{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OENZBE2JKRWP263B3RHCTTIYXB","short_pith_number":"pith:OENZBE2J","schema_version":"1.0","canonical_sha256":"711b909349546cfd7b61dc4e29cd18b8593034bfc556577eb0001b53e8c95146","source":{"kind":"arxiv","id":"2506.20817","version":2},"attestation_state":"computed","paper":{"title":"RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"Ali Tourani, Fatemeh Nazary, Yashar Deldjoo","submitted_at":"2025-06-25T20:32:12Z","abstract_excerpt":"This paper addresses the challenge of building multimodal recommender systems for the movie domain, where sparse item metadata (e.g., title and genres) can limit retrieval quality and downstream recommendations. We introduce RAG-VisualRec, an open resource and reproducible pipeline that combines (i) LLM-generated item-side plot descriptions and (ii) trailer-derived visual (and optional audio) embeddings, supporting both retrieval-augmented generation (RAG) and collaborative-filtering style workflows. Our pipeline augments sparse metadata into richer textual signals and integrates modalities vi"},"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":"2506.20817","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-25T20:32:12Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"d675e4e9425a79d34d8bc37874f6fd1772ade52dd27e9efad5017957536e5427","abstract_canon_sha256":"5f197d23c88c9ffb48480b537bdbbda41f4a6e817c37524c87fa7f991130e402"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:03.458753Z","signature_b64":"ZrlUL7gyKlKNFzqh7c23hGVCKEq2TuK3zxxieBA2S2sqZnrqMAk/yanZA4O5fCZMSRDpgp6DJHjpjtl6Wz4vAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"711b909349546cfd7b61dc4e29cd18b8593034bfc556577eb0001b53e8c95146","last_reissued_at":"2026-07-02T01:18:03.458224Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:03.458224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"Ali Tourani, Fatemeh Nazary, Yashar Deldjoo","submitted_at":"2025-06-25T20:32:12Z","abstract_excerpt":"This paper addresses the challenge of building multimodal recommender systems for the movie domain, where sparse item metadata (e.g., title and genres) can limit retrieval quality and downstream recommendations. We introduce RAG-VisualRec, an open resource and reproducible pipeline that combines (i) LLM-generated item-side plot descriptions and (ii) trailer-derived visual (and optional audio) embeddings, supporting both retrieval-augmented generation (RAG) and collaborative-filtering style workflows. Our pipeline augments sparse metadata into richer textual signals and integrates modalities vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20817","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/2506.20817/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":"2506.20817","created_at":"2026-07-02T01:18:03.458294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20817v2","created_at":"2026-07-02T01:18:03.458294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20817","created_at":"2026-07-02T01:18:03.458294+00:00"},{"alias_kind":"pith_short_12","alias_value":"OENZBE2JKRWP","created_at":"2026-07-02T01:18:03.458294+00:00"},{"alias_kind":"pith_short_16","alias_value":"OENZBE2JKRWP263B","created_at":"2026-07-02T01:18:03.458294+00:00"},{"alias_kind":"pith_short_8","alias_value":"OENZBE2J","created_at":"2026-07-02T01:18:03.458294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.09595","citing_title":"Popcorn: A Configurable Benchmark for Visual Evidence in Multimodal Movie Recommendation","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OENZBE2JKRWP263B3RHCTTIYXB","json":"https://pith.science/pith/OENZBE2JKRWP263B3RHCTTIYXB.json","graph_json":"https://pith.science/api/pith-number/OENZBE2JKRWP263B3RHCTTIYXB/graph.json","events_json":"https://pith.science/api/pith-number/OENZBE2JKRWP263B3RHCTTIYXB/events.json","paper":"https://pith.science/paper/OENZBE2J"},"agent_actions":{"view_html":"https://pith.science/pith/OENZBE2JKRWP263B3RHCTTIYXB","download_json":"https://pith.science/pith/OENZBE2JKRWP263B3RHCTTIYXB.json","view_paper":"https://pith.science/paper/OENZBE2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20817&json=true","fetch_graph":"https://pith.science/api/pith-number/OENZBE2JKRWP263B3RHCTTIYXB/graph.json","fetch_events":"https://pith.science/api/pith-number/OENZBE2JKRWP263B3RHCTTIYXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OENZBE2JKRWP263B3RHCTTIYXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OENZBE2JKRWP263B3RHCTTIYXB/action/storage_attestation","attest_author":"https://pith.science/pith/OENZBE2JKRWP263B3RHCTTIYXB/action/author_attestation","sign_citation":"https://pith.science/pith/OENZBE2JKRWP263B3RHCTTIYXB/action/citation_signature","submit_replication":"https://pith.science/pith/OENZBE2JKRWP263B3RHCTTIYXB/action/replication_record"}},"created_at":"2026-07-02T01:18:03.458294+00:00","updated_at":"2026-07-02T01:18:03.458294+00:00"}