{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G4D34MATM6JDVICPLYKJPOF53D","short_pith_number":"pith:G4D34MAT","schema_version":"1.0","canonical_sha256":"3707be301367923aa04f5e1497b8bdd8d51bcba0f5d8a2e90ad42b15be1608d2","source":{"kind":"arxiv","id":"2507.12739","version":1},"attestation_state":"computed","paper":{"title":"Transformer-based Spatial Grounding: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ijazul Haq, Muhammad Saqib, Yingjie Zhang","submitted_at":"2025-07-17T02:44:01Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.12739","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T02:44:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e8a20b398823261e92e0d8cd5f7a088beef0b7b69a7c25b502f37e5065198b3a","abstract_canon_sha256":"42f6987dfa1ea98292e3d85c8620753aeabf9c24f4520a5a64d2a52ea0bed0bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:38.245931Z","signature_b64":"fqa3NBP97ZhhBBfYTBMNGFxnexADlocbsATiuu5HDU4xSmIAJl/19SQ0iu3h0iZYGV5KnmqJ5+fRLXEJ8bnKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3707be301367923aa04f5e1497b8bdd8d51bcba0f5d8a2e90ad42b15be1608d2","last_reissued_at":"2026-07-05T11:38:38.245435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:38.245435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-based Spatial Grounding: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ijazul Haq, Muhammad Saqib, Yingjie Zhang","submitted_at":"2025-07-17T02:44:01Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12739","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.12739/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.12739","created_at":"2026-07-05T11:38:38.245505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12739v1","created_at":"2026-07-05T11:38:38.245505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12739","created_at":"2026-07-05T11:38:38.245505+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4D34MATM6JD","created_at":"2026-07-05T11:38:38.245505+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4D34MATM6JDVICP","created_at":"2026-07-05T11:38:38.245505+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4D34MAT","created_at":"2026-07-05T11:38:38.245505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G4D34MATM6JDVICPLYKJPOF53D","json":"https://pith.science/pith/G4D34MATM6JDVICPLYKJPOF53D.json","graph_json":"https://pith.science/api/pith-number/G4D34MATM6JDVICPLYKJPOF53D/graph.json","events_json":"https://pith.science/api/pith-number/G4D34MATM6JDVICPLYKJPOF53D/events.json","paper":"https://pith.science/paper/G4D34MAT"},"agent_actions":{"view_html":"https://pith.science/pith/G4D34MATM6JDVICPLYKJPOF53D","download_json":"https://pith.science/pith/G4D34MATM6JDVICPLYKJPOF53D.json","view_paper":"https://pith.science/paper/G4D34MAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12739&json=true","fetch_graph":"https://pith.science/api/pith-number/G4D34MATM6JDVICPLYKJPOF53D/graph.json","fetch_events":"https://pith.science/api/pith-number/G4D34MATM6JDVICPLYKJPOF53D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4D34MATM6JDVICPLYKJPOF53D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4D34MATM6JDVICPLYKJPOF53D/action/storage_attestation","attest_author":"https://pith.science/pith/G4D34MATM6JDVICPLYKJPOF53D/action/author_attestation","sign_citation":"https://pith.science/pith/G4D34MATM6JDVICPLYKJPOF53D/action/citation_signature","submit_replication":"https://pith.science/pith/G4D34MATM6JDVICPLYKJPOF53D/action/replication_record"}},"created_at":"2026-07-05T11:38:38.245505+00:00","updated_at":"2026-07-05T11:38:38.245505+00:00"}