{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:J27LUYD7YJAMFUYIKXPL4OOJZL","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":"77389bfe4305e961ad27bd107bf4f348b83c1b54b4aa75045a9624c3166156d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-02T18:04:10Z","title_canon_sha256":"60a325d3f305a6d77dae88514374277a4c7fe560acf0f89c69f4188130c60ec8"},"schema_version":"1.0","source":{"id":"2109.01156","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01156","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01156v3","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01156","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"J27LUYD7YJAM","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"J27LUYD7YJAMFUYI","created_at":"2026-07-05T04:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"J27LUYD7","created_at":"2026-07-05T04:23:21Z"}],"graph_snapshots":[{"event_id":"sha256:3dec3cf38bba587c2c7c903ad92dd98202feb940f5b4c68b8cff1908b8a9285c","target":"graph","created_at":"2026-07-05T04:23:21Z","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/2109.01156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work on Open Domain Question Answering has shown that there is a large discrepancy in model performance between novel test questions and those that largely overlap with training questions. However, it is unclear which aspects of novel questions make them challenging. Drawing upon studies on systematic generalization, we introduce and annotate questions according to three categories that measure different levels and kinds of generalization: training set overlap, compositional generalization (comp-gen), and novel-entity generalization (novel-entity). When evaluating six popular parametric","authors_text":"Linqing Liu, Patrick Lewis, Pontus Stenetorp, Sebastian Riedel","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-02T18:04:10Z","title":"Challenges in Generalization in Open Domain Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01156","kind":"arxiv","version":3},"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":"sha256:4bdb11578defb6bfb72d4f0abf69fec6db229ca97c8ce6a043fb26084877467d","target":"record","created_at":"2026-07-05T04:23:21Z","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":"77389bfe4305e961ad27bd107bf4f348b83c1b54b4aa75045a9624c3166156d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-02T18:04:10Z","title_canon_sha256":"60a325d3f305a6d77dae88514374277a4c7fe560acf0f89c69f4188130c60ec8"},"schema_version":"1.0","source":{"id":"2109.01156","kind":"arxiv","version":3}},"canonical_sha256":"4ebeba607fc240c2d30855debe39c9cae8f249ab13dec68d82054dc4c176c7a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ebeba607fc240c2d30855debe39c9cae8f249ab13dec68d82054dc4c176c7a1","first_computed_at":"2026-07-05T04:23:21.479487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:23:21.479487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WnS80AueNY7JqZXd2fZezAJVgEat1kNC8R5+CeFozX9rudR/IMEp/Sd+9YOiswUV0aMq++WWxKblQaPUycliAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:23:21.480048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.01156","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bdb11578defb6bfb72d4f0abf69fec6db229ca97c8ce6a043fb26084877467d","sha256:3dec3cf38bba587c2c7c903ad92dd98202feb940f5b4c68b8cff1908b8a9285c"],"state_sha256":"0f51ffefed98420a9dc08ae7ddfd745cd56bbec654d2318d0b3ef30a5a202fa7"}