{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UKN37MZMXWDX7QFUBP5PUHKB5X","short_pith_number":"pith:UKN37MZM","canonical_record":{"source":{"id":"2206.12388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-24T17:42:18Z","cross_cats_sorted":[],"title_canon_sha256":"e3e38991bfb4a2a8742585c56e719b37fb5efa30c959ac6b579bf2e883e676b8","abstract_canon_sha256":"30772d3ea36a0b87004a374fc4bdd2b2e945937c50b921bc32a115800349ce65"},"schema_version":"1.0"},"canonical_sha256":"a29bbfb32cbd877fc0b40bfafa1d41ede639a2a6ecf0c6fd46d98ac3ad0c193c","source":{"kind":"arxiv","id":"2206.12388","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12388","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12388v1","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12388","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"pith_short_12","alias_value":"UKN37MZMXWDX","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"pith_short_16","alias_value":"UKN37MZMXWDX7QFU","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"pith_short_8","alias_value":"UKN37MZM","created_at":"2026-07-05T04:34:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UKN37MZMXWDX7QFUBP5PUHKB5X","target":"record","payload":{"canonical_record":{"source":{"id":"2206.12388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-24T17:42:18Z","cross_cats_sorted":[],"title_canon_sha256":"e3e38991bfb4a2a8742585c56e719b37fb5efa30c959ac6b579bf2e883e676b8","abstract_canon_sha256":"30772d3ea36a0b87004a374fc4bdd2b2e945937c50b921bc32a115800349ce65"},"schema_version":"1.0"},"canonical_sha256":"a29bbfb32cbd877fc0b40bfafa1d41ede639a2a6ecf0c6fd46d98ac3ad0c193c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:36.109161Z","signature_b64":"f7xVxg5QYQ4m0+G2cKPJSZ8fSuo0f0hwTV4lxDmN6WrDf8DF8psMZ2JqZNra5gpcDovcJ0QkkBfmh3UNqVDDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a29bbfb32cbd877fc0b40bfafa1d41ede639a2a6ecf0c6fd46d98ac3ad0c193c","last_reissued_at":"2026-07-05T04:34:36.108788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:36.108788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.12388","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":"2026-07-05T04:34:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rC/nfG1rplaEir1xx203bYHPToKMEsmgJHLPyqgoxu+dtrJsLxg7fHKNtZ3vlzKmGCTHD7C4R510vLZSisR6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:23:06.769300Z"},"content_sha256":"7664f2b70e321e28f3ac1805de86782771c2e640b5b3b1dceab59da9ae6c004f","schema_version":"1.0","event_id":"sha256:7664f2b70e321e28f3ac1805de86782771c2e640b5b3b1dceab59da9ae6c004f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UKN37MZMXWDX7QFUBP5PUHKB5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QAGAN: Adversarial Approach To Learning Domain Invariant Language Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaiyue Wang, Shubham Shrivastava","submitted_at":"2022-06-24T17:42:18Z","abstract_excerpt":"Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has received much success with the advent of large transformer models. However, existing approaches mostly work under the assumption that data is drawn from same distribution during training and testing which is unrealistic and non-scalable in the wild.\n  In this paper, we explore adversarial training approach towards learning domain-invariant features so that lan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12388","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/2206.12388/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":"2026-07-05T04:34:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QSNMopJM+0wYjxef1ovh3nBX/km6s2EN2b4Cq3pLIGZid2TzanVSdcBtrWGzNZmGqDo4Bq+4bdTqjjVYxjSNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:23:06.769901Z"},"content_sha256":"96741ff479502d332b79aea29f7a057b5018548156826db6076fa1f2404f94bd","schema_version":"1.0","event_id":"sha256:96741ff479502d332b79aea29f7a057b5018548156826db6076fa1f2404f94bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKN37MZMXWDX7QFUBP5PUHKB5X/bundle.json","state_url":"https://pith.science/pith/UKN37MZMXWDX7QFUBP5PUHKB5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKN37MZMXWDX7QFUBP5PUHKB5X/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":"2026-08-24T03:23:06Z","links":{"resolver":"https://pith.science/pith/UKN37MZMXWDX7QFUBP5PUHKB5X","bundle":"https://pith.science/pith/UKN37MZMXWDX7QFUBP5PUHKB5X/bundle.json","state":"https://pith.science/pith/UKN37MZMXWDX7QFUBP5PUHKB5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKN37MZMXWDX7QFUBP5PUHKB5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UKN37MZMXWDX7QFUBP5PUHKB5X","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":"30772d3ea36a0b87004a374fc4bdd2b2e945937c50b921bc32a115800349ce65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-24T17:42:18Z","title_canon_sha256":"e3e38991bfb4a2a8742585c56e719b37fb5efa30c959ac6b579bf2e883e676b8"},"schema_version":"1.0","source":{"id":"2206.12388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12388","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12388v1","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12388","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"pith_short_12","alias_value":"UKN37MZMXWDX","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"pith_short_16","alias_value":"UKN37MZMXWDX7QFU","created_at":"2026-07-05T04:34:36Z"},{"alias_kind":"pith_short_8","alias_value":"UKN37MZM","created_at":"2026-07-05T04:34:36Z"}],"graph_snapshots":[{"event_id":"sha256:96741ff479502d332b79aea29f7a057b5018548156826db6076fa1f2404f94bd","target":"graph","created_at":"2026-07-05T04:34:36Z","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/2206.12388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has received much success with the advent of large transformer models. However, existing approaches mostly work under the assumption that data is drawn from same distribution during training and testing which is unrealistic and non-scalable in the wild.\n  In this paper, we explore adversarial training approach towards learning domain-invariant features so that lan","authors_text":"Kaiyue Wang, Shubham Shrivastava","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-24T17:42:18Z","title":"QAGAN: Adversarial Approach To Learning Domain Invariant Language Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12388","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":"sha256:7664f2b70e321e28f3ac1805de86782771c2e640b5b3b1dceab59da9ae6c004f","target":"record","created_at":"2026-07-05T04:34:36Z","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":"30772d3ea36a0b87004a374fc4bdd2b2e945937c50b921bc32a115800349ce65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-24T17:42:18Z","title_canon_sha256":"e3e38991bfb4a2a8742585c56e719b37fb5efa30c959ac6b579bf2e883e676b8"},"schema_version":"1.0","source":{"id":"2206.12388","kind":"arxiv","version":1}},"canonical_sha256":"a29bbfb32cbd877fc0b40bfafa1d41ede639a2a6ecf0c6fd46d98ac3ad0c193c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a29bbfb32cbd877fc0b40bfafa1d41ede639a2a6ecf0c6fd46d98ac3ad0c193c","first_computed_at":"2026-07-05T04:34:36.108788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:36.108788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f7xVxg5QYQ4m0+G2cKPJSZ8fSuo0f0hwTV4lxDmN6WrDf8DF8psMZ2JqZNra5gpcDovcJ0QkkBfmh3UNqVDDAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:36.109161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.12388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7664f2b70e321e28f3ac1805de86782771c2e640b5b3b1dceab59da9ae6c004f","sha256:96741ff479502d332b79aea29f7a057b5018548156826db6076fa1f2404f94bd"],"state_sha256":"e868b8c860a9e481d1b7b129f64bc3868d3386d1a2ac5fda7f00081e7d4af3eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8uRmO7tbhxFLom2xpbCQ5dDyxrHqr1+DWu1jT2EY8Rq5eHid5YyjYGrPDWt7/Xa+sjezHHn/HecgmpbWAGQMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T03:23:06.774319Z","bundle_sha256":"f5c3584a8ab1819d4a96cc1875b7f90b928bc380813b833b221f73394bdf26ca"}}