{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YZVH7RC2KMAISEHTB25PKALBDG","short_pith_number":"pith:YZVH7RC2","schema_version":"1.0","canonical_sha256":"c66a7fc45a53008910f30ebaf5016119b708a5aa22ac99ef062aa9adf4c95906","source":{"kind":"arxiv","id":"2108.07081","version":1},"attestation_state":"computed","paper":{"title":"Toward the Understanding of Deep Text Matching Models for Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jiafeng Guo, Liang Pang, Lijuan Chen, Xueqi Cheng, Yanyan Lan","submitted_at":"2021-08-16T13:33:15Z","abstract_excerpt":"Semantic text matching is a critical problem in information retrieval. Recently, deep learning techniques have been widely used in this area and obtained significant performance improvements. However, most models are black boxes and it is hard to understand what happened in the matching process, due to the poor interpretability of deep learning. This paper aims at tackling this problem. The key idea is to test whether existing deep text matching methods satisfy some fundamental heuristics in information retrieval. Specifically, four heuristics are used in our study, i.e., term frequency constr"},"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":"2108.07081","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-08-16T13:33:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4e806220621a374788d80efa7623fb9e7683e8e9bc177f8c08b8eeb6c068077","abstract_canon_sha256":"218a8b07025949bb2b8d64c22a60bb3025ccfcfec1edd4e76e47b9135de23469"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:00.832249Z","signature_b64":"UD2h//RG9T5yGfW0f7jXMZ+nVslmhmzJz0p/nz8YrzJ0mH5H7P1vjK/1NZAGEfmYVCuhtvfeWkHNdDuBV/cWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c66a7fc45a53008910f30ebaf5016119b708a5aa22ac99ef062aa9adf4c95906","last_reissued_at":"2026-07-05T03:06:00.831908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:00.831908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward the Understanding of Deep Text Matching Models for Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jiafeng Guo, Liang Pang, Lijuan Chen, Xueqi Cheng, Yanyan Lan","submitted_at":"2021-08-16T13:33:15Z","abstract_excerpt":"Semantic text matching is a critical problem in information retrieval. Recently, deep learning techniques have been widely used in this area and obtained significant performance improvements. However, most models are black boxes and it is hard to understand what happened in the matching process, due to the poor interpretability of deep learning. This paper aims at tackling this problem. The key idea is to test whether existing deep text matching methods satisfy some fundamental heuristics in information retrieval. Specifically, four heuristics are used in our study, i.e., term frequency constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07081","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/2108.07081/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":"2108.07081","created_at":"2026-07-05T03:06:00.831965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.07081v1","created_at":"2026-07-05T03:06:00.831965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07081","created_at":"2026-07-05T03:06:00.831965+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZVH7RC2KMAI","created_at":"2026-07-05T03:06:00.831965+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZVH7RC2KMAISEHT","created_at":"2026-07-05T03:06:00.831965+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZVH7RC2","created_at":"2026-07-05T03:06:00.831965+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/YZVH7RC2KMAISEHTB25PKALBDG","json":"https://pith.science/pith/YZVH7RC2KMAISEHTB25PKALBDG.json","graph_json":"https://pith.science/api/pith-number/YZVH7RC2KMAISEHTB25PKALBDG/graph.json","events_json":"https://pith.science/api/pith-number/YZVH7RC2KMAISEHTB25PKALBDG/events.json","paper":"https://pith.science/paper/YZVH7RC2"},"agent_actions":{"view_html":"https://pith.science/pith/YZVH7RC2KMAISEHTB25PKALBDG","download_json":"https://pith.science/pith/YZVH7RC2KMAISEHTB25PKALBDG.json","view_paper":"https://pith.science/paper/YZVH7RC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.07081&json=true","fetch_graph":"https://pith.science/api/pith-number/YZVH7RC2KMAISEHTB25PKALBDG/graph.json","fetch_events":"https://pith.science/api/pith-number/YZVH7RC2KMAISEHTB25PKALBDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZVH7RC2KMAISEHTB25PKALBDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZVH7RC2KMAISEHTB25PKALBDG/action/storage_attestation","attest_author":"https://pith.science/pith/YZVH7RC2KMAISEHTB25PKALBDG/action/author_attestation","sign_citation":"https://pith.science/pith/YZVH7RC2KMAISEHTB25PKALBDG/action/citation_signature","submit_replication":"https://pith.science/pith/YZVH7RC2KMAISEHTB25PKALBDG/action/replication_record"}},"created_at":"2026-07-05T03:06:00.831965+00:00","updated_at":"2026-07-05T03:06:00.831965+00:00"}