{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q3ZQHCI4KFNXF2DIOZDDVOPPKT","short_pith_number":"pith:Q3ZQHCI4","schema_version":"1.0","canonical_sha256":"86f303891c515b72e86876463ab9ef54f9b4835b357ce2eba6c49aa05673389d","source":{"kind":"arxiv","id":"2202.07247","version":1},"attestation_state":"computed","paper":{"title":"CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SI"],"primary_cat":"cs.CV","authors_text":"Animesh Sinha, Hugo Chen, Jun Chen, Licheng Yu, Mengjiao MJ Wang, Ning Zhang, Tamara L. Berg","submitted_at":"2022-02-15T08:23:59Z","abstract_excerpt":"We introduce CommerceMM - a multimodal model capable of providing a diverse and granular understanding of commerce topics associated to the given piece of content (image, text, image+text), and having the capability to generalize to a wide range of tasks, including Multimodal Categorization, Image-Text Retrieval, Query-to-Product Retrieval, Image-to-Product Retrieval, etc. We follow the pre-training + fine-tuning training regime and present 5 effective pre-training tasks on image-text pairs. To embrace more common and diverse commerce data with text-to-multimodal, image-to-multimodal, and mult"},"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":"2202.07247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-15T08:23:59Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SI"],"title_canon_sha256":"7fe858723fe735738df462d3dfff6164e950461d63846ff7a49a4b29d2f14854","abstract_canon_sha256":"eae711a902e73341738a6ac9eb06708e8a432df3162108743e47e9437ce01a76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:58.112651Z","signature_b64":"LC3MaOUAAqZop6XkBDrqK7Np9WSyW5EpNsAEiaF9fzhe4zbQJEDybx1OOZZ5Ukd3IOfy3EpWNWjyTY+zNmTnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86f303891c515b72e86876463ab9ef54f9b4835b357ce2eba6c49aa05673389d","last_reissued_at":"2026-07-05T03:56:58.112200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:58.112200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SI"],"primary_cat":"cs.CV","authors_text":"Animesh Sinha, Hugo Chen, Jun Chen, Licheng Yu, Mengjiao MJ Wang, Ning Zhang, Tamara L. Berg","submitted_at":"2022-02-15T08:23:59Z","abstract_excerpt":"We introduce CommerceMM - a multimodal model capable of providing a diverse and granular understanding of commerce topics associated to the given piece of content (image, text, image+text), and having the capability to generalize to a wide range of tasks, including Multimodal Categorization, Image-Text Retrieval, Query-to-Product Retrieval, Image-to-Product Retrieval, etc. We follow the pre-training + fine-tuning training regime and present 5 effective pre-training tasks on image-text pairs. To embrace more common and diverse commerce data with text-to-multimodal, image-to-multimodal, and mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07247","kind":"arxiv","version":1},"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/2202.07247/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":"2202.07247","created_at":"2026-07-05T03:56:58.112278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07247v1","created_at":"2026-07-05T03:56:58.112278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07247","created_at":"2026-07-05T03:56:58.112278+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3ZQHCI4KFNX","created_at":"2026-07-05T03:56:58.112278+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3ZQHCI4KFNXF2DI","created_at":"2026-07-05T03:56:58.112278+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3ZQHCI4","created_at":"2026-07-05T03:56:58.112278+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/Q3ZQHCI4KFNXF2DIOZDDVOPPKT","json":"https://pith.science/pith/Q3ZQHCI4KFNXF2DIOZDDVOPPKT.json","graph_json":"https://pith.science/api/pith-number/Q3ZQHCI4KFNXF2DIOZDDVOPPKT/graph.json","events_json":"https://pith.science/api/pith-number/Q3ZQHCI4KFNXF2DIOZDDVOPPKT/events.json","paper":"https://pith.science/paper/Q3ZQHCI4"},"agent_actions":{"view_html":"https://pith.science/pith/Q3ZQHCI4KFNXF2DIOZDDVOPPKT","download_json":"https://pith.science/pith/Q3ZQHCI4KFNXF2DIOZDDVOPPKT.json","view_paper":"https://pith.science/paper/Q3ZQHCI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07247&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3ZQHCI4KFNXF2DIOZDDVOPPKT/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3ZQHCI4KFNXF2DIOZDDVOPPKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3ZQHCI4KFNXF2DIOZDDVOPPKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3ZQHCI4KFNXF2DIOZDDVOPPKT/action/storage_attestation","attest_author":"https://pith.science/pith/Q3ZQHCI4KFNXF2DIOZDDVOPPKT/action/author_attestation","sign_citation":"https://pith.science/pith/Q3ZQHCI4KFNXF2DIOZDDVOPPKT/action/citation_signature","submit_replication":"https://pith.science/pith/Q3ZQHCI4KFNXF2DIOZDDVOPPKT/action/replication_record"}},"created_at":"2026-07-05T03:56:58.112278+00:00","updated_at":"2026-07-05T03:56:58.112278+00:00"}