{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:34LPWDMEGIGGYOXE5JEPA7FJEK","short_pith_number":"pith:34LPWDME","schema_version":"1.0","canonical_sha256":"df16fb0d84320c6c3ae4ea48f07ca9229dc3ea7bbc0ab07a995cf83b807f8eec","source":{"kind":"arxiv","id":"2211.15521","version":1},"attestation_state":"computed","paper":{"title":"G^3: Geolocation via Guidebook Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Daniel Fried, Giscard Biamby, Grace Luo, Trevor Darrell","submitted_at":"2022-11-28T16:34:40Z","abstract_excerpt":"We demonstrate how language can improve geolocation: the task of predicting the location where an image was taken. Here we study explicit knowledge from human-written guidebooks that describe the salient and class-discriminative visual features humans use for geolocation. We propose the task of Geolocation via Guidebook Grounding that uses a dataset of StreetView images from a diverse set of locations and an associated textual guidebook for GeoGuessr, a popular interactive geolocation game. Our approach predicts a country for each image by attending over the clues automatically extracted from "},"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":"2211.15521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T16:34:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"768f0cfad337165ea98f2a5ae6cbdbecf4dccbe14a792563d19bb81c26b7a6ed","abstract_canon_sha256":"85eefee60dcc833bf555c8b567fe9e9a52319214c26b5c036202977c4268a000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:05.210661Z","signature_b64":"/Zaou50Ti6XYf/81sXIDUsPLavfSOpFKvlO3rQmm+cbWW4Cbn66UlGAWIU4zJXCJGIdzlxAx933Hd9NY39OkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df16fb0d84320c6c3ae4ea48f07ca9229dc3ea7bbc0ab07a995cf83b807f8eec","last_reissued_at":"2026-07-05T05:20:05.210214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:05.210214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"G^3: Geolocation via Guidebook Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Daniel Fried, Giscard Biamby, Grace Luo, Trevor Darrell","submitted_at":"2022-11-28T16:34:40Z","abstract_excerpt":"We demonstrate how language can improve geolocation: the task of predicting the location where an image was taken. Here we study explicit knowledge from human-written guidebooks that describe the salient and class-discriminative visual features humans use for geolocation. We propose the task of Geolocation via Guidebook Grounding that uses a dataset of StreetView images from a diverse set of locations and an associated textual guidebook for GeoGuessr, a popular interactive geolocation game. Our approach predicts a country for each image by attending over the clues automatically extracted from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15521","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/2211.15521/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":"2211.15521","created_at":"2026-07-05T05:20:05.210272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15521v1","created_at":"2026-07-05T05:20:05.210272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15521","created_at":"2026-07-05T05:20:05.210272+00:00"},{"alias_kind":"pith_short_12","alias_value":"34LPWDMEGIGG","created_at":"2026-07-05T05:20:05.210272+00:00"},{"alias_kind":"pith_short_16","alias_value":"34LPWDMEGIGGYOXE","created_at":"2026-07-05T05:20:05.210272+00:00"},{"alias_kind":"pith_short_8","alias_value":"34LPWDME","created_at":"2026-07-05T05:20:05.210272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19967","citing_title":"Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/34LPWDMEGIGGYOXE5JEPA7FJEK","json":"https://pith.science/pith/34LPWDMEGIGGYOXE5JEPA7FJEK.json","graph_json":"https://pith.science/api/pith-number/34LPWDMEGIGGYOXE5JEPA7FJEK/graph.json","events_json":"https://pith.science/api/pith-number/34LPWDMEGIGGYOXE5JEPA7FJEK/events.json","paper":"https://pith.science/paper/34LPWDME"},"agent_actions":{"view_html":"https://pith.science/pith/34LPWDMEGIGGYOXE5JEPA7FJEK","download_json":"https://pith.science/pith/34LPWDMEGIGGYOXE5JEPA7FJEK.json","view_paper":"https://pith.science/paper/34LPWDME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15521&json=true","fetch_graph":"https://pith.science/api/pith-number/34LPWDMEGIGGYOXE5JEPA7FJEK/graph.json","fetch_events":"https://pith.science/api/pith-number/34LPWDMEGIGGYOXE5JEPA7FJEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34LPWDMEGIGGYOXE5JEPA7FJEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34LPWDMEGIGGYOXE5JEPA7FJEK/action/storage_attestation","attest_author":"https://pith.science/pith/34LPWDMEGIGGYOXE5JEPA7FJEK/action/author_attestation","sign_citation":"https://pith.science/pith/34LPWDMEGIGGYOXE5JEPA7FJEK/action/citation_signature","submit_replication":"https://pith.science/pith/34LPWDMEGIGGYOXE5JEPA7FJEK/action/replication_record"}},"created_at":"2026-07-05T05:20:05.210272+00:00","updated_at":"2026-07-05T05:20:05.210272+00:00"}