{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QLYDKPVKLK7CMJPUC6KY7MY2WH","short_pith_number":"pith:QLYDKPVK","schema_version":"1.0","canonical_sha256":"82f0353eaa5abe2625f417958fb31ab1f92b796e81295efc7b7c2d6921fbadee","source":{"kind":"arxiv","id":"2601.00567","version":2},"attestation_state":"computed","paper":{"title":"Improving Scientific Document Retrieval with Academic Concept Index","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bowen Jin, Dongha Lee, HwanJo Yu, Jeyun Lee, Jiawei Han, Junhyoung Lee, SeongKu Kang, Susik Yoon, Wonbin Kweon, Yu Zhang","submitted_at":"2026-01-02T04:47:49Z","abstract_excerpt":"Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs. Recent approaches address these issues through two independent directions that leverage large language models (LLMs): (1) generating synthetic queries for fine-tuning, and (2) generating auxiliary contexts to support relevance matching. However, both directions overlook the diverse academic concepts embedded within scientific documents, often producing redundant or conceptually narrow q"},"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":"2601.00567","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-01-02T04:47:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"214a2d8c49893885dda200b114365eafba0ad8901c685c056885b81dce9f63d3","abstract_canon_sha256":"1957e3d79d52649e41efdcb470392c1f1df973f357dc91a354379083d1631700"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:18.885046Z","signature_b64":"7Kk5BKxqeZ+iDs4mIYJb7t+Mksc41Hnr0ws8wZXBLB5Rb087LT6msomIV4bdlj4+DY+LopOiVqFowVG7g7zzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82f0353eaa5abe2625f417958fb31ab1f92b796e81295efc7b7c2d6921fbadee","last_reissued_at":"2026-06-19T16:11:18.884600Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:18.884600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Scientific Document Retrieval with Academic Concept Index","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bowen Jin, Dongha Lee, HwanJo Yu, Jeyun Lee, Jiawei Han, Junhyoung Lee, SeongKu Kang, Susik Yoon, Wonbin Kweon, Yu Zhang","submitted_at":"2026-01-02T04:47:49Z","abstract_excerpt":"Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs. Recent approaches address these issues through two independent directions that leverage large language models (LLMs): (1) generating synthetic queries for fine-tuning, and (2) generating auxiliary contexts to support relevance matching. However, both directions overlook the diverse academic concepts embedded within scientific documents, often producing redundant or conceptually narrow q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.00567","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/2601.00567/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":"2601.00567","created_at":"2026-06-19T16:11:18.884655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.00567v2","created_at":"2026-06-19T16:11:18.884655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.00567","created_at":"2026-06-19T16:11:18.884655+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLYDKPVKLK7C","created_at":"2026-06-19T16:11:18.884655+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLYDKPVKLK7CMJPU","created_at":"2026-06-19T16:11:18.884655+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLYDKPVK","created_at":"2026-06-19T16:11:18.884655+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/QLYDKPVKLK7CMJPUC6KY7MY2WH","json":"https://pith.science/pith/QLYDKPVKLK7CMJPUC6KY7MY2WH.json","graph_json":"https://pith.science/api/pith-number/QLYDKPVKLK7CMJPUC6KY7MY2WH/graph.json","events_json":"https://pith.science/api/pith-number/QLYDKPVKLK7CMJPUC6KY7MY2WH/events.json","paper":"https://pith.science/paper/QLYDKPVK"},"agent_actions":{"view_html":"https://pith.science/pith/QLYDKPVKLK7CMJPUC6KY7MY2WH","download_json":"https://pith.science/pith/QLYDKPVKLK7CMJPUC6KY7MY2WH.json","view_paper":"https://pith.science/paper/QLYDKPVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.00567&json=true","fetch_graph":"https://pith.science/api/pith-number/QLYDKPVKLK7CMJPUC6KY7MY2WH/graph.json","fetch_events":"https://pith.science/api/pith-number/QLYDKPVKLK7CMJPUC6KY7MY2WH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLYDKPVKLK7CMJPUC6KY7MY2WH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLYDKPVKLK7CMJPUC6KY7MY2WH/action/storage_attestation","attest_author":"https://pith.science/pith/QLYDKPVKLK7CMJPUC6KY7MY2WH/action/author_attestation","sign_citation":"https://pith.science/pith/QLYDKPVKLK7CMJPUC6KY7MY2WH/action/citation_signature","submit_replication":"https://pith.science/pith/QLYDKPVKLK7CMJPUC6KY7MY2WH/action/replication_record"}},"created_at":"2026-06-19T16:11:18.884655+00:00","updated_at":"2026-06-19T16:11:18.884655+00:00"}