{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OOHM4A5TIAN44DJYAS66U5SUZ7","short_pith_number":"pith:OOHM4A5T","canonical_record":{"source":{"id":"1812.02205","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T19:55:24Z","cross_cats_sorted":[],"title_canon_sha256":"e0f338e14da2fa3292f9df01732da0885521e8823c960550b47a14fb027d3791","abstract_canon_sha256":"0f0cba934282b5c953bd2ba2542ea7fb4fa2e80bc9433a348976305b8b1ead00"},"schema_version":"1.0"},"canonical_sha256":"738ece03b3401bce0d3804bdea7654cfce053a4e763bd65ef8b021a221c46a25","source":{"kind":"arxiv","id":"1812.02205","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02205","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02205v1","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02205","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"pith_short_12","alias_value":"OOHM4A5TIAN4","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OOHM4A5TIAN44DJY","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OOHM4A5T","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OOHM4A5TIAN44DJYAS66U5SUZ7","target":"record","payload":{"canonical_record":{"source":{"id":"1812.02205","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T19:55:24Z","cross_cats_sorted":[],"title_canon_sha256":"e0f338e14da2fa3292f9df01732da0885521e8823c960550b47a14fb027d3791","abstract_canon_sha256":"0f0cba934282b5c953bd2ba2542ea7fb4fa2e80bc9433a348976305b8b1ead00"},"schema_version":"1.0"},"canonical_sha256":"738ece03b3401bce0d3804bdea7654cfce053a4e763bd65ef8b021a221c46a25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:56.904211Z","signature_b64":"TOdJVVGtsq8i3dTVkDV8hYjK4H5xHp1LjXcis9kYUPxsWabefVnEdHMRHM7KWtXXJ2/ZX0iLS9r4kBTeIfoZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"738ece03b3401bce0d3804bdea7654cfce053a4e763bd65ef8b021a221c46a25","last_reissued_at":"2026-05-17T23:58:56.903608Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:56.903608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.02205","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":"2026-05-17T23:58:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOPUYPrka+5EQxtuuOCb8Tr4eTryCzKyZ1TiYEPgsIrOBiwBajd4mjMfOfQYI/mMySEmKDhFi5C7pk9GqMoeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:07:04.826105Z"},"content_sha256":"9f7b70ac17bcd8b082d4220d21c279a6a8b42686180dbe4b25f631614d8f45e2","schema_version":"1.0","event_id":"sha256:9f7b70ac17bcd8b082d4220d21c279a6a8b42686180dbe4b25f631614d8f45e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OOHM4A5TIAN44DJYAS66U5SUZ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are you tough enough? Framework for Robustness Validation of Machine Comprehension Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Rychalska, Dominika Basaj, Przemyslaw Biecek","submitted_at":"2018-12-05T19:55:24Z","abstract_excerpt":"Deep Learning NLP domain lacks procedures for the analysis of model robustness. In this paper we propose a framework which validates robustness of any Question Answering model through model explainers. We propose that a robust model should transgress the initial notion of semantic similarity induced by word embeddings to learn a more human-like understanding of meaning. We test this property by manipulating questions in two ways: swapping important question word for 1) its semantically correct synonym and 2) for word vector that is close in embedding space. We estimate importance of words in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02205","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":"2026-05-17T23:58:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fj+Ljd/1yPeVVSEO4YtQ60SgeusGkmzG5RYHWzyLxjHGCb+hoHxQ1JXA9eItx6A/tsCmelmUFR3zxLHF44hlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:07:04.827150Z"},"content_sha256":"7a627e197c99b43d5fbc37ec4275e29ffda1561cdae17eeb43576de7367babab","schema_version":"1.0","event_id":"sha256:7a627e197c99b43d5fbc37ec4275e29ffda1561cdae17eeb43576de7367babab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOHM4A5TIAN44DJYAS66U5SUZ7/bundle.json","state_url":"https://pith.science/pith/OOHM4A5TIAN44DJYAS66U5SUZ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOHM4A5TIAN44DJYAS66U5SUZ7/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":"2026-05-28T09:07:04Z","links":{"resolver":"https://pith.science/pith/OOHM4A5TIAN44DJYAS66U5SUZ7","bundle":"https://pith.science/pith/OOHM4A5TIAN44DJYAS66U5SUZ7/bundle.json","state":"https://pith.science/pith/OOHM4A5TIAN44DJYAS66U5SUZ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOHM4A5TIAN44DJYAS66U5SUZ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OOHM4A5TIAN44DJYAS66U5SUZ7","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":"0f0cba934282b5c953bd2ba2542ea7fb4fa2e80bc9433a348976305b8b1ead00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T19:55:24Z","title_canon_sha256":"e0f338e14da2fa3292f9df01732da0885521e8823c960550b47a14fb027d3791"},"schema_version":"1.0","source":{"id":"1812.02205","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02205","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02205v1","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02205","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"pith_short_12","alias_value":"OOHM4A5TIAN4","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OOHM4A5TIAN44DJY","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OOHM4A5T","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:7a627e197c99b43d5fbc37ec4275e29ffda1561cdae17eeb43576de7367babab","target":"graph","created_at":"2026-05-17T23:58:56Z","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":"Deep Learning NLP domain lacks procedures for the analysis of model robustness. In this paper we propose a framework which validates robustness of any Question Answering model through model explainers. We propose that a robust model should transgress the initial notion of semantic similarity induced by word embeddings to learn a more human-like understanding of meaning. We test this property by manipulating questions in two ways: swapping important question word for 1) its semantically correct synonym and 2) for word vector that is close in embedding space. We estimate importance of words in a","authors_text":"Barbara Rychalska, Dominika Basaj, Przemyslaw Biecek","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T19:55:24Z","title":"Are you tough enough? Framework for Robustness Validation of Machine Comprehension Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02205","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":"sha256:9f7b70ac17bcd8b082d4220d21c279a6a8b42686180dbe4b25f631614d8f45e2","target":"record","created_at":"2026-05-17T23:58:56Z","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":"0f0cba934282b5c953bd2ba2542ea7fb4fa2e80bc9433a348976305b8b1ead00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T19:55:24Z","title_canon_sha256":"e0f338e14da2fa3292f9df01732da0885521e8823c960550b47a14fb027d3791"},"schema_version":"1.0","source":{"id":"1812.02205","kind":"arxiv","version":1}},"canonical_sha256":"738ece03b3401bce0d3804bdea7654cfce053a4e763bd65ef8b021a221c46a25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"738ece03b3401bce0d3804bdea7654cfce053a4e763bd65ef8b021a221c46a25","first_computed_at":"2026-05-17T23:58:56.903608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:56.903608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TOdJVVGtsq8i3dTVkDV8hYjK4H5xHp1LjXcis9kYUPxsWabefVnEdHMRHM7KWtXXJ2/ZX0iLS9r4kBTeIfoZCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:56.904211Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02205","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f7b70ac17bcd8b082d4220d21c279a6a8b42686180dbe4b25f631614d8f45e2","sha256:7a627e197c99b43d5fbc37ec4275e29ffda1561cdae17eeb43576de7367babab"],"state_sha256":"f4bcb32809ffec964357728acd91bf153bba191d29996fa0af5926e204e3453e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OXc+ey3XfdvGjObFg3NPUUf0aeIMZh1TVzmRIKTVhep+vgH1fZNggWqV1XoKUhVhJ98fm9g1CiUPNYO85vX4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T09:07:04.841347Z","bundle_sha256":"4604d36db8c9e601ee8415af3eea7894ab8f368b29f2ef1fe4fff773dab93fea"}}