{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:24F7YE5CBGLCFIFB5CUCAX5LIX","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":"0393bb0ffb1cb6f5e323622e2e486177f1151a8f79458ea78a2ad491f2f95b60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T12:05:34Z","title_canon_sha256":"3fe9acffc8236b5dfe6e6b24d2aac8ff4c85ded8ed24bf5ec15421ec59d3577f"},"schema_version":"1.0","source":{"id":"2411.18270","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18270","created_at":"2026-07-05T09:43:37Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18270v2","created_at":"2026-07-05T09:43:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18270","created_at":"2026-07-05T09:43:37Z"},{"alias_kind":"pith_short_12","alias_value":"24F7YE5CBGLC","created_at":"2026-07-05T09:43:37Z"},{"alias_kind":"pith_short_16","alias_value":"24F7YE5CBGLCFIFB","created_at":"2026-07-05T09:43:37Z"},{"alias_kind":"pith_short_8","alias_value":"24F7YE5C","created_at":"2026-07-05T09:43:37Z"}],"graph_snapshots":[{"event_id":"sha256:1b0f720efe6478c696bd7a6b2ea88e52efd6f6d6154630228578107436923d2b","target":"graph","created_at":"2026-07-05T09:43:37Z","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/2411.18270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal models have demonstrated impressive capabilities in object recognition and scene understanding. However, these models often struggle with precise spatial localization - a critical capability for real-world applications. Inspired by how humans use grid-based references like chess boards and maps, we propose introducing explicit visual position encoding through a simple grid overlay approach. By adding a 9x9 black grid pattern onto input images, our method provides visual spatial guidance analogous to how positional encoding works in transformers, but in an explicit","authors_text":"Dongmei Yu, Joongwon Chae, Lian Zhang, Peiwu Qin, Zhenyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T12:05:34Z","title":"Grid-augmented vision: A simple yet effective approach for enhanced spatial understanding in multi-modal agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18270","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":"sha256:04f537bdbb0f45a587d1c31464fc14dfb1bc3de4980e8015cb8102853212a643","target":"record","created_at":"2026-07-05T09:43:37Z","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":"0393bb0ffb1cb6f5e323622e2e486177f1151a8f79458ea78a2ad491f2f95b60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T12:05:34Z","title_canon_sha256":"3fe9acffc8236b5dfe6e6b24d2aac8ff4c85ded8ed24bf5ec15421ec59d3577f"},"schema_version":"1.0","source":{"id":"2411.18270","kind":"arxiv","version":2}},"canonical_sha256":"d70bfc13a2099622a0a1e8a8205fab45d9d43d8285508f322b8d9ca5ecddba33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d70bfc13a2099622a0a1e8a8205fab45d9d43d8285508f322b8d9ca5ecddba33","first_computed_at":"2026-07-05T09:43:37.571394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:37.571394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HQkw469d/yQA9Zp+za4OIs4d+XGeAQY3C+MvhLKQOQFOy/u/By8DZ46KDUg6+YLO2wSwRBLVVymucKIjTGSuDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:37.572875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18270","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04f537bdbb0f45a587d1c31464fc14dfb1bc3de4980e8015cb8102853212a643","sha256:1b0f720efe6478c696bd7a6b2ea88e52efd6f6d6154630228578107436923d2b"],"state_sha256":"55170a2cfc69fe32dfab92097b4dd2687ffc5e3d10d9a2cc76195087bf409560"}