{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QL3P2ENGC4QGRB6ZA6KZE2CT36","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":"f8d2e9aa8ae8c244e31d152cfae741e3c5fa8d1de7fe7fc3f0039c90afd1d498","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T14:54:13Z","title_canon_sha256":"37d46c9b3933c39f1fbc6d50a91d02a5cece4f94b37bc85c2cb716c365b024bc"},"schema_version":"1.0","source":{"id":"2308.09599","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09599","created_at":"2026-07-05T10:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09599v3","created_at":"2026-07-05T10:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09599","created_at":"2026-07-05T10:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"QL3P2ENGC4QG","created_at":"2026-07-05T10:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"QL3P2ENGC4QGRB6Z","created_at":"2026-07-05T10:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"QL3P2ENG","created_at":"2026-07-05T10:19:19Z"}],"graph_snapshots":[{"event_id":"sha256:80491bf682bd4350187717b418175556b29959ba4be87784803cd6e29248d917","target":"graph","created_at":"2026-07-05T10:19:19Z","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/2308.09599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding (VG) tasks involve explicit cross-modal alignment, as semantically corresponding image regions are to be located for the language phrases provided. Existing approaches complete such visual-text reasoning in a single-step manner. Their performance causes high demands on large-scale anchors and over-designed multi-modal fusion modules based on human priors, leading to complicated frameworks that may be difficult to train and overfit to specific scenarios. Even worse, such once-for-all reasoning mechanisms are incapable of refining boxes continuously to enhance query-region match","authors_text":"Baochun Li, Sijia Chen","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T14:54:13Z","title":"Language-Guided Diffusion Model for Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09599","kind":"arxiv","version":3},"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":"sha256:175c1af579745426dc2eae1a870808922bc6cb25290c468d599b2b2b307930dc","target":"record","created_at":"2026-07-05T10:19:19Z","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":"f8d2e9aa8ae8c244e31d152cfae741e3c5fa8d1de7fe7fc3f0039c90afd1d498","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T14:54:13Z","title_canon_sha256":"37d46c9b3933c39f1fbc6d50a91d02a5cece4f94b37bc85c2cb716c365b024bc"},"schema_version":"1.0","source":{"id":"2308.09599","kind":"arxiv","version":3}},"canonical_sha256":"82f6fd11a617206887d90795926853df9467fec387323ff72214d7157eb3a11c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82f6fd11a617206887d90795926853df9467fec387323ff72214d7157eb3a11c","first_computed_at":"2026-07-05T10:19:19.978159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:19.978159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nLNlzGM+6xAFWX8SQWPggVDHWBAgkw0BxgxV3lVXXcaPtDr2K4U0z3grZIlPavEQeL/lr6+FbeUOqBqF0m4sDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:19.978645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.09599","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:175c1af579745426dc2eae1a870808922bc6cb25290c468d599b2b2b307930dc","sha256:80491bf682bd4350187717b418175556b29959ba4be87784803cd6e29248d917"],"state_sha256":"4f812fe68b48fbccf235980fdd5969a3bac3f93d3cde06a25da2adcf69f01e38"}