{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CSLCRUY3HWBKEQ7AAQBNBQ3LMB","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":"63e8d20d32238d6f0a15765cfd5e9a18c764d66d2833ee34963415ec62d5ce30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T21:01:01Z","title_canon_sha256":"301f41507517cb0460f1ec12d189bc29879b484a299b2786ab0f410c183e4c55"},"schema_version":"1.0","source":{"id":"2410.11087","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11087","created_at":"2026-07-05T10:23:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11087v2","created_at":"2026-07-05T10:23:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11087","created_at":"2026-07-05T10:23:24Z"},{"alias_kind":"pith_short_12","alias_value":"CSLCRUY3HWBK","created_at":"2026-07-05T10:23:24Z"},{"alias_kind":"pith_short_16","alias_value":"CSLCRUY3HWBKEQ7A","created_at":"2026-07-05T10:23:24Z"},{"alias_kind":"pith_short_8","alias_value":"CSLCRUY3","created_at":"2026-07-05T10:23:24Z"}],"graph_snapshots":[{"event_id":"sha256:ef8af761010dd596e5f16a90eb3874ecbb7201b414c0c9ac529e0ea1da09cb15","target":"graph","created_at":"2026-07-05T10:23:24Z","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/2410.11087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models (VLMs) have seen growing adoption in recent years, but many still struggle with basic spatial reasoning errors. We hypothesize that this is due to VLMs adopting pre-trained vision backbones, specifically vision transformers (ViTs) trained with image-level supervision and minimal inductive biases. Such models may fail to encode the class contents at each position in the image, and our goal is to resolve this with a vision backbone that effectively captures both local and global image semantics. Our main insight is that we do not require new supervision to learn this capab","authors_text":"Ian Covert, James Zou, Tatsunori Hashimoto, Tony Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T21:01:01Z","title":"Locality Alignment Improves Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11087","kind":"arxiv","version":2},"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":"sha256:9b94848250af21826196a44efdca0a886c6c6b9ef6219653cf382250e10bba3c","target":"record","created_at":"2026-07-05T10:23:24Z","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":"63e8d20d32238d6f0a15765cfd5e9a18c764d66d2833ee34963415ec62d5ce30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T21:01:01Z","title_canon_sha256":"301f41507517cb0460f1ec12d189bc29879b484a299b2786ab0f410c183e4c55"},"schema_version":"1.0","source":{"id":"2410.11087","kind":"arxiv","version":2}},"canonical_sha256":"149628d31b3d82a243e00402d0c36b606e58b719748fd20ff89ac7f42a659bdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"149628d31b3d82a243e00402d0c36b606e58b719748fd20ff89ac7f42a659bdf","first_computed_at":"2026-07-05T10:23:24.124308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:24.124308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5ZSHt7IAbnmgaDl26z/VXhc4VJbhH49UW7r4peAz4LaOpmyH2/jKdeH+tyBBLAlenDWJR4Ntj3OQuFfTBxQXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:24.125219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11087","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b94848250af21826196a44efdca0a886c6c6b9ef6219653cf382250e10bba3c","sha256:ef8af761010dd596e5f16a90eb3874ecbb7201b414c0c9ac529e0ea1da09cb15"],"state_sha256":"ca9f0f31775f3760d3484c9fa5e1dd75708479be0b2e0434e377c5d3e63e3cbf"}