{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y6MMVIN66RHXLUZZFTU2EMDECO","short_pith_number":"pith:Y6MMVIN6","schema_version":"1.0","canonical_sha256":"c798caa1bef44f75d3392ce9a2306413b89ceda41fc2fc5143336727f57d0856","source":{"kind":"arxiv","id":"2410.05963","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yongtao Wang, Zhi Tang, Zhiwei Lin","submitted_at":"2024-10-08T12:15:08Z","abstract_excerpt":"Existing perception models achieve great success by learning from large amounts of labeled data, but they still struggle with open-world scenarios. To alleviate this issue, researchers introduce open-set perception tasks to detect or segment unseen objects in the training set. However, these models require predefined object categories as inputs during inference, which are not available in real-world scenarios. Recently, researchers pose a new and more practical problem, \\textit{i.e.}, open-ended object detection, which discovers unseen objects without any object categories as inputs. In this p"},"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":"2410.05963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T12:15:08Z","cross_cats_sorted":[],"title_canon_sha256":"2cf2d59448e52a2553ec67050a3f861782178dcaf8751cbfde05fbc223d4c6bc","abstract_canon_sha256":"4fe23f56b7b72c0e6c25de4f574339a24282a11c7880bd0575e79b91a3b2baee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:53.797385Z","signature_b64":"pZbEhT7hPY7Bwt2r2evg90R4dezMY9TFDhfjgH78JDJOpEWLiVvgAgJQDN9Q+Sa+0vl8bhl8sf/JwQTNqnlXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c798caa1bef44f75d3392ce9a2306413b89ceda41fc2fc5143336727f57d0856","last_reissued_at":"2026-07-05T09:17:53.796908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:53.796908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yongtao Wang, Zhi Tang, Zhiwei Lin","submitted_at":"2024-10-08T12:15:08Z","abstract_excerpt":"Existing perception models achieve great success by learning from large amounts of labeled data, but they still struggle with open-world scenarios. To alleviate this issue, researchers introduce open-set perception tasks to detect or segment unseen objects in the training set. However, these models require predefined object categories as inputs during inference, which are not available in real-world scenarios. Recently, researchers pose a new and more practical problem, \\textit{i.e.}, open-ended object detection, which discovers unseen objects without any object categories as inputs. In this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05963","kind":"arxiv","version":1},"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/2410.05963/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":"2410.05963","created_at":"2026-07-05T09:17:53.796966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05963v1","created_at":"2026-07-05T09:17:53.796966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05963","created_at":"2026-07-05T09:17:53.796966+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6MMVIN66RHX","created_at":"2026-07-05T09:17:53.796966+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6MMVIN66RHXLUZZ","created_at":"2026-07-05T09:17:53.796966+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6MMVIN6","created_at":"2026-07-05T09:17:53.796966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16112","citing_title":"AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6MMVIN66RHXLUZZFTU2EMDECO","json":"https://pith.science/pith/Y6MMVIN66RHXLUZZFTU2EMDECO.json","graph_json":"https://pith.science/api/pith-number/Y6MMVIN66RHXLUZZFTU2EMDECO/graph.json","events_json":"https://pith.science/api/pith-number/Y6MMVIN66RHXLUZZFTU2EMDECO/events.json","paper":"https://pith.science/paper/Y6MMVIN6"},"agent_actions":{"view_html":"https://pith.science/pith/Y6MMVIN66RHXLUZZFTU2EMDECO","download_json":"https://pith.science/pith/Y6MMVIN66RHXLUZZFTU2EMDECO.json","view_paper":"https://pith.science/paper/Y6MMVIN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05963&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6MMVIN66RHXLUZZFTU2EMDECO/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6MMVIN66RHXLUZZFTU2EMDECO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6MMVIN66RHXLUZZFTU2EMDECO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6MMVIN66RHXLUZZFTU2EMDECO/action/storage_attestation","attest_author":"https://pith.science/pith/Y6MMVIN66RHXLUZZFTU2EMDECO/action/author_attestation","sign_citation":"https://pith.science/pith/Y6MMVIN66RHXLUZZFTU2EMDECO/action/citation_signature","submit_replication":"https://pith.science/pith/Y6MMVIN66RHXLUZZFTU2EMDECO/action/replication_record"}},"created_at":"2026-07-05T09:17:53.796966+00:00","updated_at":"2026-07-05T09:17:53.796966+00:00"}