{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BYHYKNPCNOIA65WQ6JBG4ILT2H","short_pith_number":"pith:BYHYKNPC","schema_version":"1.0","canonical_sha256":"0e0f8535e26b900f76d0f2426e2173d1d0e8dc64292298889fefb00e35c7d1ef","source":{"kind":"arxiv","id":"2508.09789","version":1},"attestation_state":"computed","paper":{"title":"Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Andreas Damianou, Marco De Nadai, Mounia Lalmas","submitted_at":"2025-08-13T13:19:31Z","abstract_excerpt":"Existing video recommender systems rely primarily on user-defined metadata or on low-level visual and acoustic signals extracted by specialised encoders. These low-level features describe what appears on the screen but miss deeper semantics such as intent, humour, and world knowledge that make clips resonate with viewers. For example, is a 30-second clip simply a singer on a rooftop, or an ironic parody filmed amid the fairy chimneys of Cappadocia, Turkey? Such distinctions are critical to personalised recommendations yet remain invisible to traditional encoding pipelines. In this paper, we in"},"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":"2508.09789","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-13T13:19:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ca3e155e03be5f2ab51e3672e82ddbb3bfd5145d51e01804c18ce8a62a31b562","abstract_canon_sha256":"ae5fcba39702386228f636e342042edda0b73e15b5812d8645f5bc82306beff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:21.877257Z","signature_b64":"QZ6PPBVSBp8T2yPMJvXzhf0Rt7yDfpp34+15CRKrCu3bOwjWUIyfFrX0lyYP4JI+y4Cqd4+aS7taRxb85ZyjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e0f8535e26b900f76d0f2426e2173d1d0e8dc64292298889fefb00e35c7d1ef","last_reissued_at":"2026-07-05T11:53:21.876683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:21.876683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Andreas Damianou, Marco De Nadai, Mounia Lalmas","submitted_at":"2025-08-13T13:19:31Z","abstract_excerpt":"Existing video recommender systems rely primarily on user-defined metadata or on low-level visual and acoustic signals extracted by specialised encoders. These low-level features describe what appears on the screen but miss deeper semantics such as intent, humour, and world knowledge that make clips resonate with viewers. For example, is a 30-second clip simply a singer on a rooftop, or an ironic parody filmed amid the fairy chimneys of Cappadocia, Turkey? Such distinctions are critical to personalised recommendations yet remain invisible to traditional encoding pipelines. In this paper, we in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09789","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/2508.09789/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":"2508.09789","created_at":"2026-07-05T11:53:21.876745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09789v1","created_at":"2026-07-05T11:53:21.876745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09789","created_at":"2026-07-05T11:53:21.876745+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYHYKNPCNOIA","created_at":"2026-07-05T11:53:21.876745+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYHYKNPCNOIA65WQ","created_at":"2026-07-05T11:53:21.876745+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYHYKNPC","created_at":"2026-07-05T11:53:21.876745+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/BYHYKNPCNOIA65WQ6JBG4ILT2H","json":"https://pith.science/pith/BYHYKNPCNOIA65WQ6JBG4ILT2H.json","graph_json":"https://pith.science/api/pith-number/BYHYKNPCNOIA65WQ6JBG4ILT2H/graph.json","events_json":"https://pith.science/api/pith-number/BYHYKNPCNOIA65WQ6JBG4ILT2H/events.json","paper":"https://pith.science/paper/BYHYKNPC"},"agent_actions":{"view_html":"https://pith.science/pith/BYHYKNPCNOIA65WQ6JBG4ILT2H","download_json":"https://pith.science/pith/BYHYKNPCNOIA65WQ6JBG4ILT2H.json","view_paper":"https://pith.science/paper/BYHYKNPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09789&json=true","fetch_graph":"https://pith.science/api/pith-number/BYHYKNPCNOIA65WQ6JBG4ILT2H/graph.json","fetch_events":"https://pith.science/api/pith-number/BYHYKNPCNOIA65WQ6JBG4ILT2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYHYKNPCNOIA65WQ6JBG4ILT2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYHYKNPCNOIA65WQ6JBG4ILT2H/action/storage_attestation","attest_author":"https://pith.science/pith/BYHYKNPCNOIA65WQ6JBG4ILT2H/action/author_attestation","sign_citation":"https://pith.science/pith/BYHYKNPCNOIA65WQ6JBG4ILT2H/action/citation_signature","submit_replication":"https://pith.science/pith/BYHYKNPCNOIA65WQ6JBG4ILT2H/action/replication_record"}},"created_at":"2026-07-05T11:53:21.876745+00:00","updated_at":"2026-07-05T11:53:21.876745+00:00"}