{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UKAGWDAXEQ2E2QXHWQCOIMVH2N","short_pith_number":"pith:UKAGWDAX","schema_version":"1.0","canonical_sha256":"a2806b0c1724344d42e7b404e432a7d351f7e82edb4a3ade75b655ac52e60077","source":{"kind":"arxiv","id":"2511.12449","version":3},"attestation_state":"computed","paper":{"title":"MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Chenghan Fu, Daoze Zhang, Jian Xu, Junxian Wu, Pengjie Wang, Wanxian Guan, Zhanheng Nie","submitted_at":"2025-11-16T04:29:35Z","abstract_excerpt":"Recent Multimodal Large Language Models (MLLMs) have significantly advanced e-commerce product understanding. However, they still face three challenges: (i) the modality imbalance induced by modality mixed training; (ii) underutilization of the intrinsic alignment relationships among visual and textual information within a product; and (iii) limited handling of noise in e-commerce multimodal data. To address these, we propose MOON2.0, a dynamic modality-balanced MultimOdal representation learning framework for e-commerce prOduct uNderstanding. It comprises: (1) a Modality-driven Mixture-of-Exp"},"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":"2511.12449","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-16T04:29:35Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"e67c12a292382a3260cbd776e48d332518f65716d158d0320b61737709aca19a","abstract_canon_sha256":"6fd337fc8022b353f4206c5ac3d562ec2a3aeb6d99423b32ad20dac87fd003be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2806b0c1724344d42e7b404e432a7d351f7e82edb4a3ade75b655ac52e60077","last_reissued_at":"2026-07-31T00:10:10.921204Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:10.921204Z"},"graph_snapshot":{"paper":{"title":"MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Chenghan Fu, Daoze Zhang, Jian Xu, Junxian Wu, Pengjie Wang, Wanxian Guan, Zhanheng Nie","submitted_at":"2025-11-16T04:29:35Z","abstract_excerpt":"Recent Multimodal Large Language Models (MLLMs) have significantly advanced e-commerce product understanding. However, they still face three challenges: (i) the modality imbalance induced by modality mixed training; (ii) underutilization of the intrinsic alignment relationships among visual and textual information within a product; and (iii) limited handling of noise in e-commerce multimodal data. To address these, we propose MOON2.0, a dynamic modality-balanced MultimOdal representation learning framework for e-commerce prOduct uNderstanding. It comprises: (1) a Modality-driven Mixture-of-Exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.12449","kind":"arxiv","version":3},"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/2511.12449/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":"2511.12449","created_at":"2026-07-31T00:10:10.923492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.12449v3","created_at":"2026-07-31T00:10:10.923492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.12449","created_at":"2026-07-31T00:10:10.923492+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKAGWDAXEQ2E","created_at":"2026-07-31T00:10:10.923492+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKAGWDAXEQ2E2QXH","created_at":"2026-07-31T00:10:10.923492+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKAGWDAX","created_at":"2026-07-31T00:10:10.923492+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKAGWDAXEQ2E2QXHWQCOIMVH2N","json":"https://pith.science/pith/UKAGWDAXEQ2E2QXHWQCOIMVH2N.json","graph_json":"https://pith.science/api/pith-number/UKAGWDAXEQ2E2QXHWQCOIMVH2N/graph.json","events_json":"https://pith.science/api/pith-number/UKAGWDAXEQ2E2QXHWQCOIMVH2N/events.json","paper":"https://pith.science/paper/UKAGWDAX"},"agent_actions":{"view_html":"https://pith.science/pith/UKAGWDAXEQ2E2QXHWQCOIMVH2N","download_json":"https://pith.science/pith/UKAGWDAXEQ2E2QXHWQCOIMVH2N.json","view_paper":"https://pith.science/paper/UKAGWDAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.12449&json=true","fetch_graph":"https://pith.science/api/pith-number/UKAGWDAXEQ2E2QXHWQCOIMVH2N/graph.json","fetch_events":"https://pith.science/api/pith-number/UKAGWDAXEQ2E2QXHWQCOIMVH2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKAGWDAXEQ2E2QXHWQCOIMVH2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKAGWDAXEQ2E2QXHWQCOIMVH2N/action/storage_attestation","attest_author":"https://pith.science/pith/UKAGWDAXEQ2E2QXHWQCOIMVH2N/action/author_attestation","sign_citation":"https://pith.science/pith/UKAGWDAXEQ2E2QXHWQCOIMVH2N/action/citation_signature","submit_replication":"https://pith.science/pith/UKAGWDAXEQ2E2QXHWQCOIMVH2N/action/replication_record"}},"created_at":"2026-07-31T00:10:10.923492+00:00","updated_at":"2026-07-31T00:10:10.923492+00:00"}