{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HGJWHT5FVGRRQN4AFX2J2NRMQE","short_pith_number":"pith:HGJWHT5F","canonical_record":{"source":{"id":"2004.05569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-12T09:06:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"207155becbcc9cd2ae9086341d3485af0b044e3e6e686a2a777be4c0f56616cc","abstract_canon_sha256":"ce651232261bb88e27361912624617d968f1727d620fc784499ea461d20373d2"},"schema_version":"1.0"},"canonical_sha256":"399363cfa5a9a31837802df49d362c812712118c9151ffd6346ddffb1101cb36","source":{"kind":"arxiv","id":"2004.05569","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05569","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05569v1","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05569","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"HGJWHT5FVGRR","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"pith_short_16","alias_value":"HGJWHT5FVGRRQN4A","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"pith_short_8","alias_value":"HGJWHT5F","created_at":"2026-07-05T00:54:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HGJWHT5FVGRRQN4AFX2J2NRMQE","target":"record","payload":{"canonical_record":{"source":{"id":"2004.05569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-12T09:06:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"207155becbcc9cd2ae9086341d3485af0b044e3e6e686a2a777be4c0f56616cc","abstract_canon_sha256":"ce651232261bb88e27361912624617d968f1727d620fc784499ea461d20373d2"},"schema_version":"1.0"},"canonical_sha256":"399363cfa5a9a31837802df49d362c812712118c9151ffd6346ddffb1101cb36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:38.810376Z","signature_b64":"66Fa226Gar+UhWHywd8ymwUTmvxhYBHaUoD3qi6reLi+MhCOp3kswke8sDLjcrJHmL4zqFm3ehrJHCHi7RA8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"399363cfa5a9a31837802df49d362c812712118c9151ffd6346ddffb1101cb36","last_reissued_at":"2026-07-05T00:54:38.809956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:38.809956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.05569","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":"2026-07-05T00:54:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5T7mu64oEVbBnwqD15Ukg08rcgItsWOXifacou+G2PnHviHfNwMKF15mkHPYQg4Cq+Ypg6EEPU79gKppb9s0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:40:11.541122Z"},"content_sha256":"fcb21e445e7eb3551abb7fe36862fb232ea680ac57e708ed9745a64a198cdae0","schema_version":"1.0","event_id":"sha256:fcb21e445e7eb3551abb7fe36862fb232ea680ac57e708ed9745a64a198cdae0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HGJWHT5FVGRRQN4AFX2J2NRMQE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explaining Question Answering Models through Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jonathan Berant, Veronica Latcinnik","submitted_at":"2020-04-12T09:06:46Z","abstract_excerpt":"Large pre-trained language models (LMs) have been shown to perform surprisingly well when fine-tuned on tasks that require commonsense and world knowledge. However, in end-to-end architectures, it is difficult to explain what is the knowledge in the LM that allows it to make a correct prediction. In this work, we propose a model for multi-choice question answering, where a LM-based generator generates a textual hypothesis that is later used by a classifier to answer the question. The hypothesis provides a window into the information used by the fine-tuned LM that can be inspected by humans. A "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05569","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/2004.05569/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":"2026-07-05T00:54:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pz4t3zg9/iNstUm3XqYnNO/JLTHXaT/pCPjmlUUoVdZr6+03f0tShRJ3PLohnTQUdSJMeyvsAUuM9DkFaSnoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:40:11.541621Z"},"content_sha256":"d761962dfce2a5819bd2d42f94d64ea3fc1683566db1566ba1876f010482fc1c","schema_version":"1.0","event_id":"sha256:d761962dfce2a5819bd2d42f94d64ea3fc1683566db1566ba1876f010482fc1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HGJWHT5FVGRRQN4AFX2J2NRMQE/bundle.json","state_url":"https://pith.science/pith/HGJWHT5FVGRRQN4AFX2J2NRMQE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HGJWHT5FVGRRQN4AFX2J2NRMQE/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":"2026-08-09T03:40:11Z","links":{"resolver":"https://pith.science/pith/HGJWHT5FVGRRQN4AFX2J2NRMQE","bundle":"https://pith.science/pith/HGJWHT5FVGRRQN4AFX2J2NRMQE/bundle.json","state":"https://pith.science/pith/HGJWHT5FVGRRQN4AFX2J2NRMQE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HGJWHT5FVGRRQN4AFX2J2NRMQE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HGJWHT5FVGRRQN4AFX2J2NRMQE","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":"ce651232261bb88e27361912624617d968f1727d620fc784499ea461d20373d2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-12T09:06:46Z","title_canon_sha256":"207155becbcc9cd2ae9086341d3485af0b044e3e6e686a2a777be4c0f56616cc"},"schema_version":"1.0","source":{"id":"2004.05569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05569","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05569v1","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05569","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"HGJWHT5FVGRR","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"pith_short_16","alias_value":"HGJWHT5FVGRRQN4A","created_at":"2026-07-05T00:54:38Z"},{"alias_kind":"pith_short_8","alias_value":"HGJWHT5F","created_at":"2026-07-05T00:54:38Z"}],"graph_snapshots":[{"event_id":"sha256:d761962dfce2a5819bd2d42f94d64ea3fc1683566db1566ba1876f010482fc1c","target":"graph","created_at":"2026-07-05T00:54:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.05569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained language models (LMs) have been shown to perform surprisingly well when fine-tuned on tasks that require commonsense and world knowledge. However, in end-to-end architectures, it is difficult to explain what is the knowledge in the LM that allows it to make a correct prediction. In this work, we propose a model for multi-choice question answering, where a LM-based generator generates a textual hypothesis that is later used by a classifier to answer the question. The hypothesis provides a window into the information used by the fine-tuned LM that can be inspected by humans. A ","authors_text":"Jonathan Berant, Veronica Latcinnik","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-12T09:06:46Z","title":"Explaining Question Answering Models through Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05569","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:fcb21e445e7eb3551abb7fe36862fb232ea680ac57e708ed9745a64a198cdae0","target":"record","created_at":"2026-07-05T00:54:38Z","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":"ce651232261bb88e27361912624617d968f1727d620fc784499ea461d20373d2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-12T09:06:46Z","title_canon_sha256":"207155becbcc9cd2ae9086341d3485af0b044e3e6e686a2a777be4c0f56616cc"},"schema_version":"1.0","source":{"id":"2004.05569","kind":"arxiv","version":1}},"canonical_sha256":"399363cfa5a9a31837802df49d362c812712118c9151ffd6346ddffb1101cb36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"399363cfa5a9a31837802df49d362c812712118c9151ffd6346ddffb1101cb36","first_computed_at":"2026-07-05T00:54:38.809956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:54:38.809956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"66Fa226Gar+UhWHywd8ymwUTmvxhYBHaUoD3qi6reLi+MhCOp3kswke8sDLjcrJHmL4zqFm3ehrJHCHi7RA8CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:54:38.810376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.05569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcb21e445e7eb3551abb7fe36862fb232ea680ac57e708ed9745a64a198cdae0","sha256:d761962dfce2a5819bd2d42f94d64ea3fc1683566db1566ba1876f010482fc1c"],"state_sha256":"7012cbbbc71677030faf5db86567983cdf3b010dd62397ce93bdb2bc5601013c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4DxKAw/nC9IxjAlEfc4LUGf3pY0NX3s9M6vYgPIhKw4VZiex6JUzAanJie4eiPkCHPcUGSzbLUW/wstnSrkPBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:40:11.545369Z","bundle_sha256":"7766ba60c03146a4afb6d6e48fe51468527f2212aa4ff6e04796d22f98ded3b1"}}