{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:URL37XP4DVNZUQG5MFROARUEHG","short_pith_number":"pith:URL37XP4","schema_version":"1.0","canonical_sha256":"a457bfddfc1d5b9a40dd6162e04684399ba9f1a3b314a132b2a6e2fcabaaf8ea","source":{"kind":"arxiv","id":"2405.17859","version":3},"attestation_state":"computed","paper":{"title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Jishnu Jaykumar P, Nicholas Ruozzi, Yangxiao Lu, Yunhui Guo, Yu Xiang","submitted_at":"2024-05-28T06:16:57Z","abstract_excerpt":"Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet effective framework (NIDS-Net) comprising object proposal generation, embedding creation for both instance templates and proposal regions, and embedding matching for instance label assignment. Leveraging recent advancements in large vision methods, we utilize Grounding DINO and Segment Anything Model (SAM) to obtain object proposals with accurate bounding boxes and masks. Central to our approach is the generation of hi"},"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":"2405.17859","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T06:16:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"538b4f30736b86f024d7d0690138ad9c49e2202fefc3ae8f2e01d55c10666974","abstract_canon_sha256":"6955d6819969b202b4e2cd1749c0806b02ace260846296882b66802d514c546e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:22.218580Z","signature_b64":"wj30eVhFafW79XqBgIgqq8gQghV6spU3vIggTpCKTLvE3z1QCzxMjEmvMyASu/vWU9E4ntRav6ALy+oIwtheDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a457bfddfc1d5b9a40dd6162e04684399ba9f1a3b314a132b2a6e2fcabaaf8ea","last_reissued_at":"2026-07-05T10:24:22.217817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:22.217817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Jishnu Jaykumar P, Nicholas Ruozzi, Yangxiao Lu, Yunhui Guo, Yu Xiang","submitted_at":"2024-05-28T06:16:57Z","abstract_excerpt":"Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet effective framework (NIDS-Net) comprising object proposal generation, embedding creation for both instance templates and proposal regions, and embedding matching for instance label assignment. Leveraging recent advancements in large vision methods, we utilize Grounding DINO and Segment Anything Model (SAM) to obtain object proposals with accurate bounding boxes and masks. Central to our approach is the generation of hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17859","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/2405.17859/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":"2405.17859","created_at":"2026-07-05T10:24:22.217888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17859v3","created_at":"2026-07-05T10:24:22.217888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17859","created_at":"2026-07-05T10:24:22.217888+00:00"},{"alias_kind":"pith_short_12","alias_value":"URL37XP4DVNZ","created_at":"2026-07-05T10:24:22.217888+00:00"},{"alias_kind":"pith_short_16","alias_value":"URL37XP4DVNZUQG5","created_at":"2026-07-05T10:24:22.217888+00:00"},{"alias_kind":"pith_short_8","alias_value":"URL37XP4","created_at":"2026-07-05T10:24:22.217888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12954","citing_title":"Towards Reliable Sequential Object Picking in Clutter: The Runner-up Solution to RGMC 2025","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URL37XP4DVNZUQG5MFROARUEHG","json":"https://pith.science/pith/URL37XP4DVNZUQG5MFROARUEHG.json","graph_json":"https://pith.science/api/pith-number/URL37XP4DVNZUQG5MFROARUEHG/graph.json","events_json":"https://pith.science/api/pith-number/URL37XP4DVNZUQG5MFROARUEHG/events.json","paper":"https://pith.science/paper/URL37XP4"},"agent_actions":{"view_html":"https://pith.science/pith/URL37XP4DVNZUQG5MFROARUEHG","download_json":"https://pith.science/pith/URL37XP4DVNZUQG5MFROARUEHG.json","view_paper":"https://pith.science/paper/URL37XP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17859&json=true","fetch_graph":"https://pith.science/api/pith-number/URL37XP4DVNZUQG5MFROARUEHG/graph.json","fetch_events":"https://pith.science/api/pith-number/URL37XP4DVNZUQG5MFROARUEHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URL37XP4DVNZUQG5MFROARUEHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URL37XP4DVNZUQG5MFROARUEHG/action/storage_attestation","attest_author":"https://pith.science/pith/URL37XP4DVNZUQG5MFROARUEHG/action/author_attestation","sign_citation":"https://pith.science/pith/URL37XP4DVNZUQG5MFROARUEHG/action/citation_signature","submit_replication":"https://pith.science/pith/URL37XP4DVNZUQG5MFROARUEHG/action/replication_record"}},"created_at":"2026-07-05T10:24:22.217888+00:00","updated_at":"2026-07-05T10:24:22.217888+00:00"}