{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:52UTWEQBNXBIK7XWRFRV4IPJ54","short_pith_number":"pith:52UTWEQB","schema_version":"1.0","canonical_sha256":"eea93b12016dc2857ef689635e21e9ef250184a647de9552b05c5e4ccb8a432f","source":{"kind":"arxiv","id":"2405.19893","version":1},"attestation_state":"computed","paper":{"title":"Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"BinBin Hu, Chunjing Gan, Dan Yang, Hanxiao Zhang, Jinjie Gu, Jun Zhou, Lei Liang, Lin Ju, Siyuan Li, Yue Shen, Zhiqiang Zhang, Ziqi Liu","submitted_at":"2024-05-30T09:50:38Z","abstract_excerpt":"In recent years, large language models (LLMs) have made remarkable achievements in various domains. However, the untimeliness and cost of knowledge updates coupled with hallucination issues of LLMs have curtailed their applications in knowledge intensive tasks, where retrieval augmented generation (RAG) can be of help. Nevertheless, existing retrieval augmented models typically use similarity as a bridge between queries and documents and follow a retrieve then read procedure. In this work, we argue that similarity is not always the panacea and totally relying on similarity would sometimes degr"},"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":"2405.19893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T09:50:38Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b0cf8f2c5ddc47072013c1e0d569a2c85776eecb2fd52c5e71ffdbd017af258b","abstract_canon_sha256":"fb5b4102a660fb37127dfe72d7bb46bea60b89a5bd169bf523a3a6395ed28416"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:23.754637Z","signature_b64":"3fHhGam0R6oyyaLaxKcGNN0n/UOrm8rCMiGA/Pt2yvUVbPPoO2KfNfQ/2JS4+MlIkl6ek87lz4c976MTKVpVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eea93b12016dc2857ef689635e21e9ef250184a647de9552b05c5e4ccb8a432f","last_reissued_at":"2026-07-05T08:25:23.754096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:23.754096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"BinBin Hu, Chunjing Gan, Dan Yang, Hanxiao Zhang, Jinjie Gu, Jun Zhou, Lei Liang, Lin Ju, Siyuan Li, Yue Shen, Zhiqiang Zhang, Ziqi Liu","submitted_at":"2024-05-30T09:50:38Z","abstract_excerpt":"In recent years, large language models (LLMs) have made remarkable achievements in various domains. However, the untimeliness and cost of knowledge updates coupled with hallucination issues of LLMs have curtailed their applications in knowledge intensive tasks, where retrieval augmented generation (RAG) can be of help. Nevertheless, existing retrieval augmented models typically use similarity as a bridge between queries and documents and follow a retrieve then read procedure. In this work, we argue that similarity is not always the panacea and totally relying on similarity would sometimes degr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19893","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/2405.19893/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":"2405.19893","created_at":"2026-07-05T08:25:23.754157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19893v1","created_at":"2026-07-05T08:25:23.754157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19893","created_at":"2026-07-05T08:25:23.754157+00:00"},{"alias_kind":"pith_short_12","alias_value":"52UTWEQBNXBI","created_at":"2026-07-05T08:25:23.754157+00:00"},{"alias_kind":"pith_short_16","alias_value":"52UTWEQBNXBIK7XW","created_at":"2026-07-05T08:25:23.754157+00:00"},{"alias_kind":"pith_short_8","alias_value":"52UTWEQB","created_at":"2026-07-05T08:25:23.754157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30690","citing_title":"ElasticMem: Latent Memory as a Learnable Resource for LLM Agents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11653","citing_title":"GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08920","citing_title":"Beyond Relevance: Utility-Centric Retrieval in the LLM Era","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52UTWEQBNXBIK7XWRFRV4IPJ54","json":"https://pith.science/pith/52UTWEQBNXBIK7XWRFRV4IPJ54.json","graph_json":"https://pith.science/api/pith-number/52UTWEQBNXBIK7XWRFRV4IPJ54/graph.json","events_json":"https://pith.science/api/pith-number/52UTWEQBNXBIK7XWRFRV4IPJ54/events.json","paper":"https://pith.science/paper/52UTWEQB"},"agent_actions":{"view_html":"https://pith.science/pith/52UTWEQBNXBIK7XWRFRV4IPJ54","download_json":"https://pith.science/pith/52UTWEQBNXBIK7XWRFRV4IPJ54.json","view_paper":"https://pith.science/paper/52UTWEQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19893&json=true","fetch_graph":"https://pith.science/api/pith-number/52UTWEQBNXBIK7XWRFRV4IPJ54/graph.json","fetch_events":"https://pith.science/api/pith-number/52UTWEQBNXBIK7XWRFRV4IPJ54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52UTWEQBNXBIK7XWRFRV4IPJ54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52UTWEQBNXBIK7XWRFRV4IPJ54/action/storage_attestation","attest_author":"https://pith.science/pith/52UTWEQBNXBIK7XWRFRV4IPJ54/action/author_attestation","sign_citation":"https://pith.science/pith/52UTWEQBNXBIK7XWRFRV4IPJ54/action/citation_signature","submit_replication":"https://pith.science/pith/52UTWEQBNXBIK7XWRFRV4IPJ54/action/replication_record"}},"created_at":"2026-07-05T08:25:23.754157+00:00","updated_at":"2026-07-05T08:25:23.754157+00:00"}