{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6PLKBFMQLD6PSTPW574NZ7XMHQ","short_pith_number":"pith:6PLKBFMQ","schema_version":"1.0","canonical_sha256":"f3d6a0959058fcf94df6eff8dcfeec3c26ef62a4b7e3ff10a5faccc24450fa72","source":{"kind":"arxiv","id":"2602.23665","version":5},"attestation_state":"computed","paper":{"title":"Geodesic Semantic Search: Cartographic Navigation of Citation Graphs with Learned Local Riemannian Maps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Learning node-specific Riemannian metrics on citation graphs turns direct similarity search into geodesic navigation that improves recall.","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.IR","authors_text":"Brandon Yee, Kundana Kommini, Lucas Wang","submitted_at":"2026-02-27T04:17:41Z","abstract_excerpt":"We present Geodesic Semantic Search (GSS), a retrieval system that learns node-specific Riemannian metrics on citation graphs to enable geometry-aware semantic search. Unlike standard embedding-based retrieval that relies on fixed Euclidean distances, \\gss{} learns a low-rank metric tensor $\\mL_i \\in \\R^{d \\times r}$ at each node, inducing a local positive semi-definite metric $\\mG_i = \\mL_i \\mL_i^\\top + \\eps \\mI$. This parameterization guarantees valid metrics while keeping the model tractable. Retrieval proceeds via multi-source Dijkstra on the learned geodesic distances, followed by Maximal"},"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":"2602.23665","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-27T04:17:41Z","cross_cats_sorted":["cs.LG","cs.SI"],"title_canon_sha256":"28edb9a09a6bd0ec50bb14e10a5cee236ff4d72921e9d3db11a191a08b175d53","abstract_canon_sha256":"9eb3e6c6776483ffcf98de7189e1543092a7c4cb29c6c97ddcb406e75285d684"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:22.468619Z","signature_b64":"0Uupd1KZYLKfxdzblDaviGUWOFeq8QJ0KgfrKD1BpbjiFSqgsy15HybnWiNWvuAbZB7LnOU0kMjsVR5smzA7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3d6a0959058fcf94df6eff8dcfeec3c26ef62a4b7e3ff10a5faccc24450fa72","last_reissued_at":"2026-06-05T01:15:22.468076Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:22.468076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geodesic Semantic Search: Cartographic Navigation of Citation Graphs with Learned Local Riemannian Maps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Learning node-specific Riemannian metrics on citation graphs turns direct similarity search into geodesic navigation that improves recall.","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.IR","authors_text":"Brandon Yee, Kundana Kommini, Lucas Wang","submitted_at":"2026-02-27T04:17:41Z","abstract_excerpt":"We present Geodesic Semantic Search (GSS), a retrieval system that learns node-specific Riemannian metrics on citation graphs to enable geometry-aware semantic search. Unlike standard embedding-based retrieval that relies on fixed Euclidean distances, \\gss{} learns a low-rank metric tensor $\\mL_i \\in \\R^{d \\times r}$ at each node, inducing a local positive semi-definite metric $\\mG_i = \\mL_i \\mL_i^\\top + \\eps \\mI$. This parameterization guarantees valid metrics while keeping the model tractable. Retrieval proceeds via multi-source Dijkstra on the learned geodesic distances, followed by Maximal"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On citation prediction benchmarks with 169K arXiv papers, GSS achieves 23% relative improvement in Recall@20 over SPECTER+FAISS baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the learned local Riemannian metrics meaningfully capture semantic relationships in the citation graph rather than merely fitting training patterns.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GSS learns per-node low-rank Riemannian metrics on citation graphs and retrieves via geodesic distances, yielding 23% higher Recall@20 than SPECTER+FAISS on 169K arXiv papers.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Learning node-specific Riemannian metrics on citation graphs turns direct similarity search into geodesic navigation that improves recall.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"78e649727e028ab9e697045600bdde60eefef7bbab4d2eae358752f0c4007eb0"},"source":{"id":"2602.23665","kind":"arxiv","version":5},"verdict":{"id":"3f9ee4e5-78ce-4b45-99ed-e516bca13b11","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T19:18:33.912220Z","strongest_claim":"On citation prediction benchmarks with 169K arXiv papers, GSS achieves 23% relative improvement in Recall@20 over SPECTER+FAISS baselines.","one_line_summary":"GSS learns per-node low-rank Riemannian metrics on citation graphs and retrieves via geodesic distances, yielding 23% higher Recall@20 than SPECTER+FAISS on 169K arXiv papers.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the learned local Riemannian metrics meaningfully capture semantic relationships in the citation graph rather than merely fitting training patterns.","pith_extraction_headline":"Learning node-specific Riemannian metrics on citation graphs turns direct similarity search into geodesic navigation that improves recall."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.23665/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":"2602.23665","created_at":"2026-06-05T01:15:22.468136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.23665v5","created_at":"2026-06-05T01:15:22.468136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23665","created_at":"2026-06-05T01:15:22.468136+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PLKBFMQLD6P","created_at":"2026-06-05T01:15:22.468136+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PLKBFMQLD6PSTPW","created_at":"2026-06-05T01:15:22.468136+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PLKBFMQ","created_at":"2026-06-05T01:15:22.468136+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/6PLKBFMQLD6PSTPW574NZ7XMHQ","json":"https://pith.science/pith/6PLKBFMQLD6PSTPW574NZ7XMHQ.json","graph_json":"https://pith.science/api/pith-number/6PLKBFMQLD6PSTPW574NZ7XMHQ/graph.json","events_json":"https://pith.science/api/pith-number/6PLKBFMQLD6PSTPW574NZ7XMHQ/events.json","paper":"https://pith.science/paper/6PLKBFMQ"},"agent_actions":{"view_html":"https://pith.science/pith/6PLKBFMQLD6PSTPW574NZ7XMHQ","download_json":"https://pith.science/pith/6PLKBFMQLD6PSTPW574NZ7XMHQ.json","view_paper":"https://pith.science/paper/6PLKBFMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.23665&json=true","fetch_graph":"https://pith.science/api/pith-number/6PLKBFMQLD6PSTPW574NZ7XMHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6PLKBFMQLD6PSTPW574NZ7XMHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PLKBFMQLD6PSTPW574NZ7XMHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PLKBFMQLD6PSTPW574NZ7XMHQ/action/storage_attestation","attest_author":"https://pith.science/pith/6PLKBFMQLD6PSTPW574NZ7XMHQ/action/author_attestation","sign_citation":"https://pith.science/pith/6PLKBFMQLD6PSTPW574NZ7XMHQ/action/citation_signature","submit_replication":"https://pith.science/pith/6PLKBFMQLD6PSTPW574NZ7XMHQ/action/replication_record"}},"created_at":"2026-06-05T01:15:22.468136+00:00","updated_at":"2026-06-05T01:15:22.468136+00:00"}