{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5IC2HMSOXRXMBO66AVVN2PX22G","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":"c8490cc9193f8a92e510ff825695683ef218b547d50276316bb8029f623ec067","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T19:48:39Z","title_canon_sha256":"61e4e88825aa7a0642ab8b30671a3c1284426d6dbed742ea3176e270dbda7866"},"schema_version":"1.0","source":{"id":"2606.29579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29579","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29579v1","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29579","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"5IC2HMSOXRXM","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"5IC2HMSOXRXMBO66","created_at":"2026-06-30T01:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"5IC2HMSO","created_at":"2026-06-30T01:18:12Z"}],"graph_snapshots":[{"event_id":"sha256:3f1eceb864f01f4e4d14da329833b461f239bb49de04f13a08f5f23d38f9329c","target":"graph","created_at":"2026-06-30T01:18:12Z","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/2606.29579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial reasoning remains a persistent challenge for many vision language models (VLMs), and improving it typically requires fine-tuning with substantial additional parameters. Our preliminary analysis reveals that rescaling activations in selected transformer layers-without modifying pretrained weights-can significantly influence downstream performance. Motivated by this observation, we propose ScAle, an ultra-lightweight adaptation method that learns a small set of scalar coefficients to modulate last-token attention and MLP activations in a fully frozen backbone. We evaluate our method on t","authors_text":"Pu Zhao, Rahul Chowdhury, Timothy A Rupprecht, Xuan Shen, Yanzhi Wang","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T19:48:39Z","title":"ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29579","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:c562d7a40dc0709bb78fa4b36e85a2429cce6d4c9a50e11f5b3ad16e7434d0a7","target":"record","created_at":"2026-06-30T01:18:12Z","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":"c8490cc9193f8a92e510ff825695683ef218b547d50276316bb8029f623ec067","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T19:48:39Z","title_canon_sha256":"61e4e88825aa7a0642ab8b30671a3c1284426d6dbed742ea3176e270dbda7866"},"schema_version":"1.0","source":{"id":"2606.29579","kind":"arxiv","version":1}},"canonical_sha256":"ea05a3b24ebc6ec0bbde056add3efad1a77207408bac2c885776722b379059ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea05a3b24ebc6ec0bbde056add3efad1a77207408bac2c885776722b379059ed","first_computed_at":"2026-06-30T01:18:12.922726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:12.922726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yg/kyCOnxaVOnlCwX4s1NxS59CjzQPZA5JVhLgbnKOlxZoMLEJ3LpR688YKYku+3hHSdl9lUb7HCsFfoYF0KDA==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:12.923189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c562d7a40dc0709bb78fa4b36e85a2429cce6d4c9a50e11f5b3ad16e7434d0a7","sha256:3f1eceb864f01f4e4d14da329833b461f239bb49de04f13a08f5f23d38f9329c"],"state_sha256":"1692f7a84b972d6c46a52b627089a5b1724436d6dc3db46fefe0ea1de68887c7"}