{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O4FDWJE4EFA4ZMV3INZBKTU4CR","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":"05a4c585e415183dfabfa226951b563d338624d5d9750c8c66249cb35255c6d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-28T19:26:37Z","title_canon_sha256":"128de6b64cfc7a0b7b4d896c0f46eb6bab3b85afadc96eaf4043c5ccf40b7f61"},"schema_version":"1.0","source":{"id":"2203.00048","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00048","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00048v3","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00048","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"O4FDWJE4EFA4","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"O4FDWJE4EFA4ZMV3","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"O4FDWJE4","created_at":"2026-07-05T04:09:02Z"}],"graph_snapshots":[{"event_id":"sha256:707feafd1556569beab26a976b7519f5341cece0f732d054ed869bd2f987a8ef","target":"graph","created_at":"2026-07-05T04:09:02Z","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/2203.00048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning signals from different modalities is an important step in vision-language representation learning as it affects the performance of later stages such as cross-modality fusion. Since image and text typically reside in different regions of the feature space, directly aligning them at instance level is challenging especially when features are still evolving during training. In this paper, we propose to align at a higher and more stable level using cluster representation. Specifically, we treat image and text as two \"views\" of the same entity, and encode them into a joint vision-language c","authors_text":"Belinda Zeng, Jiali Duan, Jinyu Yang, Liqun Chen, Son Tran, Trishul Chilimbi, Yi Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-28T19:26:37Z","title":"Multi-modal Alignment using Representation Codebook"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00048","kind":"arxiv","version":3},"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":"sha256:8434a75084c05ec8cf8fd3f5ab4d6e58bab0850f0109d7167b4e7de0fda70aa8","target":"record","created_at":"2026-07-05T04:09:02Z","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":"05a4c585e415183dfabfa226951b563d338624d5d9750c8c66249cb35255c6d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-28T19:26:37Z","title_canon_sha256":"128de6b64cfc7a0b7b4d896c0f46eb6bab3b85afadc96eaf4043c5ccf40b7f61"},"schema_version":"1.0","source":{"id":"2203.00048","kind":"arxiv","version":3}},"canonical_sha256":"770a3b249c2141ccb2bb4372154e9c147ea922b7bf120ed98ec3ccdd43c7a612","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"770a3b249c2141ccb2bb4372154e9c147ea922b7bf120ed98ec3ccdd43c7a612","first_computed_at":"2026-07-05T04:09:02.095372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:02.095372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"94c+2Hoo0PGyMb7xYLA/ywA2lQlgnTdyGVLpyXxtgLEteYkdQCSp5k81RDpJxBLtNBEmwrrJuIAKrfaHBXEHDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:02.095893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.00048","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8434a75084c05ec8cf8fd3f5ab4d6e58bab0850f0109d7167b4e7de0fda70aa8","sha256:707feafd1556569beab26a976b7519f5341cece0f732d054ed869bd2f987a8ef"],"state_sha256":"264b85cf88e83c0e7f9c23db2fd2c9d042fe7bb26e61e677072f6e90aec0c82e"}