{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Q3ZQHCI4KFNXF2DIOZDDVOPPKT","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":"eae711a902e73341738a6ac9eb06708e8a432df3162108743e47e9437ce01a76","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-15T08:23:59Z","title_canon_sha256":"7fe858723fe735738df462d3dfff6164e950461d63846ff7a49a4b29d2f14854"},"schema_version":"1.0","source":{"id":"2202.07247","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.07247","created_at":"2026-07-05T03:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2202.07247v1","created_at":"2026-07-05T03:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07247","created_at":"2026-07-05T03:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"Q3ZQHCI4KFNX","created_at":"2026-07-05T03:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"Q3ZQHCI4KFNXF2DI","created_at":"2026-07-05T03:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"Q3ZQHCI4","created_at":"2026-07-05T03:56:58Z"}],"graph_snapshots":[{"event_id":"sha256:310008e5ecf4df39f605cdfc812a3587e86adccd36bc13bece98daaf29fb7e79","target":"graph","created_at":"2026-07-05T03:56:58Z","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/2202.07247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Animesh Sinha, Hugo Chen, Jun Chen, Licheng Yu, Mengjiao MJ Wang, Ning Zhang, Tamara L. Berg","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-15T08:23:59Z","title":"CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07247","kind":"arxiv","version":1},"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":"sha256:818896090e137c82434185f5646d1574485e89418852061aac048df1b34146fc","target":"record","created_at":"2026-07-05T03:56:58Z","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":"eae711a902e73341738a6ac9eb06708e8a432df3162108743e47e9437ce01a76","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-15T08:23:59Z","title_canon_sha256":"7fe858723fe735738df462d3dfff6164e950461d63846ff7a49a4b29d2f14854"},"schema_version":"1.0","source":{"id":"2202.07247","kind":"arxiv","version":1}},"canonical_sha256":"86f303891c515b72e86876463ab9ef54f9b4835b357ce2eba6c49aa05673389d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86f303891c515b72e86876463ab9ef54f9b4835b357ce2eba6c49aa05673389d","first_computed_at":"2026-07-05T03:56:58.112200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:58.112200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LC3MaOUAAqZop6XkBDrqK7Np9WSyW5EpNsAEiaF9fzhe4zbQJEDybx1OOZZ5Ukd3IOfy3EpWNWjyTY+zNmTnCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:58.112651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.07247","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:818896090e137c82434185f5646d1574485e89418852061aac048df1b34146fc","sha256:310008e5ecf4df39f605cdfc812a3587e86adccd36bc13bece98daaf29fb7e79"],"state_sha256":"cfe37975ddc767cf419248bbc917def2d13fb6a9d8fcb2a3a8cf9836fd0f3f9b"}