{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AJCMVQ4YLUB656LAMVL3IDIZ6S","short_pith_number":"pith:AJCMVQ4Y","schema_version":"1.0","canonical_sha256":"0244cac3985d03eef9606557b40d19f4a7663a14c6304877125235a875c4ee15","source":{"kind":"arxiv","id":"2404.00621","version":2},"attestation_state":"computed","paper":{"title":"Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"Jieming Zhu, Qijiong Liu, Quanyu Dai, Rui Zhang, Xiao-Ming Wu, Yanting Yang, Zhaocheng Du, Zhenhua Dong, Zhou Zhao","submitted_at":"2024-03-31T09:20:30Z","abstract_excerpt":"Personalized recommendation serves as a ubiquitous channel for users to discover information tailored to their interests. However, traditional recommendation models primarily rely on unique IDs and categorical features for user-item matching, potentially overlooking the nuanced essence of raw item contents across multiple modalities such as text, image, audio, and video. This underutilization of multimodal data poses a limitation to recommender systems, especially in multimedia services like news, music, and short-video platforms. The recent advancements in large multimodal models offer new op"},"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":"2404.00621","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-03-31T09:20:30Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"3f72644cf3c0ffdf05a48e29514c97c7198946d07d97c0f3c922cbbc07eacf70","abstract_canon_sha256":"545b55a3ed9a844fa7417166c5b487c853299e898f985b15b0ec824abefbd1e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:33.180099Z","signature_b64":"ybcT0q2FN0kHaOdFo/NSft+0KGXM+RGpV2uFFhufxH/wxKCrqmq1akwuOtjChoHSLJBrZN0DVG6hI5Ys0hBZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0244cac3985d03eef9606557b40d19f4a7663a14c6304877125235a875c4ee15","last_reissued_at":"2026-07-05T08:39:33.179592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:33.179592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"Jieming Zhu, Qijiong Liu, Quanyu Dai, Rui Zhang, Xiao-Ming Wu, Yanting Yang, Zhaocheng Du, Zhenhua Dong, Zhou Zhao","submitted_at":"2024-03-31T09:20:30Z","abstract_excerpt":"Personalized recommendation serves as a ubiquitous channel for users to discover information tailored to their interests. However, traditional recommendation models primarily rely on unique IDs and categorical features for user-item matching, potentially overlooking the nuanced essence of raw item contents across multiple modalities such as text, image, audio, and video. This underutilization of multimodal data poses a limitation to recommender systems, especially in multimedia services like news, music, and short-video platforms. The recent advancements in large multimodal models offer new op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00621","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/2404.00621/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":"2404.00621","created_at":"2026-07-05T08:39:33.179654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00621v2","created_at":"2026-07-05T08:39:33.179654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00621","created_at":"2026-07-05T08:39:33.179654+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJCMVQ4YLUB6","created_at":"2026-07-05T08:39:33.179654+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJCMVQ4YLUB656LA","created_at":"2026-07-05T08:39:33.179654+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJCMVQ4Y","created_at":"2026-07-05T08:39:33.179654+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/AJCMVQ4YLUB656LAMVL3IDIZ6S","json":"https://pith.science/pith/AJCMVQ4YLUB656LAMVL3IDIZ6S.json","graph_json":"https://pith.science/api/pith-number/AJCMVQ4YLUB656LAMVL3IDIZ6S/graph.json","events_json":"https://pith.science/api/pith-number/AJCMVQ4YLUB656LAMVL3IDIZ6S/events.json","paper":"https://pith.science/paper/AJCMVQ4Y"},"agent_actions":{"view_html":"https://pith.science/pith/AJCMVQ4YLUB656LAMVL3IDIZ6S","download_json":"https://pith.science/pith/AJCMVQ4YLUB656LAMVL3IDIZ6S.json","view_paper":"https://pith.science/paper/AJCMVQ4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00621&json=true","fetch_graph":"https://pith.science/api/pith-number/AJCMVQ4YLUB656LAMVL3IDIZ6S/graph.json","fetch_events":"https://pith.science/api/pith-number/AJCMVQ4YLUB656LAMVL3IDIZ6S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJCMVQ4YLUB656LAMVL3IDIZ6S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJCMVQ4YLUB656LAMVL3IDIZ6S/action/storage_attestation","attest_author":"https://pith.science/pith/AJCMVQ4YLUB656LAMVL3IDIZ6S/action/author_attestation","sign_citation":"https://pith.science/pith/AJCMVQ4YLUB656LAMVL3IDIZ6S/action/citation_signature","submit_replication":"https://pith.science/pith/AJCMVQ4YLUB656LAMVL3IDIZ6S/action/replication_record"}},"created_at":"2026-07-05T08:39:33.179654+00:00","updated_at":"2026-07-05T08:39:33.179654+00:00"}