{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:EFI2WQMFB5KLRNQW2M2ALLES6B","short_pith_number":"pith:EFI2WQMF","canonical_record":{"source":{"id":"2002.09599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-22T01:49:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4eae6a225689a0e7c4fb54e956ceb656fe504df2ba3e049d2855c1a08097ba5b","abstract_canon_sha256":"49ce929a1abfa390b2067cfc4141808ffcd314283321e69e8d865c1177c7b10b"},"schema_version":"1.0"},"canonical_sha256":"2151ab41850f54b8b616d33405ac92f07760156c363a97162a8196396d8b04fc","source":{"kind":"arxiv","id":"2002.09599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09599","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09599v1","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09599","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"pith_short_12","alias_value":"EFI2WQMFB5KL","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"pith_short_16","alias_value":"EFI2WQMFB5KLRNQW","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"pith_short_8","alias_value":"EFI2WQMF","created_at":"2026-07-05T00:43:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:EFI2WQMFB5KLRNQW2M2ALLES6B","target":"record","payload":{"canonical_record":{"source":{"id":"2002.09599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-22T01:49:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4eae6a225689a0e7c4fb54e956ceb656fe504df2ba3e049d2855c1a08097ba5b","abstract_canon_sha256":"49ce929a1abfa390b2067cfc4141808ffcd314283321e69e8d865c1177c7b10b"},"schema_version":"1.0"},"canonical_sha256":"2151ab41850f54b8b616d33405ac92f07760156c363a97162a8196396d8b04fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:09.441530Z","signature_b64":"XAUHrInHw8J78g2bGuc3v9TDWqHwC1d4f9YEjrv7jgbgPrQ4R2BLTPKZAIfsj18/DJf5yb0PJbfkAJ1LrYOrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2151ab41850f54b8b616d33405ac92f07760156c363a97162a8196396d8b04fc","last_reissued_at":"2026-07-05T00:43:09.441029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:09.441029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.09599","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":"2026-07-05T00:43:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WCuHHUQMVtZyXdmc13vpiV++/MEx+vc3InVZt0tD9RAg/9D8DUvH4sTm39cujvrJM829JQrTtIoo5/aQJrybCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:29:39.543229Z"},"content_sha256":"784797f51309d8ef9e435458f9bc5901491074bbe63eed3afb008130fd327fab","schema_version":"1.0","event_id":"sha256:784797f51309d8ef9e435458f9bc5901491074bbe63eed3afb008130fd327fab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:EFI2WQMFB5KLRNQW2M2ALLES6B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Question Answering Models From Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bryan Catanzaro, Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Ryan Spring","submitted_at":"2020-02-22T01:49:27Z","abstract_excerpt":"Question and answer generation is a data augmentation method that aims to improve question answering (QA) models given the limited amount of human labeled data. However, a considerable gap remains between synthetic and human-generated question-answer pairs. This work aims to narrow this gap by taking advantage of large language models and explores several factors such as model size, quality of pretrained models, scale of data synthesized, and algorithmic choices. On the SQuAD1.1 question answering task, we achieve higher accuracy using solely synthetic questions and answers than when using the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09599","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/2002.09599/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":"2026-07-05T00:43:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VW/pwe5IGsbS5nU3QhIFoP7/DOd4nXKRj5Yy8xjS079A0Y+WNxX58pBRw7aHTGXFXeGC0FwJAKij6VBvzIO2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:29:39.543751Z"},"content_sha256":"7dcf071c213e80d89bfb2a0b937dd9e9965c72174e1103f290c57e918e82a028","schema_version":"1.0","event_id":"sha256:7dcf071c213e80d89bfb2a0b937dd9e9965c72174e1103f290c57e918e82a028"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EFI2WQMFB5KLRNQW2M2ALLES6B/bundle.json","state_url":"https://pith.science/pith/EFI2WQMFB5KLRNQW2M2ALLES6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EFI2WQMFB5KLRNQW2M2ALLES6B/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":"2026-08-09T18:29:39Z","links":{"resolver":"https://pith.science/pith/EFI2WQMFB5KLRNQW2M2ALLES6B","bundle":"https://pith.science/pith/EFI2WQMFB5KLRNQW2M2ALLES6B/bundle.json","state":"https://pith.science/pith/EFI2WQMFB5KLRNQW2M2ALLES6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EFI2WQMFB5KLRNQW2M2ALLES6B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EFI2WQMFB5KLRNQW2M2ALLES6B","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":"49ce929a1abfa390b2067cfc4141808ffcd314283321e69e8d865c1177c7b10b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-22T01:49:27Z","title_canon_sha256":"4eae6a225689a0e7c4fb54e956ceb656fe504df2ba3e049d2855c1a08097ba5b"},"schema_version":"1.0","source":{"id":"2002.09599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09599","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09599v1","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09599","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"pith_short_12","alias_value":"EFI2WQMFB5KL","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"pith_short_16","alias_value":"EFI2WQMFB5KLRNQW","created_at":"2026-07-05T00:43:09Z"},{"alias_kind":"pith_short_8","alias_value":"EFI2WQMF","created_at":"2026-07-05T00:43:09Z"}],"graph_snapshots":[{"event_id":"sha256:7dcf071c213e80d89bfb2a0b937dd9e9965c72174e1103f290c57e918e82a028","target":"graph","created_at":"2026-07-05T00:43:09Z","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/2002.09599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Question and answer generation is a data augmentation method that aims to improve question answering (QA) models given the limited amount of human labeled data. However, a considerable gap remains between synthetic and human-generated question-answer pairs. This work aims to narrow this gap by taking advantage of large language models and explores several factors such as model size, quality of pretrained models, scale of data synthesized, and algorithmic choices. On the SQuAD1.1 question answering task, we achieve higher accuracy using solely synthetic questions and answers than when using the","authors_text":"Bryan Catanzaro, Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Ryan Spring","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-22T01:49:27Z","title":"Training Question Answering Models From Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09599","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":"sha256:784797f51309d8ef9e435458f9bc5901491074bbe63eed3afb008130fd327fab","target":"record","created_at":"2026-07-05T00:43:09Z","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":"49ce929a1abfa390b2067cfc4141808ffcd314283321e69e8d865c1177c7b10b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-22T01:49:27Z","title_canon_sha256":"4eae6a225689a0e7c4fb54e956ceb656fe504df2ba3e049d2855c1a08097ba5b"},"schema_version":"1.0","source":{"id":"2002.09599","kind":"arxiv","version":1}},"canonical_sha256":"2151ab41850f54b8b616d33405ac92f07760156c363a97162a8196396d8b04fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2151ab41850f54b8b616d33405ac92f07760156c363a97162a8196396d8b04fc","first_computed_at":"2026-07-05T00:43:09.441029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:09.441029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XAUHrInHw8J78g2bGuc3v9TDWqHwC1d4f9YEjrv7jgbgPrQ4R2BLTPKZAIfsj18/DJf5yb0PJbfkAJ1LrYOrBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:09.441530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.09599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:784797f51309d8ef9e435458f9bc5901491074bbe63eed3afb008130fd327fab","sha256:7dcf071c213e80d89bfb2a0b937dd9e9965c72174e1103f290c57e918e82a028"],"state_sha256":"9c109f2991a11ec4c49d7442f6ac77f432d31d169cc5ef6a947d35520932e4a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RfEgOotwIjN5xOXbR4X0+QkP++80mazk24jg2yM30TnQDkl37uqefLW08mpVGrGHpmYHNGtq2+mHy1QWvAhWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:29:39.550228Z","bundle_sha256":"880a48758d51d44776bd4fbc3733de4d4270f441bed735fa328a1acb2644be2b"}}