{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VGWMGPRMTGC6B6ZKXKQPA7HDZA","short_pith_number":"pith:VGWMGPRM","schema_version":"1.0","canonical_sha256":"a9acc33e2c9985e0fb2abaa0f07ce3c805467f6255cb3e0709902a4c0ed0db3a","source":{"kind":"arxiv","id":"2406.02266","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Chuankai Xu, Dongming Zhao, Hanwen Xing","submitted_at":"2024-06-04T12:43:23Z","abstract_excerpt":"Despite the prevalence of retrieval-augmented language models (RALMs), the seamless integration of these models with retrieval mechanisms to enhance performance in document-based tasks remains challenging. While some post-retrieval processing Retrieval-Augmented Generation (RAG) methods have achieved success, most still lack the ability to distinguish pertinent from extraneous information, leading to potential inconsistencies and reduced precision in the generated output, which subsequently affects the truthfulness of the language model's responses. To address these limitations, this work prop"},"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":"2406.02266","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T12:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"dafa61b9ce03ad1bd522c2ee0a07f18c352bd78b3c3772bd6e91b856fdb920e7","abstract_canon_sha256":"da8608767f9d94481f168363882e4ca3e352bad60d870a57933a68aadc2ae23c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:17.157421Z","signature_b64":"XvLH4yAPc8jXcnUcYxxJfvwvjVEiRTHAuEPRPfNQxNQNXmInayrI6kX+o22F1g9cwM9NAIuuo3v2TawGmtdnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9acc33e2c9985e0fb2abaa0f07ce3c805467f6255cb3e0709902a4c0ed0db3a","last_reissued_at":"2026-07-05T08:27:17.156952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:17.156952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Chuankai Xu, Dongming Zhao, Hanwen Xing","submitted_at":"2024-06-04T12:43:23Z","abstract_excerpt":"Despite the prevalence of retrieval-augmented language models (RALMs), the seamless integration of these models with retrieval mechanisms to enhance performance in document-based tasks remains challenging. While some post-retrieval processing Retrieval-Augmented Generation (RAG) methods have achieved success, most still lack the ability to distinguish pertinent from extraneous information, leading to potential inconsistencies and reduced precision in the generated output, which subsequently affects the truthfulness of the language model's responses. To address these limitations, this work prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02266","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/2406.02266/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":"2406.02266","created_at":"2026-07-05T08:27:17.157007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02266v1","created_at":"2026-07-05T08:27:17.157007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02266","created_at":"2026-07-05T08:27:17.157007+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGWMGPRMTGC6","created_at":"2026-07-05T08:27:17.157007+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGWMGPRMTGC6B6ZK","created_at":"2026-07-05T08:27:17.157007+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGWMGPRM","created_at":"2026-07-05T08:27:17.157007+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/VGWMGPRMTGC6B6ZKXKQPA7HDZA","json":"https://pith.science/pith/VGWMGPRMTGC6B6ZKXKQPA7HDZA.json","graph_json":"https://pith.science/api/pith-number/VGWMGPRMTGC6B6ZKXKQPA7HDZA/graph.json","events_json":"https://pith.science/api/pith-number/VGWMGPRMTGC6B6ZKXKQPA7HDZA/events.json","paper":"https://pith.science/paper/VGWMGPRM"},"agent_actions":{"view_html":"https://pith.science/pith/VGWMGPRMTGC6B6ZKXKQPA7HDZA","download_json":"https://pith.science/pith/VGWMGPRMTGC6B6ZKXKQPA7HDZA.json","view_paper":"https://pith.science/paper/VGWMGPRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02266&json=true","fetch_graph":"https://pith.science/api/pith-number/VGWMGPRMTGC6B6ZKXKQPA7HDZA/graph.json","fetch_events":"https://pith.science/api/pith-number/VGWMGPRMTGC6B6ZKXKQPA7HDZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGWMGPRMTGC6B6ZKXKQPA7HDZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGWMGPRMTGC6B6ZKXKQPA7HDZA/action/storage_attestation","attest_author":"https://pith.science/pith/VGWMGPRMTGC6B6ZKXKQPA7HDZA/action/author_attestation","sign_citation":"https://pith.science/pith/VGWMGPRMTGC6B6ZKXKQPA7HDZA/action/citation_signature","submit_replication":"https://pith.science/pith/VGWMGPRMTGC6B6ZKXKQPA7HDZA/action/replication_record"}},"created_at":"2026-07-05T08:27:17.157007+00:00","updated_at":"2026-07-05T08:27:17.157007+00:00"}