{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W72BCTO335GI6G7YXRRFPETDV3","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":"209f30553fd071f5ebd8f98c571413b863c3cadc5470fab50fc381d4f71f6515","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-17T09:05:34Z","title_canon_sha256":"171126f3bffdc7477e01a212e206110f0fd9cb7aec0eab3c982475d06564fe15"},"schema_version":"1.0","source":{"id":"2507.15875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15875","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15875v1","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15875","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"pith_short_12","alias_value":"W72BCTO335GI","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"pith_short_16","alias_value":"W72BCTO335GI6G7Y","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"pith_short_8","alias_value":"W72BCTO3","created_at":"2026-07-05T11:40:58Z"}],"graph_snapshots":[{"event_id":"sha256:a956191a9d2987488e4cbd9b89d6433b820aa743c71328083b1fd8e3107d5004","target":"graph","created_at":"2026-07-05T11:40:58Z","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/2507.15875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Small language models have gained significant popularity due to their efficiency and growing capabilities. However, incorporating additional modalities, such as vision, can exacerbate the challenge of limited context windows by introducing noise. Recent studies have highlighted that Transformer attention mechanisms often disproportionately focus on irrelevant contexts. In this work, we extend the Differential Attention mechanism, originally designed for text-only models, to the text-vision model PaliGemma. Our aim is to evaluate its ability to mitigate noisy information retrieval and reduce ha","authors_text":"Jerry Li, Joseph Hoang, Timothy Oh, Vardhit Veeramachaneni","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-17T09:05:34Z","title":"Differential Multimodal Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15875","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":"sha256:60f27871b29ea2e0250779e5809b19a710c9da8d55309efe2d3b42cad7a70438","target":"record","created_at":"2026-07-05T11:40:58Z","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":"209f30553fd071f5ebd8f98c571413b863c3cadc5470fab50fc381d4f71f6515","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-17T09:05:34Z","title_canon_sha256":"171126f3bffdc7477e01a212e206110f0fd9cb7aec0eab3c982475d06564fe15"},"schema_version":"1.0","source":{"id":"2507.15875","kind":"arxiv","version":1}},"canonical_sha256":"b7f4114ddbdf4c8f1bf8bc62579263aecdfafbcd4d78c018832fdf9bb0e4ad84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7f4114ddbdf4c8f1bf8bc62579263aecdfafbcd4d78c018832fdf9bb0e4ad84","first_computed_at":"2026-07-05T11:40:58.496302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:58.496302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KJys2O1gKy4wzch4s4ED38a5V24P6Ar4eTOsC3lyd4sQvtRMV0LjyD7EtesHOxx1JWHoCXaJ32VibOX3VGryDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:58.496872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60f27871b29ea2e0250779e5809b19a710c9da8d55309efe2d3b42cad7a70438","sha256:a956191a9d2987488e4cbd9b89d6433b820aa743c71328083b1fd8e3107d5004"],"state_sha256":"9c4d2612c57258e27262c2dfa8b6e047af626745819e656a13c4c6f7b38692eb"}