{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P6BHWWIUEAVS35U2FXYPKD7KEI","short_pith_number":"pith:P6BHWWIU","schema_version":"1.0","canonical_sha256":"7f827b5914202b2df69a2df0f50fea2226610cc7cafe41043c5144384da70da6","source":{"kind":"arxiv","id":"1811.07033","version":1},"attestation_state":"computed","paper":{"title":"Analyzing Compositionality-Sensitivity of NLI Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mohit Bansal, Yicheng Wang, Yixin Nie","submitted_at":"2018-11-16T21:12:24Z","abstract_excerpt":"Success in natural language inference (NLI) should require a model to understand both lexical and compositional semantics. However, through adversarial evaluation, we find that several state-of-the-art models with diverse architectures are over-relying on the former and fail to use the latter. Further, this compositionality unawareness is not reflected via standard evaluation on current datasets. We show that removing RNNs in existing models or shuffling input words during training does not induce large performance loss despite the explicit removal of compositional information. Therefore, we p"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1811.07033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-16T21:12:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4df79500c930d979e1c4dab0db5f4f84c5935b230f21b7de41ce396ade69a889","abstract_canon_sha256":"012d26e3a2fc5e2bd4ebe90aab121ae5256ac1659c1dc587b4af20637c319ea0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:29.211707Z","signature_b64":"Id+/IQipTGQu2yde5QzS9SbOIE1mkhjtFptwo71qMpszDOEem4+FNPD+QFyZv7mlRVO48duQYV5Y4jmq+SUKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f827b5914202b2df69a2df0f50fea2226610cc7cafe41043c5144384da70da6","last_reissued_at":"2026-05-18T00:00:29.211197Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:29.211197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing Compositionality-Sensitivity of NLI Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mohit Bansal, Yicheng Wang, Yixin Nie","submitted_at":"2018-11-16T21:12:24Z","abstract_excerpt":"Success in natural language inference (NLI) should require a model to understand both lexical and compositional semantics. However, through adversarial evaluation, we find that several state-of-the-art models with diverse architectures are over-relying on the former and fail to use the latter. Further, this compositionality unawareness is not reflected via standard evaluation on current datasets. We show that removing RNNs in existing models or shuffling input words during training does not induce large performance loss despite the explicit removal of compositional information. Therefore, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07033","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1811.07033","created_at":"2026-05-18T00:00:29.211263+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.07033v1","created_at":"2026-05-18T00:00:29.211263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07033","created_at":"2026-05-18T00:00:29.211263+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6BHWWIUEAVS","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6BHWWIUEAVS35U2","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6BHWWIU","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6BHWWIUEAVS35U2FXYPKD7KEI","json":"https://pith.science/pith/P6BHWWIUEAVS35U2FXYPKD7KEI.json","graph_json":"https://pith.science/api/pith-number/P6BHWWIUEAVS35U2FXYPKD7KEI/graph.json","events_json":"https://pith.science/api/pith-number/P6BHWWIUEAVS35U2FXYPKD7KEI/events.json","paper":"https://pith.science/paper/P6BHWWIU"},"agent_actions":{"view_html":"https://pith.science/pith/P6BHWWIUEAVS35U2FXYPKD7KEI","download_json":"https://pith.science/pith/P6BHWWIUEAVS35U2FXYPKD7KEI.json","view_paper":"https://pith.science/paper/P6BHWWIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.07033&json=true","fetch_graph":"https://pith.science/api/pith-number/P6BHWWIUEAVS35U2FXYPKD7KEI/graph.json","fetch_events":"https://pith.science/api/pith-number/P6BHWWIUEAVS35U2FXYPKD7KEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6BHWWIUEAVS35U2FXYPKD7KEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6BHWWIUEAVS35U2FXYPKD7KEI/action/storage_attestation","attest_author":"https://pith.science/pith/P6BHWWIUEAVS35U2FXYPKD7KEI/action/author_attestation","sign_citation":"https://pith.science/pith/P6BHWWIUEAVS35U2FXYPKD7KEI/action/citation_signature","submit_replication":"https://pith.science/pith/P6BHWWIUEAVS35U2FXYPKD7KEI/action/replication_record"}},"created_at":"2026-05-18T00:00:29.211263+00:00","updated_at":"2026-05-18T00:00:29.211263+00:00"}