{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JRB2HAAGM57ATG2NC3KBIP4BCZ","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":"3b510813fce759e586eaa14c4c10380ca0d125b5703c5448a9221d028af7be04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-08T08:30:48Z","title_canon_sha256":"7ae019c46dfed7a7c2c06ca7f46256cf95a18953398e2627fe962f0102b9ac55"},"schema_version":"1.0","source":{"id":"2607.07135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07135","created_at":"2026-07-09T01:20:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07135v1","created_at":"2026-07-09T01:20:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07135","created_at":"2026-07-09T01:20:15Z"},{"alias_kind":"pith_short_12","alias_value":"JRB2HAAGM57A","created_at":"2026-07-09T01:20:15Z"},{"alias_kind":"pith_short_16","alias_value":"JRB2HAAGM57ATG2N","created_at":"2026-07-09T01:20:15Z"},{"alias_kind":"pith_short_8","alias_value":"JRB2HAAG","created_at":"2026-07-09T01:20:15Z"}],"graph_snapshots":[{"event_id":"sha256:ad33409c279bde43d6aa984ecd1002cdf212dd80540cea156e91d112b83ec51a","target":"graph","created_at":"2026-07-09T01:20:15Z","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/2607.07135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) relies on softmax-based self-attention, a strictly positive distribution that assigns probability mass to every pair of tokens-even semantically irrelevant ones. While these dense softmax weights are effective for gathering broad context during pre-training, they spread attention across many low-salience tokens, producing noise that obscures the fine-grained, spatially localized cues required for dense, open-vocabulary prediction. We study an inference-time substitution of the row-wise softmax in the final visual self-attention layers with the $\\a","authors_text":"Bernard Ghanem, Chen Zhao, Fatimah Zohra, Shuming Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-08T08:30:48Z","title":"Sparse Attention for Dense Open-Vocabulary Prediction in CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07135","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":"sha256:3ccadab0ab4dfddef0902b260cc9a60d6f30f30afeef6f78a4b8ece37f0acba4","target":"record","created_at":"2026-07-09T01:20:15Z","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":"3b510813fce759e586eaa14c4c10380ca0d125b5703c5448a9221d028af7be04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-08T08:30:48Z","title_canon_sha256":"7ae019c46dfed7a7c2c06ca7f46256cf95a18953398e2627fe962f0102b9ac55"},"schema_version":"1.0","source":{"id":"2607.07135","kind":"arxiv","version":1}},"canonical_sha256":"4c43a38006677e099b4d16d4143f811646b3c5691e20c4b3bf2a4eae851835f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c43a38006677e099b4d16d4143f811646b3c5691e20c4b3bf2a4eae851835f6","first_computed_at":"2026-07-09T01:20:15.486806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:15.486806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2IDFwJ5y9USdLfVich1IGI5nYnj7RnHTTUzu5ecjKTpoF9gLOJpOpSs6NoKH9KbdTDLEoEMfiFPPmhTYBXCPAA==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:15.487185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ccadab0ab4dfddef0902b260cc9a60d6f30f30afeef6f78a4b8ece37f0acba4","sha256:ad33409c279bde43d6aa984ecd1002cdf212dd80540cea156e91d112b83ec51a"],"state_sha256":"b3d87d74e08e1829861bc249b7690800ed7866f2f17bfabf366f0d9c81b94e26"}