{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3YLD3GLMVTIPPGQ5HRDS6GROID","short_pith_number":"pith:3YLD3GLM","schema_version":"1.0","canonical_sha256":"de163d996cacd0f79a1d3c472f1a2e40fe386ad6326fc16b0388aa79965d2607","source":{"kind":"arxiv","id":"2502.07555","version":2},"attestation_state":"computed","paper":{"title":"O1 Embedder: Let Retrievers Think Before Action","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Defu Lian, Ruiran Yan, Zheng Liu","submitted_at":"2025-02-11T13:48:10Z","abstract_excerpt":"The growing power of large language models (LLMs) has revolutionized how people access and utilize information. Notably, the LLMs excel at performing fine-grained data representation, which facilitates precise retrieval of information. They also generate high-quality answers based on external references, enabling the production of useful knowledge. The recent introduction of reasoning models, like OpenAI O1 and DeepSeek R1, marks another leap forward, highlighting LLMs' ability to think progressively before delivering final answers. This breakthrough significantly improves the ability to addre"},"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":"2502.07555","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T13:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"3f6d9e64c30928dd075f76e27d71b3316f7e6fc7070e8f7e6bf0c65d84abbf73","abstract_canon_sha256":"dfdad2fd1a56edb218c1dadd7d99bae07c2940e8bd98b7b23ad836e9add42b6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:09.587857Z","signature_b64":"5LVD5KVqrjIw6BLqZHHtSs+8nggWlcV21Lg3hHEwdPDZrYpsM9fEDCNtAZxExHPn/nMq4dbyHiHieDnTTWY2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de163d996cacd0f79a1d3c472f1a2e40fe386ad6326fc16b0388aa79965d2607","last_reissued_at":"2026-07-05T10:13:09.587281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:09.587281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"O1 Embedder: Let Retrievers Think Before Action","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Defu Lian, Ruiran Yan, Zheng Liu","submitted_at":"2025-02-11T13:48:10Z","abstract_excerpt":"The growing power of large language models (LLMs) has revolutionized how people access and utilize information. Notably, the LLMs excel at performing fine-grained data representation, which facilitates precise retrieval of information. They also generate high-quality answers based on external references, enabling the production of useful knowledge. The recent introduction of reasoning models, like OpenAI O1 and DeepSeek R1, marks another leap forward, highlighting LLMs' ability to think progressively before delivering final answers. This breakthrough significantly improves the ability to addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07555","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/2502.07555/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":"2502.07555","created_at":"2026-07-05T10:13:09.587361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07555v2","created_at":"2026-07-05T10:13:09.587361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07555","created_at":"2026-07-05T10:13:09.587361+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YLD3GLMVTIP","created_at":"2026-07-05T10:13:09.587361+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YLD3GLMVTIPPGQ5","created_at":"2026-07-05T10:13:09.587361+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YLD3GLM","created_at":"2026-07-05T10:13:09.587361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.19827","citing_title":"When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00063","citing_title":"A Survey of Reasoning-Intensive Retrieval: Progress and Challenges","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YLD3GLMVTIPPGQ5HRDS6GROID","json":"https://pith.science/pith/3YLD3GLMVTIPPGQ5HRDS6GROID.json","graph_json":"https://pith.science/api/pith-number/3YLD3GLMVTIPPGQ5HRDS6GROID/graph.json","events_json":"https://pith.science/api/pith-number/3YLD3GLMVTIPPGQ5HRDS6GROID/events.json","paper":"https://pith.science/paper/3YLD3GLM"},"agent_actions":{"view_html":"https://pith.science/pith/3YLD3GLMVTIPPGQ5HRDS6GROID","download_json":"https://pith.science/pith/3YLD3GLMVTIPPGQ5HRDS6GROID.json","view_paper":"https://pith.science/paper/3YLD3GLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07555&json=true","fetch_graph":"https://pith.science/api/pith-number/3YLD3GLMVTIPPGQ5HRDS6GROID/graph.json","fetch_events":"https://pith.science/api/pith-number/3YLD3GLMVTIPPGQ5HRDS6GROID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YLD3GLMVTIPPGQ5HRDS6GROID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YLD3GLMVTIPPGQ5HRDS6GROID/action/storage_attestation","attest_author":"https://pith.science/pith/3YLD3GLMVTIPPGQ5HRDS6GROID/action/author_attestation","sign_citation":"https://pith.science/pith/3YLD3GLMVTIPPGQ5HRDS6GROID/action/citation_signature","submit_replication":"https://pith.science/pith/3YLD3GLMVTIPPGQ5HRDS6GROID/action/replication_record"}},"created_at":"2026-07-05T10:13:09.587361+00:00","updated_at":"2026-07-05T10:13:09.587361+00:00"}