{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5PNOWZB2TPWV24ZAAZLC6HAQAS","short_pith_number":"pith:5PNOWZB2","canonical_record":{"source":{"id":"1906.05416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T22:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"72a1d84ae355f3523f3f23cd0cbcb6a8f61b219451f4011f595a3de65e079855","abstract_canon_sha256":"34fd19ea2deaef03929927386441c4d998dc1ec78639cd018e93d78475b1e8ef"},"schema_version":"1.0"},"canonical_sha256":"ebdaeb643a9bed5d732006562f1c100483a760eda1f0d5c59d853ecb5e49e298","source":{"kind":"arxiv","id":"1906.05416","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05416","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05416v1","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05416","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"5PNOWZB2TPWV","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5PNOWZB2TPWV24ZA","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5PNOWZB2","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5PNOWZB2TPWV24ZAAZLC6HAQAS","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T22:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"72a1d84ae355f3523f3f23cd0cbcb6a8f61b219451f4011f595a3de65e079855","abstract_canon_sha256":"34fd19ea2deaef03929927386441c4d998dc1ec78639cd018e93d78475b1e8ef"},"schema_version":"1.0"},"canonical_sha256":"ebdaeb643a9bed5d732006562f1c100483a760eda1f0d5c59d853ecb5e49e298","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:25.372988Z","signature_b64":"5fhMqya2d9UN9Ura8s8IiWHm23Ts2WvOTFRqrQGhM6bl7LTYGX7+FYnF+dCGUA5lwj9bfTNKyogJGJTJByOZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebdaeb643a9bed5d732006562f1c100483a760eda1f0d5c59d853ecb5e49e298","last_reissued_at":"2026-05-17T23:43:25.372583Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:25.372583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05416","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":"2026-05-17T23:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u39OI3/cAP5cY9bX0fkBNCcCmc+M2DP11n7b2h0i5gVVflFgSMznc+LYQmx63ZhafzlObhcJCB9e/ket//09Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:00:10.751171Z"},"content_sha256":"2e02f1bcdb3db921f688c410bd046966aa4dba588aa8b3914fd3435b18f214ff","schema_version":"1.0","event_id":"sha256:2e02f1bcdb3db921f688c410bd046966aa4dba588aa8b3914fd3435b18f214ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5PNOWZB2TPWV24ZAAZLC6HAQAS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic QA Corpora Generation with Roundtrip Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Alberti, Daniel Andor, Emily Pitler, Jacob Devlin, Michael Collins","submitted_at":"2019-06-12T22:50:31Z","abstract_excerpt":"We introduce a novel method of generating synthetic question answering corpora by combining models of question generation and answer extraction, and by filtering the results to ensure roundtrip consistency. By pretraining on the resulting corpora we obtain significant improvements on SQuAD2 and NQ, establishing a new state-of-the-art on the latter. Our synthetic data generation models, for both question generation and answer extraction, can be fully reproduced by finetuning a publicly available BERT model on the extractive subsets of SQuAD2 and NQ. We also describe a more powerful variant that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05416","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":""},"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":"2026-05-17T23:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KBTT4ID3SPSbZghoZZRwZeMNv1G5xMb8fx6EQoty6wwuFytULDWQNR1V6EmHMYy7atb5GV5m2fXCaTbYGRVbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:00:10.751543Z"},"content_sha256":"4e8003aa12085eaa505abc4fbc0a15f941e81647bb59b4b5537d5575227acab5","schema_version":"1.0","event_id":"sha256:4e8003aa12085eaa505abc4fbc0a15f941e81647bb59b4b5537d5575227acab5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5PNOWZB2TPWV24ZAAZLC6HAQAS/bundle.json","state_url":"https://pith.science/pith/5PNOWZB2TPWV24ZAAZLC6HAQAS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5PNOWZB2TPWV24ZAAZLC6HAQAS/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":"2026-05-30T05:00:10Z","links":{"resolver":"https://pith.science/pith/5PNOWZB2TPWV24ZAAZLC6HAQAS","bundle":"https://pith.science/pith/5PNOWZB2TPWV24ZAAZLC6HAQAS/bundle.json","state":"https://pith.science/pith/5PNOWZB2TPWV24ZAAZLC6HAQAS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5PNOWZB2TPWV24ZAAZLC6HAQAS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5PNOWZB2TPWV24ZAAZLC6HAQAS","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":"34fd19ea2deaef03929927386441c4d998dc1ec78639cd018e93d78475b1e8ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T22:50:31Z","title_canon_sha256":"72a1d84ae355f3523f3f23cd0cbcb6a8f61b219451f4011f595a3de65e079855"},"schema_version":"1.0","source":{"id":"1906.05416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05416","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05416v1","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05416","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"5PNOWZB2TPWV","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5PNOWZB2TPWV24ZA","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5PNOWZB2","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:4e8003aa12085eaa505abc4fbc0a15f941e81647bb59b4b5537d5575227acab5","target":"graph","created_at":"2026-05-17T23:43:25Z","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"},"paper":{"abstract_excerpt":"We introduce a novel method of generating synthetic question answering corpora by combining models of question generation and answer extraction, and by filtering the results to ensure roundtrip consistency. By pretraining on the resulting corpora we obtain significant improvements on SQuAD2 and NQ, establishing a new state-of-the-art on the latter. Our synthetic data generation models, for both question generation and answer extraction, can be fully reproduced by finetuning a publicly available BERT model on the extractive subsets of SQuAD2 and NQ. We also describe a more powerful variant that","authors_text":"Chris Alberti, Daniel Andor, Emily Pitler, Jacob Devlin, Michael Collins","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T22:50:31Z","title":"Synthetic QA Corpora Generation with Roundtrip Consistency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05416","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":"sha256:2e02f1bcdb3db921f688c410bd046966aa4dba588aa8b3914fd3435b18f214ff","target":"record","created_at":"2026-05-17T23:43:25Z","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":"34fd19ea2deaef03929927386441c4d998dc1ec78639cd018e93d78475b1e8ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-12T22:50:31Z","title_canon_sha256":"72a1d84ae355f3523f3f23cd0cbcb6a8f61b219451f4011f595a3de65e079855"},"schema_version":"1.0","source":{"id":"1906.05416","kind":"arxiv","version":1}},"canonical_sha256":"ebdaeb643a9bed5d732006562f1c100483a760eda1f0d5c59d853ecb5e49e298","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebdaeb643a9bed5d732006562f1c100483a760eda1f0d5c59d853ecb5e49e298","first_computed_at":"2026-05-17T23:43:25.372583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:25.372583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5fhMqya2d9UN9Ura8s8IiWHm23Ts2WvOTFRqrQGhM6bl7LTYGX7+FYnF+dCGUA5lwj9bfTNKyogJGJTJByOZBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:25.372988Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e02f1bcdb3db921f688c410bd046966aa4dba588aa8b3914fd3435b18f214ff","sha256:4e8003aa12085eaa505abc4fbc0a15f941e81647bb59b4b5537d5575227acab5"],"state_sha256":"6b1ccb969db8fb438b00ccb65ea35993e487d26ac8b314569c1554bbfded0d73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nIHE1Bzzzeut3X9EJSuZwmlQNtkeRevYl3XWG9KE1H24Whg8oiWp5/6M72jnC1n5s7ytBa7OdxFbAYuh/2D9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T05:00:10.753688Z","bundle_sha256":"63824639d3584788aaa6e2c0734044a62dc9af8fa494fa62b0f37ed2aeb7f09b"}}