{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5EHZED6O5FNH22WNJGY5SBYTFW","short_pith_number":"pith:5EHZED6O","schema_version":"1.0","canonical_sha256":"e90f920fcee95a7d6acd49b1d907132d813038f89cbe35ea66484a32434691c2","source":{"kind":"arxiv","id":"2509.08216","version":1},"attestation_state":"computed","paper":{"title":"Vector embedding of multi-modal texts: a tool for discovery?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Beth Plale, Sachith Withana, Sai Navya Jyesta","submitted_at":"2025-09-10T01:14:48Z","abstract_excerpt":"Computer science texts are particularly rich in both narrative content and illustrative charts, algorithms, images, annotated diagrams, etc. This study explores the extent to which vector-based multimodal retrieval, powered by vision-language models (VLMs), can improve discovery across multi-modal (text and images) content. Using over 3,600 digitized textbook pages largely from computer science textbooks and a Vision Language Model (VLM), we generate multi-vector representations capturing both textual and visual semantics. These embeddings are stored in a vector database. We issue a benchmark "},"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":"2509.08216","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-10T01:14:48Z","cross_cats_sorted":[],"title_canon_sha256":"d5b03c70e158cfc611afd2abbbf2f896ea6d722020d59271d5fa9343113bb52a","abstract_canon_sha256":"d63ccb5eb83a62d948c8a32176a2e57df6a152d2489a5d0a9b9eec0ebffc2912"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:25.271819Z","signature_b64":"FW0Tx2jo6nAShY2NZysk6glAVKSUI7tySp2ET0Aq0p1rcuPvQ9Xcxg5ZEozfCMLYfOwl7XTnWO1BPm1yUfY/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e90f920fcee95a7d6acd49b1d907132d813038f89cbe35ea66484a32434691c2","last_reissued_at":"2026-07-05T12:08:25.271350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:25.271350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vector embedding of multi-modal texts: a tool for discovery?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Beth Plale, Sachith Withana, Sai Navya Jyesta","submitted_at":"2025-09-10T01:14:48Z","abstract_excerpt":"Computer science texts are particularly rich in both narrative content and illustrative charts, algorithms, images, annotated diagrams, etc. This study explores the extent to which vector-based multimodal retrieval, powered by vision-language models (VLMs), can improve discovery across multi-modal (text and images) content. Using over 3,600 digitized textbook pages largely from computer science textbooks and a Vision Language Model (VLM), we generate multi-vector representations capturing both textual and visual semantics. These embeddings are stored in a vector database. We issue a benchmark "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08216","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/2509.08216/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":"2509.08216","created_at":"2026-07-05T12:08:25.271414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08216v1","created_at":"2026-07-05T12:08:25.271414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08216","created_at":"2026-07-05T12:08:25.271414+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EHZED6O5FNH","created_at":"2026-07-05T12:08:25.271414+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EHZED6O5FNH22WN","created_at":"2026-07-05T12:08:25.271414+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EHZED6O","created_at":"2026-07-05T12:08:25.271414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20173","citing_title":"Qiskit Code Migration with LLMs","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EHZED6O5FNH22WNJGY5SBYTFW","json":"https://pith.science/pith/5EHZED6O5FNH22WNJGY5SBYTFW.json","graph_json":"https://pith.science/api/pith-number/5EHZED6O5FNH22WNJGY5SBYTFW/graph.json","events_json":"https://pith.science/api/pith-number/5EHZED6O5FNH22WNJGY5SBYTFW/events.json","paper":"https://pith.science/paper/5EHZED6O"},"agent_actions":{"view_html":"https://pith.science/pith/5EHZED6O5FNH22WNJGY5SBYTFW","download_json":"https://pith.science/pith/5EHZED6O5FNH22WNJGY5SBYTFW.json","view_paper":"https://pith.science/paper/5EHZED6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08216&json=true","fetch_graph":"https://pith.science/api/pith-number/5EHZED6O5FNH22WNJGY5SBYTFW/graph.json","fetch_events":"https://pith.science/api/pith-number/5EHZED6O5FNH22WNJGY5SBYTFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EHZED6O5FNH22WNJGY5SBYTFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EHZED6O5FNH22WNJGY5SBYTFW/action/storage_attestation","attest_author":"https://pith.science/pith/5EHZED6O5FNH22WNJGY5SBYTFW/action/author_attestation","sign_citation":"https://pith.science/pith/5EHZED6O5FNH22WNJGY5SBYTFW/action/citation_signature","submit_replication":"https://pith.science/pith/5EHZED6O5FNH22WNJGY5SBYTFW/action/replication_record"}},"created_at":"2026-07-05T12:08:25.271414+00:00","updated_at":"2026-07-05T12:08:25.271414+00:00"}