{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WSYMD6LDFSHAGF4ZORAJJCDBQZ","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":"12a634875d3b8259da8e3412944a390f6c279f20d17d8a7dc522f6a637221ec8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T17:47:09Z","title_canon_sha256":"5eb9421ed10c7c467e882664c39f10f2c57878b56a64f159a292c878301fb95c"},"schema_version":"1.0","source":{"id":"2507.20025","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20025","created_at":"2026-07-05T11:43:46Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20025v1","created_at":"2026-07-05T11:43:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20025","created_at":"2026-07-05T11:43:46Z"},{"alias_kind":"pith_short_12","alias_value":"WSYMD6LDFSHA","created_at":"2026-07-05T11:43:46Z"},{"alias_kind":"pith_short_16","alias_value":"WSYMD6LDFSHAGF4Z","created_at":"2026-07-05T11:43:46Z"},{"alias_kind":"pith_short_8","alias_value":"WSYMD6LD","created_at":"2026-07-05T11:43:46Z"}],"graph_snapshots":[{"event_id":"sha256:0fd08d674ed9da769c6fa12b5107887f2a09ba1a2100d7290edf2f68456913ac","target":"graph","created_at":"2026-07-05T11:43:46Z","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/2507.20025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning visual representations is foundational for a broad spectrum of downstream tasks. Although recent vision-language contrastive models, such as CLIP and SigLIP, have achieved impressive zero-shot performance via large-scale vision-language alignment, their reliance on global representations constrains their effectiveness for dense prediction tasks, such as grounding, OCR, and segmentation. To address this gap, we introduce Region-Aware Cluster Discrimination (RICE), a novel method that enhances region-level visual and OCR capabilities. We first construct a billion-scale candidate region ","authors_text":"Ismail Elezi, Jiankang Deng, Kaicheng Yang, Kun Wu, Roy Miles, Weimo Deng, Xiang An, Yin Xie, Yongle Zhao, Yumeng Wang, Zimin Ran, Ziyong Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T17:47:09Z","title":"Region-based Cluster Discrimination for Visual Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20025","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:ebade5404530b2dc6a81c91950142e68773755e7bf5c2c2257c1ca1174b0f23e","target":"record","created_at":"2026-07-05T11:43:46Z","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":"12a634875d3b8259da8e3412944a390f6c279f20d17d8a7dc522f6a637221ec8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T17:47:09Z","title_canon_sha256":"5eb9421ed10c7c467e882664c39f10f2c57878b56a64f159a292c878301fb95c"},"schema_version":"1.0","source":{"id":"2507.20025","kind":"arxiv","version":1}},"canonical_sha256":"b4b0c1f9632c8e0317997440948861865e94bf33fa27c82bde279fdcabb1c2a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4b0c1f9632c8e0317997440948861865e94bf33fa27c82bde279fdcabb1c2a6","first_computed_at":"2026-07-05T11:43:46.790173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:46.790173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ev/vdYtb84EwQ7gJb2Vg6bNziKM2EXiyTolnYVWiXuTiJHBKfKbV9k8wQ6JrfbCvgd6skywJ/ybyuEOoPv7NAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:46.790731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20025","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebade5404530b2dc6a81c91950142e68773755e7bf5c2c2257c1ca1174b0f23e","sha256:0fd08d674ed9da769c6fa12b5107887f2a09ba1a2100d7290edf2f68456913ac"],"state_sha256":"a0b0360d91815e5b5ee76ac9d7ba0d37df6f44979b05ab19caefbe794f047430"}