{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F2PDY32FDGEJIXUMIUDHOGHFGZ","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":"41af66712c052939a5863d976fc1c2defd364656d0e6bac2821377f0fd8af514","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-28T17:20:39Z","title_canon_sha256":"dfde16d5afa193d0c4b6c18bee0c39a89b649af88eeb7a4202eecf9f2a2e42bc"},"schema_version":"1.0","source":{"id":"2403.19596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19596","created_at":"2026-07-05T09:34:12Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19596v2","created_at":"2026-07-05T09:34:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19596","created_at":"2026-07-05T09:34:12Z"},{"alias_kind":"pith_short_12","alias_value":"F2PDY32FDGEJ","created_at":"2026-07-05T09:34:12Z"},{"alias_kind":"pith_short_16","alias_value":"F2PDY32FDGEJIXUM","created_at":"2026-07-05T09:34:12Z"},{"alias_kind":"pith_short_8","alias_value":"F2PDY32F","created_at":"2026-07-05T09:34:12Z"}],"graph_snapshots":[{"event_id":"sha256:c71aa720a016b395fcdf866f9de31ace64ca20aad1d131b57c9432621d36c69c","target":"graph","created_at":"2026-07-05T09:34:12Z","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/2403.19596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning has been shown as an effective pretraining method similar to contrastive pretraining. However, the incorporation of location-aware information into visual pretraining remains an area with limited research. In this paper, we propose a simple visual pretraining method with location-aware captioners (LocCa). LocCa uses a simple image captioner task interface, to teach a model to read out rich information, i.e. bounding box coordinates, and captions, conditioned on the image pixel input. Thanks to the multitask capabilities of an encoder-decoder architecture, we show that an image","authors_text":"Andreas Steiner, Andr\\'e Susano Pinto, Bo Wan, Filip Pavetic, Ibrahim Alabdulmohsin, Lucas Beyer, Michael Tschannen, Xiaohua Zhai, Xiao Wang, Yongqin Xian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-28T17:20:39Z","title":"LocCa: Visual Pretraining with Location-aware Captioners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19596","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":"sha256:58c1600acf8a3f52d803e0ed7c5c6775105c121bcf97c4e7de154ce6b1007834","target":"record","created_at":"2026-07-05T09:34:12Z","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":"41af66712c052939a5863d976fc1c2defd364656d0e6bac2821377f0fd8af514","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-28T17:20:39Z","title_canon_sha256":"dfde16d5afa193d0c4b6c18bee0c39a89b649af88eeb7a4202eecf9f2a2e42bc"},"schema_version":"1.0","source":{"id":"2403.19596","kind":"arxiv","version":2}},"canonical_sha256":"2e9e3c6f451988945e8c45067718e53673167fbd15b5cc099eff9958b609fb7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e9e3c6f451988945e8c45067718e53673167fbd15b5cc099eff9958b609fb7b","first_computed_at":"2026-07-05T09:34:12.517457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:12.517457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lvpI2xO2viKLetMTyk3XIM/n5HwVFPQlR8Ani0e7rW0XSUtm+crg71K+iPdJzYUQFdogZKQf2MrZzhiXJqYlDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:12.517911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58c1600acf8a3f52d803e0ed7c5c6775105c121bcf97c4e7de154ce6b1007834","sha256:c71aa720a016b395fcdf866f9de31ace64ca20aad1d131b57c9432621d36c69c"],"state_sha256":"92a0685693aa7cc384f55fe641161ebc30406c84a2870e320aca87264357b452"}