{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3HXFAFLX6HLR4ITOLVAZ33SDXI","short_pith_number":"pith:3HXFAFLX","schema_version":"1.0","canonical_sha256":"d9ee501577f1d71e226e5d419dee43ba2f78cab9be7f8e2482f2568c7dfab49c","source":{"kind":"arxiv","id":"2010.03061","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Recognizing Textual Entailment as an NLP Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Poliak","submitted_at":"2020-10-06T22:23:00Z","abstract_excerpt":"Recognizing Textual Entailment (RTE) was proposed as a unified evaluation framework to compare semantic understanding of different NLP systems. In this survey paper, we provide an overview of different approaches for evaluating and understanding the reasoning capabilities of NLP systems. We then focus our discussion on RTE by highlighting prominent RTE datasets as well as advances in RTE dataset that focus on specific linguistic phenomena that can be used to evaluate NLP systems on a fine-grained level. We conclude by arguing that when evaluating NLP systems, the community should utilize newly"},"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":"2010.03061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T22:23:00Z","cross_cats_sorted":[],"title_canon_sha256":"2b1ae9d4a08aa4eeb9880861327af6b993e46271ec79241793355513c3c86f4c","abstract_canon_sha256":"3e6efc9afa1f3ddc887bb61b52ed8a1627c8f63455a1c614cdc060d68f7d01f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:59.043809Z","signature_b64":"yDghppY5MOPptUm0fcccpcdzJo8Z6JN4+orq24cVdphZGcdNh8W7jAkRaf9e/ykVBHj0piCdtGpjQeTy5i2lDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9ee501577f1d71e226e5d419dee43ba2f78cab9be7f8e2482f2568c7dfab49c","last_reissued_at":"2026-07-05T01:40:59.043291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:59.043291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Recognizing Textual Entailment as an NLP Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Poliak","submitted_at":"2020-10-06T22:23:00Z","abstract_excerpt":"Recognizing Textual Entailment (RTE) was proposed as a unified evaluation framework to compare semantic understanding of different NLP systems. In this survey paper, we provide an overview of different approaches for evaluating and understanding the reasoning capabilities of NLP systems. We then focus our discussion on RTE by highlighting prominent RTE datasets as well as advances in RTE dataset that focus on specific linguistic phenomena that can be used to evaluate NLP systems on a fine-grained level. We conclude by arguing that when evaluating NLP systems, the community should utilize newly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03061","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/2010.03061/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.03061","created_at":"2026-07-05T01:40:59.043355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03061v1","created_at":"2026-07-05T01:40:59.043355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03061","created_at":"2026-07-05T01:40:59.043355+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HXFAFLX6HLR","created_at":"2026-07-05T01:40:59.043355+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HXFAFLX6HLR4ITO","created_at":"2026-07-05T01:40:59.043355+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HXFAFLX","created_at":"2026-07-05T01:40:59.043355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14055","citing_title":"PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11222","citing_title":"ADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HXFAFLX6HLR4ITOLVAZ33SDXI","json":"https://pith.science/pith/3HXFAFLX6HLR4ITOLVAZ33SDXI.json","graph_json":"https://pith.science/api/pith-number/3HXFAFLX6HLR4ITOLVAZ33SDXI/graph.json","events_json":"https://pith.science/api/pith-number/3HXFAFLX6HLR4ITOLVAZ33SDXI/events.json","paper":"https://pith.science/paper/3HXFAFLX"},"agent_actions":{"view_html":"https://pith.science/pith/3HXFAFLX6HLR4ITOLVAZ33SDXI","download_json":"https://pith.science/pith/3HXFAFLX6HLR4ITOLVAZ33SDXI.json","view_paper":"https://pith.science/paper/3HXFAFLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03061&json=true","fetch_graph":"https://pith.science/api/pith-number/3HXFAFLX6HLR4ITOLVAZ33SDXI/graph.json","fetch_events":"https://pith.science/api/pith-number/3HXFAFLX6HLR4ITOLVAZ33SDXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HXFAFLX6HLR4ITOLVAZ33SDXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HXFAFLX6HLR4ITOLVAZ33SDXI/action/storage_attestation","attest_author":"https://pith.science/pith/3HXFAFLX6HLR4ITOLVAZ33SDXI/action/author_attestation","sign_citation":"https://pith.science/pith/3HXFAFLX6HLR4ITOLVAZ33SDXI/action/citation_signature","submit_replication":"https://pith.science/pith/3HXFAFLX6HLR4ITOLVAZ33SDXI/action/replication_record"}},"created_at":"2026-07-05T01:40:59.043355+00:00","updated_at":"2026-07-05T01:40:59.043355+00:00"}