{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZXWRXB27ULUH63PTIOMYQQRWXC","short_pith_number":"pith:ZXWRXB27","schema_version":"1.0","canonical_sha256":"cded1b875fa2e87f6df34399884236b8b4445caa14ade1b3f1ca26ba095f7918","source":{"kind":"arxiv","id":"2408.08444","version":2},"attestation_state":"computed","paper":{"title":"W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinming Nian, Qifan Wang, Yi Fang, Zhiyuan Peng","submitted_at":"2024-08-15T22:34:44Z","abstract_excerpt":"In knowledge-intensive tasks such as open-domain question answering (OpenQA), large language models (LLMs) often struggle to generate factual answers, relying solely on their internal (parametric) knowledge. To address this limitation, Retrieval-Augmented Generation (RAG) systems enhance LLMs by retrieving relevant information from external sources, thereby positioning the retriever as a pivotal component. Although dense retrieval demonstrates state-of-the-art performance, its training poses challenges due to the scarcity of ground-truth evidence, largely attributed to the high costs of human "},"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":"2408.08444","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T22:34:44Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"5496f9c48d5f2d401906c565f773fca7ab0bb9b4c8a1bbe758c10b96240d001d","abstract_canon_sha256":"cba32e00cc0fe4f26db9b6971daa105544a09b12c49598541da822230e745c6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:12.556784Z","signature_b64":"kho3LdX/hRMsewCcYeQbxa4ArwhiuUyHuacZDC8xEy2iSuBB3oQu7OZAaU4eqn4ul43465OSirRNU7JfavP3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cded1b875fa2e87f6df34399884236b8b4445caa14ade1b3f1ca26ba095f7918","last_reissued_at":"2026-07-05T10:54:12.556205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:12.556205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinming Nian, Qifan Wang, Yi Fang, Zhiyuan Peng","submitted_at":"2024-08-15T22:34:44Z","abstract_excerpt":"In knowledge-intensive tasks such as open-domain question answering (OpenQA), large language models (LLMs) often struggle to generate factual answers, relying solely on their internal (parametric) knowledge. To address this limitation, Retrieval-Augmented Generation (RAG) systems enhance LLMs by retrieving relevant information from external sources, thereby positioning the retriever as a pivotal component. Although dense retrieval demonstrates state-of-the-art performance, its training poses challenges due to the scarcity of ground-truth evidence, largely attributed to the high costs of human "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08444","kind":"arxiv","version":2},"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/2408.08444/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":"2408.08444","created_at":"2026-07-05T10:54:12.556277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08444v2","created_at":"2026-07-05T10:54:12.556277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08444","created_at":"2026-07-05T10:54:12.556277+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXWRXB27ULUH","created_at":"2026-07-05T10:54:12.556277+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXWRXB27ULUH63PT","created_at":"2026-07-05T10:54:12.556277+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXWRXB27","created_at":"2026-07-05T10:54:12.556277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18710","citing_title":"GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXWRXB27ULUH63PTIOMYQQRWXC","json":"https://pith.science/pith/ZXWRXB27ULUH63PTIOMYQQRWXC.json","graph_json":"https://pith.science/api/pith-number/ZXWRXB27ULUH63PTIOMYQQRWXC/graph.json","events_json":"https://pith.science/api/pith-number/ZXWRXB27ULUH63PTIOMYQQRWXC/events.json","paper":"https://pith.science/paper/ZXWRXB27"},"agent_actions":{"view_html":"https://pith.science/pith/ZXWRXB27ULUH63PTIOMYQQRWXC","download_json":"https://pith.science/pith/ZXWRXB27ULUH63PTIOMYQQRWXC.json","view_paper":"https://pith.science/paper/ZXWRXB27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08444&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXWRXB27ULUH63PTIOMYQQRWXC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXWRXB27ULUH63PTIOMYQQRWXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXWRXB27ULUH63PTIOMYQQRWXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXWRXB27ULUH63PTIOMYQQRWXC/action/storage_attestation","attest_author":"https://pith.science/pith/ZXWRXB27ULUH63PTIOMYQQRWXC/action/author_attestation","sign_citation":"https://pith.science/pith/ZXWRXB27ULUH63PTIOMYQQRWXC/action/citation_signature","submit_replication":"https://pith.science/pith/ZXWRXB27ULUH63PTIOMYQQRWXC/action/replication_record"}},"created_at":"2026-07-05T10:54:12.556277+00:00","updated_at":"2026-07-05T10:54:12.556277+00:00"}