{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2IG5BAQGCWKVWZCPQHBRO436TP","short_pith_number":"pith:2IG5BAQG","schema_version":"1.0","canonical_sha256":"d20dd0820615955b644f81c317737e9bda5392ce37fcf500be7fac1392d3243b","source":{"kind":"arxiv","id":"2203.16265","version":2},"attestation_state":"computed","paper":{"title":"SeqTR: A Simple yet Universal Network for Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Chen, Chaoyang Zhu, Gen Luo, Liujuan Cao, Mingbao Lin, Rongrong Ji, Xiaoshuai Sun, Xingjia Pan, Yiyi Zhou, Yunhang Shen","submitted_at":"2022-03-30T12:52:46Z","abstract_excerpt":"In this paper, we propose a simple yet universal network termed SeqTR for visual grounding tasks, e.g., phrase localization, referring expression comprehension (REC) and segmentation (RES). The canonical paradigms for visual grounding often require substantial expertise in designing network architectures and loss functions, making them hard to generalize across tasks. To simplify and unify the modeling, we cast visual grounding as a point prediction problem conditioned on image and text inputs, where either the bounding box or binary mask is represented as a sequence of discrete coordinate tok"},"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":"2203.16265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-30T12:52:46Z","cross_cats_sorted":[],"title_canon_sha256":"d3e040350ca01cf9498baa4833ea3440e606d55a391b887fc2a11e307caa2474","abstract_canon_sha256":"1e149abbe3fc4bd8b0de41f5d60626f95240533221168e0fdfe9a4f5e60bd89e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:34.726996Z","signature_b64":"yCqKDA6AXWExxRO9X6FyBTay3uRleywEQy4wCZ5B3l85GmHoUVmzqkl+xjmzbqSFKtA5D3ylQCSl8ZtGUUjhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d20dd0820615955b644f81c317737e9bda5392ce37fcf500be7fac1392d3243b","last_reissued_at":"2026-07-05T05:19:34.726423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:34.726423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeqTR: A Simple yet Universal Network for Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Chen, Chaoyang Zhu, Gen Luo, Liujuan Cao, Mingbao Lin, Rongrong Ji, Xiaoshuai Sun, Xingjia Pan, Yiyi Zhou, Yunhang Shen","submitted_at":"2022-03-30T12:52:46Z","abstract_excerpt":"In this paper, we propose a simple yet universal network termed SeqTR for visual grounding tasks, e.g., phrase localization, referring expression comprehension (REC) and segmentation (RES). The canonical paradigms for visual grounding often require substantial expertise in designing network architectures and loss functions, making them hard to generalize across tasks. To simplify and unify the modeling, we cast visual grounding as a point prediction problem conditioned on image and text inputs, where either the bounding box or binary mask is represented as a sequence of discrete coordinate tok"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16265","kind":"arxiv","version":2},"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/2203.16265/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":"2203.16265","created_at":"2026-07-05T05:19:34.726485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16265v2","created_at":"2026-07-05T05:19:34.726485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16265","created_at":"2026-07-05T05:19:34.726485+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IG5BAQGCWKV","created_at":"2026-07-05T05:19:34.726485+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IG5BAQGCWKVWZCP","created_at":"2026-07-05T05:19:34.726485+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IG5BAQG","created_at":"2026-07-05T05:19:34.726485+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/2IG5BAQGCWKVWZCPQHBRO436TP","json":"https://pith.science/pith/2IG5BAQGCWKVWZCPQHBRO436TP.json","graph_json":"https://pith.science/api/pith-number/2IG5BAQGCWKVWZCPQHBRO436TP/graph.json","events_json":"https://pith.science/api/pith-number/2IG5BAQGCWKVWZCPQHBRO436TP/events.json","paper":"https://pith.science/paper/2IG5BAQG"},"agent_actions":{"view_html":"https://pith.science/pith/2IG5BAQGCWKVWZCPQHBRO436TP","download_json":"https://pith.science/pith/2IG5BAQGCWKVWZCPQHBRO436TP.json","view_paper":"https://pith.science/paper/2IG5BAQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16265&json=true","fetch_graph":"https://pith.science/api/pith-number/2IG5BAQGCWKVWZCPQHBRO436TP/graph.json","fetch_events":"https://pith.science/api/pith-number/2IG5BAQGCWKVWZCPQHBRO436TP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IG5BAQGCWKVWZCPQHBRO436TP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IG5BAQGCWKVWZCPQHBRO436TP/action/storage_attestation","attest_author":"https://pith.science/pith/2IG5BAQGCWKVWZCPQHBRO436TP/action/author_attestation","sign_citation":"https://pith.science/pith/2IG5BAQGCWKVWZCPQHBRO436TP/action/citation_signature","submit_replication":"https://pith.science/pith/2IG5BAQGCWKVWZCPQHBRO436TP/action/replication_record"}},"created_at":"2026-07-05T05:19:34.726485+00:00","updated_at":"2026-07-05T05:19:34.726485+00:00"}