{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G4D34MATM6JDVICPLYKJPOF53D","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":"42f6987dfa1ea98292e3d85c8620753aeabf9c24f4520a5a64d2a52ea0bed0bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T02:44:01Z","title_canon_sha256":"e8a20b398823261e92e0d8cd5f7a088beef0b7b69a7c25b502f37e5065198b3a"},"schema_version":"1.0","source":{"id":"2507.12739","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12739","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12739v1","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12739","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"G4D34MATM6JD","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"G4D34MATM6JDVICP","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"G4D34MAT","created_at":"2026-07-05T11:38:38Z"}],"graph_snapshots":[{"event_id":"sha256:87429869daef6a07f29cae4f5fd963ca2a60e189befdae696eb97b5ae6cfe1e3","target":"graph","created_at":"2026-07-05T11:38:38Z","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/2507.12739/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial grounding, the process of associating natural language expressions with corresponding image regions, has rapidly advanced due to the introduction of transformer-based models, significantly enhancing multimodal representation and cross-modal alignment. Despite this progress, the field lacks a comprehensive synthesis of current methodologies, dataset usage, evaluation metrics, and industrial applicability. This paper presents a systematic literature review of transformer-based spatial grounding approaches from 2018 to 2025. Our analysis identifies dominant model architectures, prevalent ","authors_text":"Ijazul Haq, Muhammad Saqib, Yingjie Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T02:44:01Z","title":"Transformer-based Spatial Grounding: A Comprehensive Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12739","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":"sha256:4dbc1057a3c96b4dbe103722fff18f6f05ea9b263d7a9aecbc39f7c238136637","target":"record","created_at":"2026-07-05T11:38:38Z","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":"42f6987dfa1ea98292e3d85c8620753aeabf9c24f4520a5a64d2a52ea0bed0bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T02:44:01Z","title_canon_sha256":"e8a20b398823261e92e0d8cd5f7a088beef0b7b69a7c25b502f37e5065198b3a"},"schema_version":"1.0","source":{"id":"2507.12739","kind":"arxiv","version":1}},"canonical_sha256":"3707be301367923aa04f5e1497b8bdd8d51bcba0f5d8a2e90ad42b15be1608d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3707be301367923aa04f5e1497b8bdd8d51bcba0f5d8a2e90ad42b15be1608d2","first_computed_at":"2026-07-05T11:38:38.245435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:38.245435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fqa3NBP97ZhhBBfYTBMNGFxnexADlocbsATiuu5HDU4xSmIAJl/19SQ0iu3h0iZYGV5KnmqJ5+fRLXEJ8bnKBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:38.245931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12739","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dbc1057a3c96b4dbe103722fff18f6f05ea9b263d7a9aecbc39f7c238136637","sha256:87429869daef6a07f29cae4f5fd963ca2a60e189befdae696eb97b5ae6cfe1e3"],"state_sha256":"a2266652fa7a296f2fd7e00b8bc9a0890399b77f776db17bdf2d344ae794e89b"}