{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7VYKSJPZH77YRWARQPFVJGAVX4","short_pith_number":"pith:7VYKSJPZ","canonical_record":{"source":{"id":"2405.16789","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T03:24:01Z","cross_cats_sorted":[],"title_canon_sha256":"d549e20ff51f2287b242de4d8c3a4cfa66bb710bee7fb49a763ae64386c9da24","abstract_canon_sha256":"148e7cf0f8a21086883125d5eef82a3f8f65ce2056723774891ff4eda4bc9449"},"schema_version":"1.0"},"canonical_sha256":"fd70a925f93fff88d81183cb549815bf2214493cdec5e401289a95a30c5c09c5","source":{"kind":"arxiv","id":"2405.16789","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16789","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16789v2","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16789","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"7VYKSJPZH77Y","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"7VYKSJPZH77YRWAR","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"7VYKSJPZ","created_at":"2026-07-05T10:03:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7VYKSJPZH77YRWARQPFVJGAVX4","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16789","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T03:24:01Z","cross_cats_sorted":[],"title_canon_sha256":"d549e20ff51f2287b242de4d8c3a4cfa66bb710bee7fb49a763ae64386c9da24","abstract_canon_sha256":"148e7cf0f8a21086883125d5eef82a3f8f65ce2056723774891ff4eda4bc9449"},"schema_version":"1.0"},"canonical_sha256":"fd70a925f93fff88d81183cb549815bf2214493cdec5e401289a95a30c5c09c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:25.465541Z","signature_b64":"UZyc2IXiH4bvLnLGXNS55qimvJeypzafsjHAZbn8UHHZumm5yqwpZ8kn1t2SY0E3XbBKNHdyQArFxpzHWPggDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd70a925f93fff88d81183cb549815bf2214493cdec5e401289a95a30c5c09c5","last_reissued_at":"2026-07-05T10:03:25.465069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:25.465069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16789","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":"2026-07-05T10:03:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOYqmwLzXqyc3BeH3hRAt8/6uEZtjrVUfs0moJiLKsHlIbFXsuZevammf0k5jBM+0z++9KXtWpTcT68lN6VCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:25:01.723153Z"},"content_sha256":"ffce0cca501733cd42eba958d4d0f473187d1e8bacf38670191d115e036b647c","schema_version":"1.0","event_id":"sha256:ffce0cca501733cd42eba958d4d0f473187d1e8bacf38670191d115e036b647c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7VYKSJPZH77YRWARQPFVJGAVX4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NoteLLM-2: Multimodal Large Representation Models for Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chao Zhang, Di Wu, Enhong Chen, Haoxin Zhang, Shiwei Wu, Tong Xu, Xiangyu Zhao, Yan Gao, Yao Hu","submitted_at":"2024-05-27T03:24:01Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains underexplored. While leveraging existing Multimodal Large Language Models (MLLMs) for such tasks is promising, challenges arise due to their delayed release compared to corresponding LLMs and the inefficiency in representation tasks. To address these issues, we propose an end-to-end fine-tuning method that customizes the integration of any existing LLMs and vision enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16789","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/2405.16789/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":"2026-07-05T10:03:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ln17Y4E+VSPxfWBGywjy4JSaJjUrs9GNtDDkR3bA+IfPbPNeyxfnKHfqBMOBmi9okn6NKH6EaYa53pzKS0QeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:25:01.723636Z"},"content_sha256":"93a27d3b9e330af4905e06b3176c87470698631e0a2394a1c3fcd0b74e90499e","schema_version":"1.0","event_id":"sha256:93a27d3b9e330af4905e06b3176c87470698631e0a2394a1c3fcd0b74e90499e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7VYKSJPZH77YRWARQPFVJGAVX4/bundle.json","state_url":"https://pith.science/pith/7VYKSJPZH77YRWARQPFVJGAVX4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7VYKSJPZH77YRWARQPFVJGAVX4/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":"2026-08-14T08:25:01Z","links":{"resolver":"https://pith.science/pith/7VYKSJPZH77YRWARQPFVJGAVX4","bundle":"https://pith.science/pith/7VYKSJPZH77YRWARQPFVJGAVX4/bundle.json","state":"https://pith.science/pith/7VYKSJPZH77YRWARQPFVJGAVX4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7VYKSJPZH77YRWARQPFVJGAVX4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7VYKSJPZH77YRWARQPFVJGAVX4","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":"148e7cf0f8a21086883125d5eef82a3f8f65ce2056723774891ff4eda4bc9449","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T03:24:01Z","title_canon_sha256":"d549e20ff51f2287b242de4d8c3a4cfa66bb710bee7fb49a763ae64386c9da24"},"schema_version":"1.0","source":{"id":"2405.16789","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16789","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16789v2","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16789","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"7VYKSJPZH77Y","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"7VYKSJPZH77YRWAR","created_at":"2026-07-05T10:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"7VYKSJPZ","created_at":"2026-07-05T10:03:25Z"}],"graph_snapshots":[{"event_id":"sha256:93a27d3b9e330af4905e06b3176c87470698631e0a2394a1c3fcd0b74e90499e","target":"graph","created_at":"2026-07-05T10:03:25Z","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/2405.16789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains underexplored. While leveraging existing Multimodal Large Language Models (MLLMs) for such tasks is promising, challenges arise due to their delayed release compared to corresponding LLMs and the inefficiency in representation tasks. To address these issues, we propose an end-to-end fine-tuning method that customizes the integration of any existing LLMs and vision enc","authors_text":"Chao Zhang, Di Wu, Enhong Chen, Haoxin Zhang, Shiwei Wu, Tong Xu, Xiangyu Zhao, Yan Gao, Yao Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T03:24:01Z","title":"NoteLLM-2: Multimodal Large Representation Models for Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16789","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:ffce0cca501733cd42eba958d4d0f473187d1e8bacf38670191d115e036b647c","target":"record","created_at":"2026-07-05T10:03:25Z","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":"148e7cf0f8a21086883125d5eef82a3f8f65ce2056723774891ff4eda4bc9449","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T03:24:01Z","title_canon_sha256":"d549e20ff51f2287b242de4d8c3a4cfa66bb710bee7fb49a763ae64386c9da24"},"schema_version":"1.0","source":{"id":"2405.16789","kind":"arxiv","version":2}},"canonical_sha256":"fd70a925f93fff88d81183cb549815bf2214493cdec5e401289a95a30c5c09c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd70a925f93fff88d81183cb549815bf2214493cdec5e401289a95a30c5c09c5","first_computed_at":"2026-07-05T10:03:25.465069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:25.465069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UZyc2IXiH4bvLnLGXNS55qimvJeypzafsjHAZbn8UHHZumm5yqwpZ8kn1t2SY0E3XbBKNHdyQArFxpzHWPggDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:25.465541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16789","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffce0cca501733cd42eba958d4d0f473187d1e8bacf38670191d115e036b647c","sha256:93a27d3b9e330af4905e06b3176c87470698631e0a2394a1c3fcd0b74e90499e"],"state_sha256":"b99dab00b5f275e4b45a80818dc64967423e150e9b5814bccc4bacb9bbe4c7f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tvt1+Rs+yUM2yU7y4+kit6g0B2cb/ga1nt83WAxsQ0Yvo/w9lqs9GXq/YgmS07LdcYeH+TMjU/svaQviU9ztDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:25:01.727955Z","bundle_sha256":"e04148ce319e8715282472dac7d9df0d35a21eee4f8ba2bd0a3668bff8889e49"}}