{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B4JTIBYHQH6AYHSNO4GVIUSRVB","short_pith_number":"pith:B4JTIBYH","schema_version":"1.0","canonical_sha256":"0f1334070781fc0c1e4d770d545251a86958aaadcf2bd0e1b46f7a7dc8030ad5","source":{"kind":"arxiv","id":"2602.00682","version":2},"attestation_state":"computed","paper":{"title":"RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chi Lu, Hengwei Ju, Kun Gai, Peng Jiang, Wei Yang, Yuecheng Li, Zeyu Song","submitted_at":"2026-01-31T11:58:38Z","abstract_excerpt":"Integrating large language model (LLM) representations into multimodal recommendation has shown promise, yet a fundamental challenge remains largely overlooked: the semantic heterogeneity between generative LM representations and the ID-based collaborative signals that recommendation systems rely on. Naively injecting LM features without alignment degrades recommendation performance rather than improving it. To resolve this, we propose RecGOAT, a dual-granularity semantic alignment framework built on graph neural networks and optimal transport theory. RecGOAT first enriches collaborative seman"},"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":"2602.00682","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-01-31T11:58:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2aea5cb45b3776b5ddb38ddfabfa2b806610438909c2356bd708cd6bd0b12bdd","abstract_canon_sha256":"37b193e3f2040f4f0c5fd9feebe5752b0dc092ac49d380a310b6d34b36acc698"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:06.241920Z","signature_b64":"MCXngkkGnUnx2Vo92MxfV0/FwVpO3IigV64gSpYmWFqO708gxgDNQusSj4AL7NUH2djEqMJuUTaOI+sGB02eCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f1334070781fc0c1e4d770d545251a86958aaadcf2bd0e1b46f7a7dc8030ad5","last_reissued_at":"2026-05-26T02:05:06.241159Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:06.241159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chi Lu, Hengwei Ju, Kun Gai, Peng Jiang, Wei Yang, Yuecheng Li, Zeyu Song","submitted_at":"2026-01-31T11:58:38Z","abstract_excerpt":"Integrating large language model (LLM) representations into multimodal recommendation has shown promise, yet a fundamental challenge remains largely overlooked: the semantic heterogeneity between generative LM representations and the ID-based collaborative signals that recommendation systems rely on. Naively injecting LM features without alignment degrades recommendation performance rather than improving it. To resolve this, we propose RecGOAT, a dual-granularity semantic alignment framework built on graph neural networks and optimal transport theory. RecGOAT first enriches collaborative seman"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00682","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/2602.00682/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":"2602.00682","created_at":"2026-05-26T02:05:06.241301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.00682v2","created_at":"2026-05-26T02:05:06.241301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00682","created_at":"2026-05-26T02:05:06.241301+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4JTIBYHQH6A","created_at":"2026-05-26T02:05:06.241301+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4JTIBYHQH6AYHSN","created_at":"2026-05-26T02:05:06.241301+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4JTIBYH","created_at":"2026-05-26T02:05:06.241301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.22073","citing_title":"Behavior-Guided Candidate Calibration for Multimodal Recommendation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26247","citing_title":"TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4JTIBYHQH6AYHSNO4GVIUSRVB","json":"https://pith.science/pith/B4JTIBYHQH6AYHSNO4GVIUSRVB.json","graph_json":"https://pith.science/api/pith-number/B4JTIBYHQH6AYHSNO4GVIUSRVB/graph.json","events_json":"https://pith.science/api/pith-number/B4JTIBYHQH6AYHSNO4GVIUSRVB/events.json","paper":"https://pith.science/paper/B4JTIBYH"},"agent_actions":{"view_html":"https://pith.science/pith/B4JTIBYHQH6AYHSNO4GVIUSRVB","download_json":"https://pith.science/pith/B4JTIBYHQH6AYHSNO4GVIUSRVB.json","view_paper":"https://pith.science/paper/B4JTIBYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.00682&json=true","fetch_graph":"https://pith.science/api/pith-number/B4JTIBYHQH6AYHSNO4GVIUSRVB/graph.json","fetch_events":"https://pith.science/api/pith-number/B4JTIBYHQH6AYHSNO4GVIUSRVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4JTIBYHQH6AYHSNO4GVIUSRVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4JTIBYHQH6AYHSNO4GVIUSRVB/action/storage_attestation","attest_author":"https://pith.science/pith/B4JTIBYHQH6AYHSNO4GVIUSRVB/action/author_attestation","sign_citation":"https://pith.science/pith/B4JTIBYHQH6AYHSNO4GVIUSRVB/action/citation_signature","submit_replication":"https://pith.science/pith/B4JTIBYHQH6AYHSNO4GVIUSRVB/action/replication_record"}},"created_at":"2026-05-26T02:05:06.241301+00:00","updated_at":"2026-05-26T02:05:06.241301+00:00"}