{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QL3P2ENGC4QGRB6ZA6KZE2CT36","short_pith_number":"pith:QL3P2ENG","schema_version":"1.0","canonical_sha256":"82f6fd11a617206887d90795926853df9467fec387323ff72214d7157eb3a11c","source":{"kind":"arxiv","id":"2308.09599","version":3},"attestation_state":"computed","paper":{"title":"Language-Guided Diffusion Model for Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Baochun Li, Sijia Chen","submitted_at":"2023-08-18T14:54:13Z","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"},"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":"2308.09599","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T14:54:13Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"37d46c9b3933c39f1fbc6d50a91d02a5cece4f94b37bc85c2cb716c365b024bc","abstract_canon_sha256":"f8d2e9aa8ae8c244e31d152cfae741e3c5fa8d1de7fe7fc3f0039c90afd1d498"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:19.978645Z","signature_b64":"nLNlzGM+6xAFWX8SQWPggVDHWBAgkw0BxgxV3lVXXcaPtDr2K4U0z3grZIlPavEQeL/lr6+FbeUOqBqF0m4sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82f6fd11a617206887d90795926853df9467fec387323ff72214d7157eb3a11c","last_reissued_at":"2026-07-05T10:19:19.978159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:19.978159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Guided Diffusion Model for Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Baochun Li, Sijia Chen","submitted_at":"2023-08-18T14:54:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09599","kind":"arxiv","version":3},"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/2308.09599/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":"2308.09599","created_at":"2026-07-05T10:19:19.978224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09599v3","created_at":"2026-07-05T10:19:19.978224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09599","created_at":"2026-07-05T10:19:19.978224+00:00"},{"alias_kind":"pith_short_12","alias_value":"QL3P2ENGC4QG","created_at":"2026-07-05T10:19:19.978224+00:00"},{"alias_kind":"pith_short_16","alias_value":"QL3P2ENGC4QGRB6Z","created_at":"2026-07-05T10:19:19.978224+00:00"},{"alias_kind":"pith_short_8","alias_value":"QL3P2ENG","created_at":"2026-07-05T10:19:19.978224+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/QL3P2ENGC4QGRB6ZA6KZE2CT36","json":"https://pith.science/pith/QL3P2ENGC4QGRB6ZA6KZE2CT36.json","graph_json":"https://pith.science/api/pith-number/QL3P2ENGC4QGRB6ZA6KZE2CT36/graph.json","events_json":"https://pith.science/api/pith-number/QL3P2ENGC4QGRB6ZA6KZE2CT36/events.json","paper":"https://pith.science/paper/QL3P2ENG"},"agent_actions":{"view_html":"https://pith.science/pith/QL3P2ENGC4QGRB6ZA6KZE2CT36","download_json":"https://pith.science/pith/QL3P2ENGC4QGRB6ZA6KZE2CT36.json","view_paper":"https://pith.science/paper/QL3P2ENG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09599&json=true","fetch_graph":"https://pith.science/api/pith-number/QL3P2ENGC4QGRB6ZA6KZE2CT36/graph.json","fetch_events":"https://pith.science/api/pith-number/QL3P2ENGC4QGRB6ZA6KZE2CT36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QL3P2ENGC4QGRB6ZA6KZE2CT36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QL3P2ENGC4QGRB6ZA6KZE2CT36/action/storage_attestation","attest_author":"https://pith.science/pith/QL3P2ENGC4QGRB6ZA6KZE2CT36/action/author_attestation","sign_citation":"https://pith.science/pith/QL3P2ENGC4QGRB6ZA6KZE2CT36/action/citation_signature","submit_replication":"https://pith.science/pith/QL3P2ENGC4QGRB6ZA6KZE2CT36/action/replication_record"}},"created_at":"2026-07-05T10:19:19.978224+00:00","updated_at":"2026-07-05T10:19:19.978224+00:00"}