{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:W5SVNSCDIDLB6362CTDOFCBZXF","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":"4e21407ead8eed0145a9cd849664dcf19d86dde926633e5b6da16c67e66a7627","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-17T17:03:57Z","title_canon_sha256":"92c9fb3e9f2364474b1ca3d36fe6afceff7064aaaa5fe10ca3685415ee7ad197"},"schema_version":"1.0","source":{"id":"1906.07132","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.07132","created_at":"2026-05-17T23:43:11Z"},{"alias_kind":"arxiv_version","alias_value":"1906.07132v1","created_at":"2026-05-17T23:43:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07132","created_at":"2026-05-17T23:43:11Z"},{"alias_kind":"pith_short_12","alias_value":"W5SVNSCDIDLB","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"W5SVNSCDIDLB6362","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"W5SVNSCD","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:cfc56054063a7abbc98f21ef79c49ec1c8aa5c8703bddd7c14366f07b8d3c0cd","target":"graph","created_at":"2026-05-17T23:43:11Z","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":"Multi-hop question answering requires a model to connect multiple pieces of evidence scattered in a long context to answer the question. In this paper, we show that in the multi-hop HotpotQA (Yang et al., 2018) dataset, the examples often contain reasoning shortcuts through which models can directly locate the answer by word-matching the question with a sentence in the context. We demonstrate this issue by constructing adversarial documents that create contradicting answers to the shortcut but do not affect the validity of the original answer. The performance of strong baseline models drops si","authors_text":"Mohit Bansal, Yichen Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-17T17:03:57Z","title":"Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07132","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":"sha256:99c587bf5f3d208da1453a1dac0e0764af29af324001e500c8cf7378ccba742c","target":"record","created_at":"2026-05-17T23:43:11Z","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":"4e21407ead8eed0145a9cd849664dcf19d86dde926633e5b6da16c67e66a7627","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-17T17:03:57Z","title_canon_sha256":"92c9fb3e9f2364474b1ca3d36fe6afceff7064aaaa5fe10ca3685415ee7ad197"},"schema_version":"1.0","source":{"id":"1906.07132","kind":"arxiv","version":1}},"canonical_sha256":"b76556c84340d61f6fda14c6e28839b9436561105c46f52114b153e7f9977f9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b76556c84340d61f6fda14c6e28839b9436561105c46f52114b153e7f9977f9a","first_computed_at":"2026-05-17T23:43:11.797629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:11.797629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ieikSq1UchjA9HCV4PGJgbQ5VL4r1di6RpIlUlunToMdA5TDMtLKxLfWksYruOBkztf2CL5QCze72wWfuTIgCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:11.798205Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.07132","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99c587bf5f3d208da1453a1dac0e0764af29af324001e500c8cf7378ccba742c","sha256:cfc56054063a7abbc98f21ef79c49ec1c8aa5c8703bddd7c14366f07b8d3c0cd"],"state_sha256":"0b2dee260abef2b005406b9c523d3c63fb627d03318bb016b6195291aafd8ca8"}