{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:U3KH34HOCS6ZPHUMQJB2FP37YO","short_pith_number":"pith:U3KH34HO","canonical_record":{"source":{"id":"1904.12106","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-27T04:36:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21fc325c26fcbadf6caca2b3751b0cd66ecc929b917c36e76a07ba10afb07b7a","abstract_canon_sha256":"9c538c31dbcfe9c3ba2c2108bca9f6110f8f8ff9080aad7cf543f8c9dd521a04"},"schema_version":"1.0"},"canonical_sha256":"a6d47df0ee14bd979e8c8243a2bf7fc380e6b92d06404b2e2c759d6586ab6d64","source":{"kind":"arxiv","id":"1904.12106","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.12106","created_at":"2026-05-17T23:47:38Z"},{"alias_kind":"arxiv_version","alias_value":"1904.12106v1","created_at":"2026-05-17T23:47:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12106","created_at":"2026-05-17T23:47:38Z"},{"alias_kind":"pith_short_12","alias_value":"U3KH34HOCS6Z","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"U3KH34HOCS6ZPHUM","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"U3KH34HO","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:U3KH34HOCS6ZPHUMQJB2FP37YO","target":"record","payload":{"canonical_record":{"source":{"id":"1904.12106","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-27T04:36:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21fc325c26fcbadf6caca2b3751b0cd66ecc929b917c36e76a07ba10afb07b7a","abstract_canon_sha256":"9c538c31dbcfe9c3ba2c2108bca9f6110f8f8ff9080aad7cf543f8c9dd521a04"},"schema_version":"1.0"},"canonical_sha256":"a6d47df0ee14bd979e8c8243a2bf7fc380e6b92d06404b2e2c759d6586ab6d64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:38.925015Z","signature_b64":"ogNh1sg4mhmTBBE82yn49vEA/FCww/IiDcc4EkueaixwZZuTYbIfmnOYVo0GkKo5p3gPNvinsSk2ZvArem8sBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6d47df0ee14bd979e8c8243a2bf7fc380e6b92d06404b2e2c759d6586ab6d64","last_reissued_at":"2026-05-17T23:47:38.924652Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:38.924652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.12106","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":"2026-05-17T23:47:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UBRXcqulvORUCOvrNBIgOwBze+TpGF2cXqmTF/WpGtd8IJS3pSWSAAnrySVK7LyOYs9MkxHPU9STgvNcCIk1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T21:53:31.954904Z"},"content_sha256":"e42406e06f807144f665c6e73ce5db923ac0d3fb7dc4bfb66aa39a5a348bf4b0","schema_version":"1.0","event_id":"sha256:e42406e06f807144f665c6e73ce5db923ac0d3fb7dc4bfb66aa39a5a348bf4b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:U3KH34HOCS6ZPHUMQJB2FP37YO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Dataset Design Choices for Multi-hop Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Jifan Chen","submitted_at":"2019-04-27T04:36:57Z","abstract_excerpt":"Learning multi-hop reasoning has been a key challenge for reading comprehension models, leading to the design of datasets that explicitly focus on it. Ideally, a model should not be able to perform well on a multi-hop question answering task without doing multi-hop reasoning. In this paper, we investigate two recently proposed datasets, WikiHop and HotpotQA. First, we explore sentence-factored models for these tasks; by design, these models cannot do multi-hop reasoning, but they are still able to solve a large number of examples in both datasets. Furthermore, we find spurious correlations in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12106","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":"2026-05-17T23:47:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kkp+9spE03foXrrFw6aJWmDwjF/RuEh1NYfIELvUQNpJpKxIhbM45fUHqxTS6PNibpDobrTYmFi6eb3/aipcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T21:53:31.955610Z"},"content_sha256":"002ef3feb9fa0b86852833a89aced8f4bc20cf62172a4fcf501613b9347784ea","schema_version":"1.0","event_id":"sha256:002ef3feb9fa0b86852833a89aced8f4bc20cf62172a4fcf501613b9347784ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3KH34HOCS6ZPHUMQJB2FP37YO/bundle.json","state_url":"https://pith.science/pith/U3KH34HOCS6ZPHUMQJB2FP37YO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3KH34HOCS6ZPHUMQJB2FP37YO/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":"2026-05-22T21:53:31Z","links":{"resolver":"https://pith.science/pith/U3KH34HOCS6ZPHUMQJB2FP37YO","bundle":"https://pith.science/pith/U3KH34HOCS6ZPHUMQJB2FP37YO/bundle.json","state":"https://pith.science/pith/U3KH34HOCS6ZPHUMQJB2FP37YO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3KH34HOCS6ZPHUMQJB2FP37YO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:U3KH34HOCS6ZPHUMQJB2FP37YO","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":"9c538c31dbcfe9c3ba2c2108bca9f6110f8f8ff9080aad7cf543f8c9dd521a04","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-27T04:36:57Z","title_canon_sha256":"21fc325c26fcbadf6caca2b3751b0cd66ecc929b917c36e76a07ba10afb07b7a"},"schema_version":"1.0","source":{"id":"1904.12106","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.12106","created_at":"2026-05-17T23:47:38Z"},{"alias_kind":"arxiv_version","alias_value":"1904.12106v1","created_at":"2026-05-17T23:47:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12106","created_at":"2026-05-17T23:47:38Z"},{"alias_kind":"pith_short_12","alias_value":"U3KH34HOCS6Z","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"U3KH34HOCS6ZPHUM","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"U3KH34HO","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:002ef3feb9fa0b86852833a89aced8f4bc20cf62172a4fcf501613b9347784ea","target":"graph","created_at":"2026-05-17T23:47:38Z","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":"Learning multi-hop reasoning has been a key challenge for reading comprehension models, leading to the design of datasets that explicitly focus on it. Ideally, a model should not be able to perform well on a multi-hop question answering task without doing multi-hop reasoning. In this paper, we investigate two recently proposed datasets, WikiHop and HotpotQA. First, we explore sentence-factored models for these tasks; by design, these models cannot do multi-hop reasoning, but they are still able to solve a large number of examples in both datasets. Furthermore, we find spurious correlations in ","authors_text":"Greg Durrett, Jifan Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-27T04:36:57Z","title":"Understanding Dataset Design Choices for Multi-hop Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12106","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:e42406e06f807144f665c6e73ce5db923ac0d3fb7dc4bfb66aa39a5a348bf4b0","target":"record","created_at":"2026-05-17T23:47:38Z","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":"9c538c31dbcfe9c3ba2c2108bca9f6110f8f8ff9080aad7cf543f8c9dd521a04","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-27T04:36:57Z","title_canon_sha256":"21fc325c26fcbadf6caca2b3751b0cd66ecc929b917c36e76a07ba10afb07b7a"},"schema_version":"1.0","source":{"id":"1904.12106","kind":"arxiv","version":1}},"canonical_sha256":"a6d47df0ee14bd979e8c8243a2bf7fc380e6b92d06404b2e2c759d6586ab6d64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6d47df0ee14bd979e8c8243a2bf7fc380e6b92d06404b2e2c759d6586ab6d64","first_computed_at":"2026-05-17T23:47:38.924652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:38.924652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ogNh1sg4mhmTBBE82yn49vEA/FCww/IiDcc4EkueaixwZZuTYbIfmnOYVo0GkKo5p3gPNvinsSk2ZvArem8sBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:38.925015Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.12106","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e42406e06f807144f665c6e73ce5db923ac0d3fb7dc4bfb66aa39a5a348bf4b0","sha256:002ef3feb9fa0b86852833a89aced8f4bc20cf62172a4fcf501613b9347784ea"],"state_sha256":"95877a492e534280ab2c5d8e135ff4fdda2ee03e23c89949029954c62874dfa7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YhIkpwAXN/hzMPxVeXr7HQ3OVzPohxMAu1kaJ9EL+1vgc+tecUijY/nmOduh7Usak/Gew5HPc4FQ7fP3vLcNAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T21:53:31.958587Z","bundle_sha256":"97f82e329f4853a5adc63eb44731ac322a17cc0cfdd42351ed1e84b10655c4b0"}}