{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I3QVJPTUKUG4F7QSEVYPXB3HQG","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":"b8a29d1a8c79b930efb982ebaa6d0cefd67c8ccfe37d52cad3f3ad67f9ccc7da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T05:47:59Z","title_canon_sha256":"6219ee0537e98545c5b09032ba80b38e9d5ac62c5d31ca6871c0511179147111"},"schema_version":"1.0","source":{"id":"2412.00684","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00684","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00684v2","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00684","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"I3QVJPTUKUG4","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"I3QVJPTUKUG4F7QS","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"I3QVJPTU","created_at":"2026-07-05T10:51:29Z"}],"graph_snapshots":[{"event_id":"sha256:af85ab277a6b412ebac177e4103572db4a044c1737087e8f97178fc42d26f53f","target":"graph","created_at":"2026-07-05T10:51:29Z","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/2412.00684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding aims to localize the image regions based on a textual query. Given the difficulty of large-scale data curation, we investigate how to effectively learn visual grounding under data-scarce settings in this paper. To address the data scarcity, we propose a novel framework, POBF (Paint Outside the Box and Filter). POBF synthesizes images by inpainting outside the box, tackling a label misalignment issue encountered in previous works. Furthermore, POBF leverages an innovative filtering scheme to select the most effective training data. This scheme combines a hardness score and an o","authors_text":"Boyang Li, Haoxin Li, Jianfei Yu, Zilin Du","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T05:47:59Z","title":"Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00684","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":"sha256:87ab6df597a1a77819f31db3d760c22337487a83bc264edcde60b1966dd20f94","target":"record","created_at":"2026-07-05T10:51:29Z","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":"b8a29d1a8c79b930efb982ebaa6d0cefd67c8ccfe37d52cad3f3ad67f9ccc7da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T05:47:59Z","title_canon_sha256":"6219ee0537e98545c5b09032ba80b38e9d5ac62c5d31ca6871c0511179147111"},"schema_version":"1.0","source":{"id":"2412.00684","kind":"arxiv","version":2}},"canonical_sha256":"46e154be74550dc2fe122570fb876781982f504630ef8a22da4ab78bfcd0b037","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46e154be74550dc2fe122570fb876781982f504630ef8a22da4ab78bfcd0b037","first_computed_at":"2026-07-05T10:51:29.352421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:29.352421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MXetEuXJ1AwCdflAQ5GvDMqR3BJYHsM8LEyY21+teh/abQaTv4JZ0aXDA+QvMFCAeOo7CXdM1x9p/Nniec9WDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:29.352924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00684","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87ab6df597a1a77819f31db3d760c22337487a83bc264edcde60b1966dd20f94","sha256:af85ab277a6b412ebac177e4103572db4a044c1737087e8f97178fc42d26f53f"],"state_sha256":"cfd2285de9a253542b548448a3b8a28c59ba153a2d7826868ac83c55fda67a8b"}