{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D3WOVQR4E3GSCDX7R7AU6V7JOT","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":"7741b732ac36e76627142621ed234173e336c7b7050ca400ec06f98601240c24","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T07:04:56Z","title_canon_sha256":"7aaf7f2b7cbb3f45606c2b9a22e20df9e4ac023cf04438dc3ebda2ef3eeebb90"},"schema_version":"1.0","source":{"id":"2504.02328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02328","created_at":"2026-07-05T10:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02328v1","created_at":"2026-07-05T10:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02328","created_at":"2026-07-05T10:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"D3WOVQR4E3GS","created_at":"2026-07-05T10:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"D3WOVQR4E3GSCDX7","created_at":"2026-07-05T10:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"D3WOVQR4","created_at":"2026-07-05T10:43:54Z"}],"graph_snapshots":[{"event_id":"sha256:9c9a9f139fb3d07c877a567335d83bc99bc6c45408db8d052756155d8e06abd8","target":"graph","created_at":"2026-07-05T10:43:54Z","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/2504.02328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) excels in global alignment with language but exhibits limited sensitivity to spatial information, leading to strong performance in zero-shot classification tasks but underperformance in tasks requiring precise spatial understanding. Recent approaches have introduced Region-Language Alignment (RLA) to enhance CLIP's performance in dense multimodal tasks by aligning regional visual representations with corresponding text inputs. However, we find that CLIP ViTs fine-tuned with RLA suffer from notable loss in spatial awareness, which is crucial for de","authors_text":"Congpei Qiu, Tong Zhang, Wei Ke, Xiuxiu Bai, Yanhao Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T07:04:56Z","title":"Refining CLIP's Spatial Awareness: A Visual-Centric Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02328","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":"sha256:898dd137c14b67ccc92655de4839b4d93e186b354113e53df48a729ba4c01413","target":"record","created_at":"2026-07-05T10:43:54Z","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":"7741b732ac36e76627142621ed234173e336c7b7050ca400ec06f98601240c24","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T07:04:56Z","title_canon_sha256":"7aaf7f2b7cbb3f45606c2b9a22e20df9e4ac023cf04438dc3ebda2ef3eeebb90"},"schema_version":"1.0","source":{"id":"2504.02328","kind":"arxiv","version":1}},"canonical_sha256":"1eeceac23c26cd210eff8fc14f57e974db0cfd7394335448dd6c34117897517e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1eeceac23c26cd210eff8fc14f57e974db0cfd7394335448dd6c34117897517e","first_computed_at":"2026-07-05T10:43:54.974282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:54.974282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5pb6lCGGO+2kVxzxGtfCjAsbOgWwXuyg9CF2sNLfzJjWnaHXkO15Dr2RtqSxE7nhG31pbtI+HQ0YFZGWfyxwCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:54.974766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:898dd137c14b67ccc92655de4839b4d93e186b354113e53df48a729ba4c01413","sha256:9c9a9f139fb3d07c877a567335d83bc99bc6c45408db8d052756155d8e06abd8"],"state_sha256":"4594aa32da0cc28e6a9fdd9568acb3fc1a710af0c21642304fe39da5cd062c3a"}