff44ca4ec5e5767ba27d4f18e2cccf9308fc6f5742919db","source":{"kind":"arxiv","id":"2605.15213","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15213","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15213v1","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15213","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"UMBJWU2RYZTS","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_16","alias_value":"UMBJWU2RYZTSBD7U","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_8","alias_value":"UMBJWU2R","created_at":"2026-05-20T00:00:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UMBJWU2RYZTSBD7UJSSOYXSXM6","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15213","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-11T03:40:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a453835240ef2fd95c34db836682ecfb05e8fab3e5d707b3bc1359e26a681d51","abstract_canon_sha256":"7d01138732b9ab22260880abb929db8c8ca59cdf6e20688e27b2faa34252ca40"},"schema_version":"1.0"},"canonical_sha256":"a3029b5351c667208ff44ca4ec5e5767ba27d4f18e2cccf9308fc6f5742919db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:46.538057Z","signature_b64":"0XoX5zCks8iAzgTcsA6d9GXBcwc58gmwnmwh7BPnX6FcIyuHhtsswJ8DzBUa1Eb7U+74hPHcadIqQCzaPx/mBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3029b5351c667208ff44ca4ec5e5767ba27d4f18e2cccf9308fc6f5742919db","last_reissued_at":"2026-05-20T00:00:46.537088Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:46.537088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15213","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":"2026-05-20T00:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLJfPzXbo0XsJ2MjvBT1xpS8HxsR4pllwVKlN8St5dgpx6K8ulbq11Ed74YjCaPlNLpeMY+xX+hxfr2nGh6iBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:21:38.755700Z"},"content_sha256":"4580de156531d4aa2926f2cbfc9abd9178014753de667d6edbcc4ffc641967d9","schema_version":"1.0","event_id":"sha256:4580de156531d4aa2926f2cbfc9abd9178014753de667d6edbcc4ffc641967d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UMBJWU2RYZTSBD7UJSSOYXSXM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An LLM-RAG Approach for Healthy Eating Index-Informed Personalized Food Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An LLM-RAG system anchored in national nutrition data improves simulated Healthy Eating Index scores by 6.45 points on average.","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Azlan Zahid, Grace Melo Guerrero, Rodolfo M. Nayga Jr., Yanjie Yang, Yibin Wang","submitted_at":"2026-05-11T03:40:17Z","abstract_excerpt":"Diet quality is a leading determinant of chronic disease risk. Advances in artificial intelligence (AI) have enabled food recommendation systems to adapt suggestions to user preferences and health goals. However, most current systems rely on loosely curated food databases and provide limited connection to a validated index. In this study, we propose a Healthy Eating Index (HEI) informed retrieval-augmented generation (RAG) framework that combines standardized nutrition databases with large language models (LLMs) for personalized food recommendations. Our proposed method anchors retrieval in th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The simulation results showed a mean HEI improvement of 6.45, with the proportion of users HEI over 50 increasing from 45.12 to 61.26. Our findings suggest that the proposed LLM-RAG-based AI systems can support more precise, explainable, and personalized nutrition guidance to improve diet quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The simulation accurately models real-world user responses and dietary behaviors, and that the embedding space from FPED descriptions effectively captures nutritional relevance for retrieval and HEI impact estimation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"An LLM-RAG framework anchored in NHANES and FPED databases generates personalized food recommendations that improve simulated HEI scores by an average of 6.45 points.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An LLM-RAG system anchored in national nutrition data improves simulated Healthy Eating Index scores by 6.45 points on average.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0d31d9aa576c0fe89e6120f62b3eaf76ccc73b6470a4448a58947b510d5634ff"},"source":{"id":"2605.15213","kind":"arxiv","version":1},"verdict":{"id":"74d85b0d-eccf-44e5-8d57-0eb74763d509","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:56:35.010575Z","strongest_claim":"The simulation results showed a mean HEI improvement of 6.45, with the proportion of users HEI over 50 increasing from 45.12 to 61.26. Our findings suggest that the proposed LLM-RAG-based AI systems can support more precise, explainable, and personalized nutrition guidance to improve diet quality.","one_line_summary":"An LLM-RAG framework anchored in NHANES and FPED databases generates personalized food recommendations that improve simulated HEI scores by an average of 6.45 points.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The simulation accurately models real-world user responses and dietary behaviors, and that the embedding space from FPED descriptions effectively captures nutritional relevance for retrieval and HEI impact estimation.","pith_extraction_headline":"An LLM-RAG system anchored in national nutrition data improves simulated Healthy Eating Index scores by 6.45 points on average."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15213/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T18:10:18.387487Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:18.644898Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T16:33:27.104654Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0893e5b1182294a6994ffc7b7d0ff349be0d4d4b3f2d557b5c8f4de430a049da"},"references":{"count":7,"sample":[{"doi":"10.22434/ifamr1131","year":2025,"title":"Adhikari, S., & McFadden, B. R. (2025). Bridging taste and health: The role of machine learning in consumer food selection. International Food and Agribusiness Management Review, 28(2), 441–456. https","work_id":"f35ec22f-db31-4824-b22d-4a2f84a1a458","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.3390/nu13041046","year":2025,"title":"https://doi.org/10.3390/nu13041046 Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazaré, P.-E., Lomeli, M., Hosseini, L., & Jégou, H. (2025). THE FAISS LIBRARY . IEEE Transactions on Big","work_id":"2fcbd7ed-f665-4a23-acd6-e392c9d89f28","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.jand.2023.05.015","year":2023,"title":"S., Ajay, A., Shams, R., & Dash, K","work_id":"9b59b6de-54b9-449b-975e-9b421d36d9e6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1186/s41110-025-00360-4","year":2023,"title":"https://doi.org/10.1186/s41110-025-00360-4 Silva, P., Araújo, R., Lopes, F., & Ray, S. (2023). Nutrition and Food Literacy: Framing the Challenges to Health Communication. Nutrients, 15(22),","work_id":"02be523b-6a22-4ac9-b9dd-4038aff64cf7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.3390/nu15224708","year":2024,"title":"K., Hu, X.-H., Singh, A","work_id":"94765555-db41-47a6-8056-a43bc0b17a41","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":7,"snapshot_sha256":"833d5739a0cba5981b6779d0f06692207716e422e513e327c6066bcfc623bb83","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bb42a43769e1637a0d65e893cba3e3eef0bfbafba422673b98fc7e1a46b36861"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"74d85b0d-eccf-44e5-8d57-0eb74763d509"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E1EkfJPVm9YX6Tp11NjKc42c0I0FMRDyOwzHWfnoqHB1KR+1jBOZjb2Viy7q66Y7XJ/tZSBsxCLZCkaI3/wFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:21:38.757045Z"},"content_sha256":"7672cba29f7e01509785a019693bacfa457aee19fc1bf752ff89aae995951ea5","schema_version":"1.0","event_id":"sha256:7672cba29f7e01509785a019693bacfa457aee19fc1bf752ff89aae995951ea5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UMBJWU2RYZTSBD7UJSSOYXSXM6/bundle.json","state_url":"https://pith.science/pith/UMBJWU2RYZTSBD7UJSSOYXSXM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UMBJWU2RYZTSBD7UJSSOYXSXM6/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":"2026-06-09T02:21:38Z","links":{"resolver":"https://pith.science/pith/UMBJWU2RYZTSBD7UJSSOYXSXM6","bundle":"https://pith.science/pith/UMBJWU2RYZTSBD7UJSSOYXSXM6/bundle.json","state":"https://pith.science/pith/UMBJWU2RYZTSBD7UJSSOYXSXM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UMBJWU2RYZTSBD7UJSSOYXSXM6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UMBJWU2RYZTSBD7UJSSOYXSXM6","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":"7d01138732b9ab22260880abb929db8c8ca59cdf6e20688e27b2faa34252ca40","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-11T03:40:17Z","title_canon_sha256":"a453835240ef2fd95c34db836682ecfb05e8fab3e5d707b3bc1359e26a681d51"},"schema_version":"1.0","source":{"id":"2605.15213","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15213","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15213v1","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15213","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"UMBJWU2RYZTS","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_16","alias_value":"UMBJWU2RYZTSBD7U","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_8","alias_value":"UMBJWU2R","created_at":"2026-05-20T00:00:46Z"}],"graph_snapshots":[{"event_id":"sha256:7672cba29f7e01509785a019693bacfa457aee19fc1bf752ff89aae995951ea5","target":"graph","created_at":"2026-05-20T00:00:46Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The simulation results showed a mean HEI improvement of 6.45, with the proportion of users HEI over 50 increasing from 45.12 to 61.26. Our findings suggest that the proposed LLM-RAG-based AI systems can support more precise, explainable, and personalized nutrition guidance to improve diet quality."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The simulation accurately models real-world user responses and dietary behaviors, and that the embedding space from FPED descriptions effectively captures nutritional relevance for retrieval and HEI impact estimation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"An LLM-RAG framework anchored in NHANES and FPED databases generates personalized food recommendations that improve simulated HEI scores by an average of 6.45 points."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"An LLM-RAG system anchored in national nutrition data improves simulated Healthy Eating Index scores by 6.45 points on average."}],"snapshot_sha256":"0d31d9aa576c0fe89e6120f62b3eaf76ccc73b6470a4448a58947b510d5634ff"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bb42a43769e1637a0d65e893cba3e3eef0bfbafba422673b98fc7e1a46b36861"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:10:18.387487Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:18.644898Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T16:33:27.104654Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15213/integrity.json","findings":[],"snapshot_sha256":"0893e5b1182294a6994ffc7b7d0ff349be0d4d4b3f2d557b5c8f4de430a049da","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diet quality is a leading determinant of chronic disease risk. Advances in artificial intelligence (AI) have enabled food recommendation systems to adapt suggestions to user preferences and health goals. However, most current systems rely on loosely curated food databases and provide limited connection to a validated index. In this study, we propose a Healthy Eating Index (HEI) informed retrieval-augmented generation (RAG) framework that combines standardized nutrition databases with large language models (LLMs) for personalized food recommendations. Our proposed method anchors retrieval in th","authors_text":"Azlan Zahid, Grace Melo Guerrero, Rodolfo M. Nayga Jr., Yanjie Yang, Yibin Wang","cross_cats":["cs.AI"],"headline":"An LLM-RAG system anchored in national nutrition data improves simulated Healthy Eating Index scores by 6.45 points on average.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-11T03:40:17Z","title":"An LLM-RAG Approach for Healthy Eating Index-Informed Personalized Food Recommendations"},"references":{"count":7,"internal_anchors":0,"resolved_work":7,"sample":[{"cited_arxiv_id":"","doi":"10.22434/ifamr1131","is_internal_anchor":false,"ref_index":1,"title":"Adhikari, S., & McFadden, B. R. (2025). Bridging taste and health: The role of machine learning in consumer food selection. International Food and Agribusiness Management Review, 28(2), 441–456. https","work_id":"f35ec22f-db31-4824-b22d-4a2f84a1a458","year":2025},{"cited_arxiv_id":"","doi":"10.3390/nu13041046","is_internal_anchor":false,"ref_index":2,"title":"https://doi.org/10.3390/nu13041046 Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazaré, P.-E., Lomeli, M., Hosseini, L., & Jégou, H. (2025). THE FAISS LIBRARY . IEEE Transactions on Big","work_id":"2fcbd7ed-f665-4a23-acd6-e392c9d89f28","year":2025},{"cited_arxiv_id":"","doi":"10.1016/j.jand.2023.05.015","is_internal_anchor":false,"ref_index":3,"title":"S., Ajay, A., Shams, R., & Dash, K","work_id":"9b59b6de-54b9-449b-975e-9b421d36d9e6","year":2023},{"cited_arxiv_id":"","doi":"10.1186/s41110-025-00360-4","is_internal_anchor":false,"ref_index":4,"title":"https://doi.org/10.1186/s41110-025-00360-4 Silva, P., Araújo, R., Lopes, F., & Ray, S. (2023). Nutrition and Food Literacy: Framing the Challenges to Health Communication. Nutrients, 15(22),","work_id":"02be523b-6a22-4ac9-b9dd-4038aff64cf7","year":2023},{"cited_arxiv_id":"","doi":"10.3390/nu15224708","is_internal_anchor":false,"ref_index":5,"title":"K., Hu, X.-H., Singh, A","work_id":"94765555-db41-47a6-8056-a43bc0b17a41","year":2024}],"snapshot_sha256":"833d5739a0cba5981b6779d0f06692207716e422e513e327c6066bcfc623bb83"},"source":{"id":"2605.15213","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T17:56:35.010575Z","id":"74d85b0d-eccf-44e5-8d57-0eb74763d509","model_set":{"reader":"grok-4.3"},"one_line_summary":"An LLM-RAG framework anchored in NHANES and FPED databases generates personalized food recommendations that improve simulated HEI scores by an average of 6.45 points.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"An LLM-RAG system anchored in national nutrition data improves simulated Healthy Eating Index scores by 6.45 points on average.","strongest_claim":"The simulation results showed a mean HEI improvement of 6.45, with the proportion of users HEI over 50 increasing from 45.12 to 61.26. Our findings suggest that the proposed LLM-RAG-based AI systems can support more precise, explainable, and personalized nutrition guidance to improve diet quality.","weakest_assumption":"The simulation accurately models real-world user responses and dietary behaviors, and that the embedding space from FPED descriptions effectively captures nutritional relevance for retrieval and HEI impact estimation."}},"verdict_id":"74d85b0d-eccf-44e5-8d57-0eb74763d509"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4580de156531d4aa2926f2cbfc9abd9178014753de667d6edbcc4ffc641967d9","target":"record","created_at":"2026-05-20T00:00:46Z","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":"7d01138732b9ab22260880abb929db8c8ca59cdf6e20688e27b2faa34252ca40","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-11T03:40:17Z","title_canon_sha256":"a453835240ef2fd95c34db836682ecfb05e8fab3e5d707b3bc1359e26a681d51"},"schema_version":"1.0","source":{"id":"2605.15213","kind":"arxiv","version":1}},"canonical_sha256":"a3029b5351c667208ff44ca4ec5e5767ba27d4f18e2cccf9308fc6f5742919db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3029b5351c667208ff44ca4ec5e5767ba27d4f18e2cccf9308fc6f5742919db","first_computed_at":"2026-05-20T00:00:46.537088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:46.537088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0XoX5zCks8iAzgTcsA6d9GXBcwc58gmwnmwh7BPnX6FcIyuHhtsswJ8DzBUa1Eb7U+74hPHcadIqQCzaPx/mBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:46.538057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15213","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4580de156531d4aa2926f2cbfc9abd9178014753de667d6edbcc4ffc641967d9","sha256:7672cba29f7e01509785a019693bacfa457aee19fc1bf752ff89aae995951ea5"],"state_sha256":"f63c1147c1e34b159cce94326a370dc10e29e4ace7f76cbd6cd7bb0bf7b1bb97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kXSVLfcVcQ+rqKrxoqfKDDH0UbLyOImfVV9zgz5uP3NM7yw10fB8wddaxuCrMbTHgqLUuSsPPIniUqB9lg2VDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T02:21:38.763834Z","bundle_sha256":"76c97d4eb90126af6ae2f4e981f9ffbfc17609481414c0ccd12bf0b276a60e06"}}