{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BBK6ZLJIA3DCDF63XTH3GMTQAT","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":"ffe9b9efd35a65feff11c692fe46bd3dd2238c647b4d328a87974106fc69305c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-03T12:31:49Z","title_canon_sha256":"abb77a00daaa265331d8b64d3b8d67307e6db22bd6e07805eeb5192fe40efb90"},"schema_version":"1.0","source":{"id":"2608.02148","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02148","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02148v1","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02148","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"pith_short_12","alias_value":"BBK6ZLJIA3DC","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"pith_short_16","alias_value":"BBK6ZLJIA3DCDF63","created_at":"2026-08-04T02:11:06Z"},{"alias_kind":"pith_short_8","alias_value":"BBK6ZLJI","created_at":"2026-08-04T02:11:06Z"}],"graph_snapshots":[{"event_id":"sha256:1c321d22d465a8245cc67356451fdd4e05efcc15d97ab584219c11d287bb7dd3","target":"graph","created_at":"2026-08-04T02:11:06Z","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/2608.02148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal representation learning is a cornerstone of modern AI. By encoding multimodal queries and targets into vectors, it powers industrial search and recommendation and underpins modern agents. Real-world platforms with complex modalities and massive-scale content, such as Douyin, Xiaohongshu, and YouTube, demand both efficiency under billion-scale indexing and fine-grained discrimination for hard matching. Existing MLLM embedding models rarely satisfy both. Contrastive models are efficient but rely on pair-level supervision too coarse for fine-grained distinctions, while CoT-based models","authors_text":"Chu Li, Haonan Chen, Shaohua Jiang, Yuanjiang Wang, Yuanwei Liu, Zhicheng Dou, Zhicheng Wang","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-03T12:31:49Z","title":"Douyin Multimodal Embedding Model Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02148","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":"sha256:103c45b43ac9af959b674b0d3e6cb182bdc0304e1d671d62d21a5131e719d162","target":"record","created_at":"2026-08-04T02:11:06Z","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":"ffe9b9efd35a65feff11c692fe46bd3dd2238c647b4d328a87974106fc69305c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-03T12:31:49Z","title_canon_sha256":"abb77a00daaa265331d8b64d3b8d67307e6db22bd6e07805eeb5192fe40efb90"},"schema_version":"1.0","source":{"id":"2608.02148","kind":"arxiv","version":1}},"canonical_sha256":"0855ecad2806c62197dbbccfb3327004cfbbcd8f46e2594a7adb0cb4d2a19452","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0855ecad2806c62197dbbccfb3327004cfbbcd8f46e2594a7adb0cb4d2a19452","first_computed_at":"2026-08-04T02:11:06.714954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:11:06.714954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LmMOS3TfwiHAORLGOMZlPjVXYCiy4RHx8kSHayNWn7Zqkft5PC7ltp8I+YPYzw4ggWSkTC/DqoLE1aawklq7Aw==","signature_status":"signed_v1","signed_at":"2026-08-04T02:11:06.716672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02148","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:103c45b43ac9af959b674b0d3e6cb182bdc0304e1d671d62d21a5131e719d162","sha256:1c321d22d465a8245cc67356451fdd4e05efcc15d97ab584219c11d287bb7dd3"],"state_sha256":"e615e7bf23edc784e974f9557f128fbc60731c75bb8e21b6b4a3f7f93182c69f"}