{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SAE3SRGUE23XUFZDTNXHBNDQBN","short_pith_number":"pith:SAE3SRGU","canonical_record":{"source":{"id":"2211.03818","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-07T19:06:53Z","cross_cats_sorted":[],"title_canon_sha256":"748e173b820b0e19b0526ae32c76ec764b919665cb522332f2b5893695cd65cd","abstract_canon_sha256":"2e99543ecdbe4233bc072ff9598059f13237e568fdd8442996598c61966c15f5"},"schema_version":"1.0"},"canonical_sha256":"9009b944d426b77a17239b6e70b4700b7908a266bc7427c2ebb96faa2e7e893e","source":{"kind":"arxiv","id":"2211.03818","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.03818","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"arxiv_version","alias_value":"2211.03818v2","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03818","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"pith_short_12","alias_value":"SAE3SRGUE23X","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"pith_short_16","alias_value":"SAE3SRGUE23XUFZD","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"pith_short_8","alias_value":"SAE3SRGU","created_at":"2026-07-05T07:37:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SAE3SRGUE23XUFZDTNXHBNDQBN","target":"record","payload":{"canonical_record":{"source":{"id":"2211.03818","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-07T19:06:53Z","cross_cats_sorted":[],"title_canon_sha256":"748e173b820b0e19b0526ae32c76ec764b919665cb522332f2b5893695cd65cd","abstract_canon_sha256":"2e99543ecdbe4233bc072ff9598059f13237e568fdd8442996598c61966c15f5"},"schema_version":"1.0"},"canonical_sha256":"9009b944d426b77a17239b6e70b4700b7908a266bc7427c2ebb96faa2e7e893e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:10.181470Z","signature_b64":"/GqlvaorwkG8BLgbn3BlqcwtJhcii+O8yc9Q0SfgoLxv1pYTlINQOoMJwbzdV6UoXRy54+TnBmEhCgbL8brxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9009b944d426b77a17239b6e70b4700b7908a266bc7427c2ebb96faa2e7e893e","last_reissued_at":"2026-07-05T07:37:10.181092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:10.181092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.03818","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":"2026-07-05T07:37:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4zrIJtagEaN1FZJPdwOu3Stq4KvKdpWfluOOeRPCuBTHfadmXR+dCXTd8Za+oH0enaQ7PR+ZcL620QPzXPA7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:23:32.254287Z"},"content_sha256":"1edc615ec3bcab98a7deab07a60aa8b62197b6c72d463ee2e70041ea69fa4020","schema_version":"1.0","event_id":"sha256:1edc615ec3bcab98a7deab07a60aa8b62197b6c72d463ee2e70041ea69fa4020"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SAE3SRGUE23XUFZDTNXHBNDQBN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval augmentation of large language models for lay language generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gondy Leroy, Sheng Wang, Trevor Cohen, Wei Qiu, Yue Guo","submitted_at":"2022-11-07T19:06:53Z","abstract_excerpt":"Recent lay language generation systems have used Transformer models trained on a parallel corpus to increase health information accessibility. However, the applicability of these models is constrained by the limited size and topical breadth of available corpora. We introduce CELLS, the largest (63k pairs) and broadest-ranging (12 journals) parallel corpus for lay language generation. The abstract and the corresponding lay language summary are written by domain experts, assuring the quality of our dataset. Furthermore, qualitative evaluation of expert-authored plain language summaries has revea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03818","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/2211.03818/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":"2026-07-05T07:37:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0fvUf13r5doqE/O4uzI2aBNoRVJb0Er+ItvzP3Mc9BsFwm+WWZTQPKWUKa8KNxbkzHsn3HGwnfoUGSOG0vzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:23:32.254869Z"},"content_sha256":"2c2eb26c389177ca3361a6f9184860e215164a698f33726fec3b871e2d911878","schema_version":"1.0","event_id":"sha256:2c2eb26c389177ca3361a6f9184860e215164a698f33726fec3b871e2d911878"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SAE3SRGUE23XUFZDTNXHBNDQBN/bundle.json","state_url":"https://pith.science/pith/SAE3SRGUE23XUFZDTNXHBNDQBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SAE3SRGUE23XUFZDTNXHBNDQBN/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":"2026-08-19T18:23:32Z","links":{"resolver":"https://pith.science/pith/SAE3SRGUE23XUFZDTNXHBNDQBN","bundle":"https://pith.science/pith/SAE3SRGUE23XUFZDTNXHBNDQBN/bundle.json","state":"https://pith.science/pith/SAE3SRGUE23XUFZDTNXHBNDQBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SAE3SRGUE23XUFZDTNXHBNDQBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SAE3SRGUE23XUFZDTNXHBNDQBN","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":"2e99543ecdbe4233bc072ff9598059f13237e568fdd8442996598c61966c15f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-07T19:06:53Z","title_canon_sha256":"748e173b820b0e19b0526ae32c76ec764b919665cb522332f2b5893695cd65cd"},"schema_version":"1.0","source":{"id":"2211.03818","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.03818","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"arxiv_version","alias_value":"2211.03818v2","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03818","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"pith_short_12","alias_value":"SAE3SRGUE23X","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"pith_short_16","alias_value":"SAE3SRGUE23XUFZD","created_at":"2026-07-05T07:37:10Z"},{"alias_kind":"pith_short_8","alias_value":"SAE3SRGU","created_at":"2026-07-05T07:37:10Z"}],"graph_snapshots":[{"event_id":"sha256:2c2eb26c389177ca3361a6f9184860e215164a698f33726fec3b871e2d911878","target":"graph","created_at":"2026-07-05T07:37:10Z","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/2211.03818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent lay language generation systems have used Transformer models trained on a parallel corpus to increase health information accessibility. However, the applicability of these models is constrained by the limited size and topical breadth of available corpora. We introduce CELLS, the largest (63k pairs) and broadest-ranging (12 journals) parallel corpus for lay language generation. The abstract and the corresponding lay language summary are written by domain experts, assuring the quality of our dataset. Furthermore, qualitative evaluation of expert-authored plain language summaries has revea","authors_text":"Gondy Leroy, Sheng Wang, Trevor Cohen, Wei Qiu, Yue Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-07T19:06:53Z","title":"Retrieval augmentation of large language models for lay language generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03818","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":"sha256:1edc615ec3bcab98a7deab07a60aa8b62197b6c72d463ee2e70041ea69fa4020","target":"record","created_at":"2026-07-05T07:37:10Z","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":"2e99543ecdbe4233bc072ff9598059f13237e568fdd8442996598c61966c15f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-07T19:06:53Z","title_canon_sha256":"748e173b820b0e19b0526ae32c76ec764b919665cb522332f2b5893695cd65cd"},"schema_version":"1.0","source":{"id":"2211.03818","kind":"arxiv","version":2}},"canonical_sha256":"9009b944d426b77a17239b6e70b4700b7908a266bc7427c2ebb96faa2e7e893e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9009b944d426b77a17239b6e70b4700b7908a266bc7427c2ebb96faa2e7e893e","first_computed_at":"2026-07-05T07:37:10.181092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:10.181092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/GqlvaorwkG8BLgbn3BlqcwtJhcii+O8yc9Q0SfgoLxv1pYTlINQOoMJwbzdV6UoXRy54+TnBmEhCgbL8brxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:10.181470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.03818","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1edc615ec3bcab98a7deab07a60aa8b62197b6c72d463ee2e70041ea69fa4020","sha256:2c2eb26c389177ca3361a6f9184860e215164a698f33726fec3b871e2d911878"],"state_sha256":"6df7403c2e93c82fcc9fc9ba4a8a4e6a51ca882562b5a047cbe107a1a0d45ba7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8zRm5nNDzY1ZtV5l2YDFK40XHiapeHEaN/BZdNeZ7phheWqgc67jAinvqI2qdGuNHtmGk9bdlXAbHozKC4pVAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T18:23:32.258156Z","bundle_sha256":"3152a9dd5c2a8c1b1c42dc41be1ffb4f94583d917beae60b89a9563533b055cf"}}