{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3NSNGH5NDGVKBBVWHYPLCYFJZQ","short_pith_number":"pith:3NSNGH5N","canonical_record":{"source":{"id":"2305.14302","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T17:43:46Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"title_canon_sha256":"82467a35327a09f48cb26d721acf8af473bea17c2c0daef152ae78ff32be019b","abstract_canon_sha256":"c857233d96e5825799ef1bb76970c07c3dc75398206cd0aec60e377a96b511f6"},"schema_version":"1.0"},"canonical_sha256":"db64d31fad19aaa086b63e1eb160a9cc3775be68563da5e311fdf821fc6f3f34","source":{"kind":"arxiv","id":"2305.14302","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14302","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14302v2","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14302","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"3NSNGH5NDGVK","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"3NSNGH5NDGVKBBVW","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"3NSNGH5N","created_at":"2026-07-05T07:01:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3NSNGH5NDGVKBBVWHYPLCYFJZQ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14302","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T17:43:46Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"title_canon_sha256":"82467a35327a09f48cb26d721acf8af473bea17c2c0daef152ae78ff32be019b","abstract_canon_sha256":"c857233d96e5825799ef1bb76970c07c3dc75398206cd0aec60e377a96b511f6"},"schema_version":"1.0"},"canonical_sha256":"db64d31fad19aaa086b63e1eb160a9cc3775be68563da5e311fdf821fc6f3f34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:01.716072Z","signature_b64":"yGax2vWRje4n7cN2tQ3FW9jMQCkcTvHyM5FROKaqmoz1XVs3UfTggzegEWP28EE9pse8bNDhWhC5YkPqUxE8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db64d31fad19aaa086b63e1eb160a9cc3775be68563da5e311fdf821fc6f3f34","last_reissued_at":"2026-07-05T07:01:01.715594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:01.715594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14302","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"actzdro3NOyeUeVQ1Jij/9B/ugRt7bzDmSHz/MyZ/h3X2/9YJPIqE205g6sKKEDZhkIErg7n+zuw54vwTlVyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:49:18.466544Z"},"content_sha256":"ae6a5b7f10bf4f539b52661d4ac67508f102c3fe3e1dba50f25d5675be06f045","schema_version":"1.0","event_id":"sha256:ae6a5b7f10bf4f539b52661d4ac67508f102c3fe3e1dba50f25d5675be06f045"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3NSNGH5NDGVKBBVWHYPLCYFJZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VIP5: Towards Multimodal Foundation Models for Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"Juntao Tan, Shijie Geng, Shuchang Liu, Yongfeng Zhang, Zuohui Fu","submitted_at":"2023-05-23T17:43:46Z","abstract_excerpt":"Computer Vision (CV), Natural Language Processing (NLP), and Recommender Systems (RecSys) are three prominent AI applications that have traditionally developed independently, resulting in disparate modeling and engineering methodologies. This has impeded the ability for these fields to directly benefit from each other's advancements. With the recent development of foundation models, large language models have emerged as a potential general-purpose interface for unifying different modalities and problem formulations. In light of this, we propose the development of a multimodal foundation model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14302","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/2305.14302/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4kIQckECVrcMWhEg2UsEThdIzgXPTX3jLsiAjej+1O1Gu1gtox/OaPKhUQW9QCvCCu4MkxVVCI1Ozrkfb6X/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:49:18.467053Z"},"content_sha256":"4c987e75bc347fc30e0b4fc7af5c2e5e94c2871f0c214cbb8f5a0972219a9591","schema_version":"1.0","event_id":"sha256:4c987e75bc347fc30e0b4fc7af5c2e5e94c2871f0c214cbb8f5a0972219a9591"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3NSNGH5NDGVKBBVWHYPLCYFJZQ/bundle.json","state_url":"https://pith.science/pith/3NSNGH5NDGVKBBVWHYPLCYFJZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3NSNGH5NDGVKBBVWHYPLCYFJZQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T06:49:18Z","links":{"resolver":"https://pith.science/pith/3NSNGH5NDGVKBBVWHYPLCYFJZQ","bundle":"https://pith.science/pith/3NSNGH5NDGVKBBVWHYPLCYFJZQ/bundle.json","state":"https://pith.science/pith/3NSNGH5NDGVKBBVWHYPLCYFJZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3NSNGH5NDGVKBBVWHYPLCYFJZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3NSNGH5NDGVKBBVWHYPLCYFJZQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c857233d96e5825799ef1bb76970c07c3dc75398206cd0aec60e377a96b511f6","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T17:43:46Z","title_canon_sha256":"82467a35327a09f48cb26d721acf8af473bea17c2c0daef152ae78ff32be019b"},"schema_version":"1.0","source":{"id":"2305.14302","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14302","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14302v2","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14302","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"3NSNGH5NDGVK","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"3NSNGH5NDGVKBBVW","created_at":"2026-07-05T07:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"3NSNGH5N","created_at":"2026-07-05T07:01:01Z"}],"graph_snapshots":[{"event_id":"sha256:4c987e75bc347fc30e0b4fc7af5c2e5e94c2871f0c214cbb8f5a0972219a9591","target":"graph","created_at":"2026-07-05T07:01:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.14302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computer Vision (CV), Natural Language Processing (NLP), and Recommender Systems (RecSys) are three prominent AI applications that have traditionally developed independently, resulting in disparate modeling and engineering methodologies. This has impeded the ability for these fields to directly benefit from each other's advancements. With the recent development of foundation models, large language models have emerged as a potential general-purpose interface for unifying different modalities and problem formulations. In light of this, we propose the development of a multimodal foundation model ","authors_text":"Juntao Tan, Shijie Geng, Shuchang Liu, Yongfeng Zhang, Zuohui Fu","cross_cats":["cs.AI","cs.HC","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T17:43:46Z","title":"VIP5: Towards Multimodal Foundation Models for Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14302","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ae6a5b7f10bf4f539b52661d4ac67508f102c3fe3e1dba50f25d5675be06f045","target":"record","created_at":"2026-07-05T07:01:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c857233d96e5825799ef1bb76970c07c3dc75398206cd0aec60e377a96b511f6","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T17:43:46Z","title_canon_sha256":"82467a35327a09f48cb26d721acf8af473bea17c2c0daef152ae78ff32be019b"},"schema_version":"1.0","source":{"id":"2305.14302","kind":"arxiv","version":2}},"canonical_sha256":"db64d31fad19aaa086b63e1eb160a9cc3775be68563da5e311fdf821fc6f3f34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db64d31fad19aaa086b63e1eb160a9cc3775be68563da5e311fdf821fc6f3f34","first_computed_at":"2026-07-05T07:01:01.715594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:01.715594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yGax2vWRje4n7cN2tQ3FW9jMQCkcTvHyM5FROKaqmoz1XVs3UfTggzegEWP28EE9pse8bNDhWhC5YkPqUxE8Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:01.716072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14302","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae6a5b7f10bf4f539b52661d4ac67508f102c3fe3e1dba50f25d5675be06f045","sha256:4c987e75bc347fc30e0b4fc7af5c2e5e94c2871f0c214cbb8f5a0972219a9591"],"state_sha256":"baa3a356c0f4c03f67441ef9b97c963a6c05dace17fe16be045b3a4d41a4b9a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k++VOrcOt5EgyTvxa50KD2otRkkgUYI4PJrnsNlyAw4N560cTTvNoAgHkZZupdNhGqaOJlHmyd+lwaroFH+bDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:49:18.471492Z","bundle_sha256":"9b2a2fc9ec8cb1f4c4c21b716efcba55bda3773c97184b09f9f7e286b25d62ee"}}