{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZN5BIM3U6HZT7465CPEPK7LPRK","short_pith_number":"pith:ZN5BIM3U","schema_version":"1.0","canonical_sha256":"cb7a143374f1f33ff3dd13c8f57d6f8abac1616fa620563f7ef64c91ed9a1700","source":{"kind":"arxiv","id":"2509.00276","version":1},"attestation_state":"computed","paper":{"title":"Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gourab Kundu, Guang Cheng, Jianshu Chen, Qingjun Cui, Tian Wang, Tianyu Cao, Trishul Chilimbi, Yuxiang Liu, Zhen Ge","submitted_at":"2025-08-29T23:22:34Z","abstract_excerpt":"Transformer-based models such as BERT and E5 have significantly advanced text embedding by capturing rich contextual representations. However, many complex real-world queries require sophisticated reasoning to retrieve relevant documents beyond surface-level lexical matching, where encoder-only retrievers often fall short. Decoder-only large language models (LLMs), known for their strong reasoning capabilities, offer a promising alternative. Despite this potential, existing LLM-based embedding methods primarily focus on contextual representation and do not fully exploit the reasoning strength "},"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":"2509.00276","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T23:22:34Z","cross_cats_sorted":[],"title_canon_sha256":"2566a11f00fb70874d0d243007200b316ce70ce7cdd619e0fef5bd8b27d335ca","abstract_canon_sha256":"c0b854c92815d49e26139aede55ec77f661237b47308943f2bade698c39bc3c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:12.667750Z","signature_b64":"RAvcgB/HDzrwKQGNUdREiTwXrZic7AulwJStAXpHXmYatNeTXkeSYQMOROX/3atagHZK8bgzIjONnga4p7zFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb7a143374f1f33ff3dd13c8f57d6f8abac1616fa620563f7ef64c91ed9a1700","last_reissued_at":"2026-07-05T12:02:12.667217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:12.667217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gourab Kundu, Guang Cheng, Jianshu Chen, Qingjun Cui, Tian Wang, Tianyu Cao, Trishul Chilimbi, Yuxiang Liu, Zhen Ge","submitted_at":"2025-08-29T23:22:34Z","abstract_excerpt":"Transformer-based models such as BERT and E5 have significantly advanced text embedding by capturing rich contextual representations. However, many complex real-world queries require sophisticated reasoning to retrieve relevant documents beyond surface-level lexical matching, where encoder-only retrievers often fall short. Decoder-only large language models (LLMs), known for their strong reasoning capabilities, offer a promising alternative. Despite this potential, existing LLM-based embedding methods primarily focus on contextual representation and do not fully exploit the reasoning strength "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00276","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/2509.00276/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":"2509.00276","created_at":"2026-07-05T12:02:12.667281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00276v1","created_at":"2026-07-05T12:02:12.667281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00276","created_at":"2026-07-05T12:02:12.667281+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZN5BIM3U6HZT","created_at":"2026-07-05T12:02:12.667281+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZN5BIM3U6HZT7465","created_at":"2026-07-05T12:02:12.667281+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZN5BIM3U","created_at":"2026-07-05T12:02:12.667281+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/ZN5BIM3U6HZT7465CPEPK7LPRK","json":"https://pith.science/pith/ZN5BIM3U6HZT7465CPEPK7LPRK.json","graph_json":"https://pith.science/api/pith-number/ZN5BIM3U6HZT7465CPEPK7LPRK/graph.json","events_json":"https://pith.science/api/pith-number/ZN5BIM3U6HZT7465CPEPK7LPRK/events.json","paper":"https://pith.science/paper/ZN5BIM3U"},"agent_actions":{"view_html":"https://pith.science/pith/ZN5BIM3U6HZT7465CPEPK7LPRK","download_json":"https://pith.science/pith/ZN5BIM3U6HZT7465CPEPK7LPRK.json","view_paper":"https://pith.science/paper/ZN5BIM3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00276&json=true","fetch_graph":"https://pith.science/api/pith-number/ZN5BIM3U6HZT7465CPEPK7LPRK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZN5BIM3U6HZT7465CPEPK7LPRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZN5BIM3U6HZT7465CPEPK7LPRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZN5BIM3U6HZT7465CPEPK7LPRK/action/storage_attestation","attest_author":"https://pith.science/pith/ZN5BIM3U6HZT7465CPEPK7LPRK/action/author_attestation","sign_citation":"https://pith.science/pith/ZN5BIM3U6HZT7465CPEPK7LPRK/action/citation_signature","submit_replication":"https://pith.science/pith/ZN5BIM3U6HZT7465CPEPK7LPRK/action/replication_record"}},"created_at":"2026-07-05T12:02:12.667281+00:00","updated_at":"2026-07-05T12:02:12.667281+00:00"}