{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EGR44RKADYK5CUXMAWLPNHKWK5","short_pith_number":"pith:EGR44RKA","canonical_record":{"source":{"id":"2206.15076","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T07:15:45Z","cross_cats_sorted":[],"title_canon_sha256":"0c1ccc38a0ff3175957e45cca1f57d9e254b05c54399738a7c317cf2b5b455d5","abstract_canon_sha256":"c2ba208586684f391d72ec058abff871d3845222c99aecc5f4d1dd87a5420f70"},"schema_version":"1.0"},"canonical_sha256":"21a3ce45401e15d152ec0596f69d56574b02dafbedf20cad951ab2712db9a99d","source":{"kind":"arxiv","id":"2206.15076","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15076","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15076v1","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15076","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"pith_short_12","alias_value":"EGR44RKADYK5","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"pith_short_16","alias_value":"EGR44RKADYK5CUXM","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"pith_short_8","alias_value":"EGR44RKA","created_at":"2026-07-05T04:36:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EGR44RKADYK5CUXMAWLPNHKWK5","target":"record","payload":{"canonical_record":{"source":{"id":"2206.15076","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T07:15:45Z","cross_cats_sorted":[],"title_canon_sha256":"0c1ccc38a0ff3175957e45cca1f57d9e254b05c54399738a7c317cf2b5b455d5","abstract_canon_sha256":"c2ba208586684f391d72ec058abff871d3845222c99aecc5f4d1dd87a5420f70"},"schema_version":"1.0"},"canonical_sha256":"21a3ce45401e15d152ec0596f69d56574b02dafbedf20cad951ab2712db9a99d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:24.973095Z","signature_b64":"Ex9RQwIZ6cIUL4nrzUEhuX130X21GsA/+NglME3M75WRQ8kCq+S5e5817udxbs3oKtvUCq7mNfwqgzKzH3qPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21a3ce45401e15d152ec0596f69d56574b02dafbedf20cad951ab2712db9a99d","last_reissued_at":"2026-07-05T04:36:24.972676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:24.972676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.15076","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":"2026-07-05T04:36:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"st1ABXGpOUWdFl+wOoxApARHjyGYQn4OA5b9jhIO425fNON4RhdyHkt3qH0lg8suBGtjyn4MJM/7KkyH9HqrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:45:16.905666Z"},"content_sha256":"301625706204ba9a715864971782945eb231f16fad5e38d0dbc74cc984900b34","schema_version":"1.0","event_id":"sha256:301625706204ba9a715864971782945eb231f16fad5e38d0dbc74cc984900b34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EGR44RKADYK5CUXMAWLPNHKWK5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Villanova del Moral, Alison Callahan, Ayush Singh, Benjamin Beilharz, Bo Wang, Daniel Le\\'on Peri\\~n\\'an, Debajyoti Datta, Fabio Barth, Gabriel Altay, Jason Alan Fries, Jenny Chim, John Michael Giorgi, Jonas Golde, Jose David Posada, Karthik Rangasai Sivaraman, Leon Weber, Marc P\\`amies, Marianna Nezhurina, Mario S\\\"anger, Matthias Samwald, Michael Cullan, Minh Chien Vu, Moritz Freidank, Myungsun Kang, Natasha Seelam, Nathan Dahlberg, Nicholas Michio Broad, Patrick Haller, Robert Martin, Ruisi Su, Samuel Cahyawijaya, Samuele Garda, Shamik Bose, Shlok S Deshmukh, Shubhanshu Mishra, Sid Kiblawi, Simon Ott, Stella Biderman, Stephen Bach, Th\\'eo Gigant, Trishala Neeraj, Wojciech Kusa, Yanis Labrak","submitted_at":"2022-06-30T07:15:45Z","abstract_excerpt":"Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization by transforming existing, supervised datasets into a diversity of novel pretraining tasks, highlighting the benefits of meta-dataset curation. While successful in general-domain text, translating these data-centric approaches to biomedical language modeling remains challenging, as labeled biomedical datasets are significantly underrepresented in popular data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15076","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/2206.15076/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":"2026-07-05T04:36:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dHCATV6PHNd1Kc/1mGNiyjvHh5XLHcYlQMaWAk0NeZA9pLFWz++sb1TMxfj3mOrguUHu+mciCI2ZPsfYYmo1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:45:16.906470Z"},"content_sha256":"b37941d4a0da7254cd1d3839f83c852763ec1fa749c461e8d9c704b4be02dbdc","schema_version":"1.0","event_id":"sha256:b37941d4a0da7254cd1d3839f83c852763ec1fa749c461e8d9c704b4be02dbdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EGR44RKADYK5CUXMAWLPNHKWK5/bundle.json","state_url":"https://pith.science/pith/EGR44RKADYK5CUXMAWLPNHKWK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EGR44RKADYK5CUXMAWLPNHKWK5/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":"2026-08-04T12:45:16Z","links":{"resolver":"https://pith.science/pith/EGR44RKADYK5CUXMAWLPNHKWK5","bundle":"https://pith.science/pith/EGR44RKADYK5CUXMAWLPNHKWK5/bundle.json","state":"https://pith.science/pith/EGR44RKADYK5CUXMAWLPNHKWK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EGR44RKADYK5CUXMAWLPNHKWK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EGR44RKADYK5CUXMAWLPNHKWK5","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":"c2ba208586684f391d72ec058abff871d3845222c99aecc5f4d1dd87a5420f70","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T07:15:45Z","title_canon_sha256":"0c1ccc38a0ff3175957e45cca1f57d9e254b05c54399738a7c317cf2b5b455d5"},"schema_version":"1.0","source":{"id":"2206.15076","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15076","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15076v1","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15076","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"pith_short_12","alias_value":"EGR44RKADYK5","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"pith_short_16","alias_value":"EGR44RKADYK5CUXM","created_at":"2026-07-05T04:36:24Z"},{"alias_kind":"pith_short_8","alias_value":"EGR44RKA","created_at":"2026-07-05T04:36:24Z"}],"graph_snapshots":[{"event_id":"sha256:b37941d4a0da7254cd1d3839f83c852763ec1fa749c461e8d9c704b4be02dbdc","target":"graph","created_at":"2026-07-05T04:36:24Z","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/2206.15076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization by transforming existing, supervised datasets into a diversity of novel pretraining tasks, highlighting the benefits of meta-dataset curation. While successful in general-domain text, translating these data-centric approaches to biomedical language modeling remains challenging, as labeled biomedical datasets are significantly underrepresented in popular data ","authors_text":"Albert Villanova del Moral, Alison Callahan, Ayush Singh, Benjamin Beilharz, Bo Wang, Daniel Le\\'on Peri\\~n\\'an, Debajyoti Datta, Fabio Barth, Gabriel Altay, Jason Alan Fries, Jenny Chim, John Michael Giorgi, Jonas Golde, Jose David Posada, Karthik Rangasai Sivaraman, Leon Weber, Marc P\\`amies, Marianna Nezhurina, Mario S\\\"anger, Matthias Samwald, Michael Cullan, Minh Chien Vu, Moritz Freidank, Myungsun Kang, Natasha Seelam, Nathan Dahlberg, Nicholas Michio Broad, Patrick Haller, Robert Martin, Ruisi Su, Samuel Cahyawijaya, Samuele Garda, Shamik Bose, Shlok S Deshmukh, Shubhanshu Mishra, Sid Kiblawi, Simon Ott, Stella Biderman, Stephen Bach, Th\\'eo Gigant, Trishala Neeraj, Wojciech Kusa, Yanis Labrak","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T07:15:45Z","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15076","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":"sha256:301625706204ba9a715864971782945eb231f16fad5e38d0dbc74cc984900b34","target":"record","created_at":"2026-07-05T04:36:24Z","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":"c2ba208586684f391d72ec058abff871d3845222c99aecc5f4d1dd87a5420f70","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T07:15:45Z","title_canon_sha256":"0c1ccc38a0ff3175957e45cca1f57d9e254b05c54399738a7c317cf2b5b455d5"},"schema_version":"1.0","source":{"id":"2206.15076","kind":"arxiv","version":1}},"canonical_sha256":"21a3ce45401e15d152ec0596f69d56574b02dafbedf20cad951ab2712db9a99d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21a3ce45401e15d152ec0596f69d56574b02dafbedf20cad951ab2712db9a99d","first_computed_at":"2026-07-05T04:36:24.972676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:24.972676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ex9RQwIZ6cIUL4nrzUEhuX130X21GsA/+NglME3M75WRQ8kCq+S5e5817udxbs3oKtvUCq7mNfwqgzKzH3qPAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:24.973095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.15076","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:301625706204ba9a715864971782945eb231f16fad5e38d0dbc74cc984900b34","sha256:b37941d4a0da7254cd1d3839f83c852763ec1fa749c461e8d9c704b4be02dbdc"],"state_sha256":"0572507d70d927d0426eaed789b4002f36d3f31b4b73686f6e3ce98d713ede0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rfjhB+SczqS6e2bUrhM/V4SkA0wiIPRzoydVHo6RZUayzJccSmEO4S2bAYMgB2edLHmvWY+iCSN3FrG3bUttAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:45:16.911566Z","bundle_sha256":"70c70139a935047a61c6625ead265c94aafebf6059fe63887b67b29040376533"}}