{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HHXGPAYCUS33T7UYJ65NFBMPCX","short_pith_number":"pith:HHXGPAYC","schema_version":"1.0","canonical_sha256":"39ee678302a4b7b9fe984fbad2858f15f2bc4fb56968413cc292a9fdd2ce4e62","source":{"kind":"arxiv","id":"2411.16319","version":3},"attestation_state":"computed","paper":{"title":"CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dominik Engel, Leon Sick, Pedro Hermosilla, Sebastian Hartwig, Timo Ropinski","submitted_at":"2024-11-25T12:11:27Z","abstract_excerpt":"Traditionally, algorithms that learn to segment object instances in 2D images have heavily relied on large amounts of human-annotated data. Only recently, novel approaches have emerged tackling this problem in an unsupervised fashion. Generally, these approaches first generate pseudo-masks and then train a class-agnostic detector. While such methods deliver the current state of the art, they often fail to correctly separate instances overlapping in 2D image space since only semantics are considered. To tackle this issue, we instead propose to cut the semantic masks in 3D to obtain the final 2D"},"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":"2411.16319","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T12:11:27Z","cross_cats_sorted":[],"title_canon_sha256":"dbff22f95892a1bf416154f28d452a879c29098e890549b6405b3484391d6eba","abstract_canon_sha256":"70699db155e07ba0cba8b2f2fea5aeb465b000a2f3e5e2078b050e9ef9a6e83e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:24.364580Z","signature_b64":"MfEQdTHtmYKpUj757PmPRPY9XjJRHxJrxF4hv2VwivY5z5EdvccXqcdGVNMzZ7OBLD4oeHbqr63N52yS3Cg6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39ee678302a4b7b9fe984fbad2858f15f2bc4fb56968413cc292a9fdd2ce4e62","last_reissued_at":"2026-07-05T11:42:24.364101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:24.364101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dominik Engel, Leon Sick, Pedro Hermosilla, Sebastian Hartwig, Timo Ropinski","submitted_at":"2024-11-25T12:11:27Z","abstract_excerpt":"Traditionally, algorithms that learn to segment object instances in 2D images have heavily relied on large amounts of human-annotated data. Only recently, novel approaches have emerged tackling this problem in an unsupervised fashion. Generally, these approaches first generate pseudo-masks and then train a class-agnostic detector. While such methods deliver the current state of the art, they often fail to correctly separate instances overlapping in 2D image space since only semantics are considered. To tackle this issue, we instead propose to cut the semantic masks in 3D to obtain the final 2D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16319","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/2411.16319/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":"2411.16319","created_at":"2026-07-05T11:42:24.364162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16319v3","created_at":"2026-07-05T11:42:24.364162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16319","created_at":"2026-07-05T11:42:24.364162+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHXGPAYCUS33","created_at":"2026-07-05T11:42:24.364162+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHXGPAYCUS33T7UY","created_at":"2026-07-05T11:42:24.364162+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHXGPAYC","created_at":"2026-07-05T11:42:24.364162+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/HHXGPAYCUS33T7UYJ65NFBMPCX","json":"https://pith.science/pith/HHXGPAYCUS33T7UYJ65NFBMPCX.json","graph_json":"https://pith.science/api/pith-number/HHXGPAYCUS33T7UYJ65NFBMPCX/graph.json","events_json":"https://pith.science/api/pith-number/HHXGPAYCUS33T7UYJ65NFBMPCX/events.json","paper":"https://pith.science/paper/HHXGPAYC"},"agent_actions":{"view_html":"https://pith.science/pith/HHXGPAYCUS33T7UYJ65NFBMPCX","download_json":"https://pith.science/pith/HHXGPAYCUS33T7UYJ65NFBMPCX.json","view_paper":"https://pith.science/paper/HHXGPAYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16319&json=true","fetch_graph":"https://pith.science/api/pith-number/HHXGPAYCUS33T7UYJ65NFBMPCX/graph.json","fetch_events":"https://pith.science/api/pith-number/HHXGPAYCUS33T7UYJ65NFBMPCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHXGPAYCUS33T7UYJ65NFBMPCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHXGPAYCUS33T7UYJ65NFBMPCX/action/storage_attestation","attest_author":"https://pith.science/pith/HHXGPAYCUS33T7UYJ65NFBMPCX/action/author_attestation","sign_citation":"https://pith.science/pith/HHXGPAYCUS33T7UYJ65NFBMPCX/action/citation_signature","submit_replication":"https://pith.science/pith/HHXGPAYCUS33T7UYJ65NFBMPCX/action/replication_record"}},"created_at":"2026-07-05T11:42:24.364162+00:00","updated_at":"2026-07-05T11:42:24.364162+00:00"}