{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XQVHVGZL34L7Y7ZTBZAUDM3LRK","short_pith_number":"pith:XQVHVGZL","schema_version":"1.0","canonical_sha256":"bc2a7a9b2bdf17fc7f330e4141b36b8ab5d88153ae0ef849b5a3ea24a24ea6a0","source":{"kind":"arxiv","id":"2203.09343","version":2},"attestation_state":"computed","paper":{"title":"CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hang Zhao, Renhao Wang, Yang Gao","submitted_at":"2022-03-17T14:20:05Z","abstract_excerpt":"Many recent approaches in contrastive learning have worked to close the gap between pretraining on iconic images like ImageNet and pretraining on complex scenes like COCO. This gap exists largely because commonly used random crop augmentations obtain semantically inconsistent content in crowded scene images of diverse objects. Previous works use preprocessing pipelines to localize salient objects for improved cropping, but an end-to-end solution is still elusive. In this work, we propose a framework which accomplishes this goal via joint learning of representations and segmentation. We leverag"},"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":"2203.09343","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-17T14:20:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"53e30175cc68bfed22b01c6d781e2de19b30f81d43cf423756f10ffa7a095f1e","abstract_canon_sha256":"d70cc7da7580683126fd15dae70742fc9a5b17d22d7eabe24dca5832a9bede23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:44.600525Z","signature_b64":"P2YAScqxM1eE2yNE5rlEXfCxde3RKnQ5/a6wd66ZvIJJVALmbyGC54e1QpkWQEN7NyBzFWgyrStucd41cRDLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc2a7a9b2bdf17fc7f330e4141b36b8ab5d88153ae0ef849b5a3ea24a24ea6a0","last_reissued_at":"2026-07-05T04:48:44.600061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:44.600061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hang Zhao, Renhao Wang, Yang Gao","submitted_at":"2022-03-17T14:20:05Z","abstract_excerpt":"Many recent approaches in contrastive learning have worked to close the gap between pretraining on iconic images like ImageNet and pretraining on complex scenes like COCO. This gap exists largely because commonly used random crop augmentations obtain semantically inconsistent content in crowded scene images of diverse objects. Previous works use preprocessing pipelines to localize salient objects for improved cropping, but an end-to-end solution is still elusive. In this work, we propose a framework which accomplishes this goal via joint learning of representations and segmentation. We leverag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09343","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/2203.09343/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":"2203.09343","created_at":"2026-07-05T04:48:44.600121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09343v2","created_at":"2026-07-05T04:48:44.600121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09343","created_at":"2026-07-05T04:48:44.600121+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQVHVGZL34L7","created_at":"2026-07-05T04:48:44.600121+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQVHVGZL34L7Y7ZT","created_at":"2026-07-05T04:48:44.600121+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQVHVGZL","created_at":"2026-07-05T04:48:44.600121+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/XQVHVGZL34L7Y7ZTBZAUDM3LRK","json":"https://pith.science/pith/XQVHVGZL34L7Y7ZTBZAUDM3LRK.json","graph_json":"https://pith.science/api/pith-number/XQVHVGZL34L7Y7ZTBZAUDM3LRK/graph.json","events_json":"https://pith.science/api/pith-number/XQVHVGZL34L7Y7ZTBZAUDM3LRK/events.json","paper":"https://pith.science/paper/XQVHVGZL"},"agent_actions":{"view_html":"https://pith.science/pith/XQVHVGZL34L7Y7ZTBZAUDM3LRK","download_json":"https://pith.science/pith/XQVHVGZL34L7Y7ZTBZAUDM3LRK.json","view_paper":"https://pith.science/paper/XQVHVGZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09343&json=true","fetch_graph":"https://pith.science/api/pith-number/XQVHVGZL34L7Y7ZTBZAUDM3LRK/graph.json","fetch_events":"https://pith.science/api/pith-number/XQVHVGZL34L7Y7ZTBZAUDM3LRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQVHVGZL34L7Y7ZTBZAUDM3LRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQVHVGZL34L7Y7ZTBZAUDM3LRK/action/storage_attestation","attest_author":"https://pith.science/pith/XQVHVGZL34L7Y7ZTBZAUDM3LRK/action/author_attestation","sign_citation":"https://pith.science/pith/XQVHVGZL34L7Y7ZTBZAUDM3LRK/action/citation_signature","submit_replication":"https://pith.science/pith/XQVHVGZL34L7Y7ZTBZAUDM3LRK/action/replication_record"}},"created_at":"2026-07-05T04:48:44.600121+00:00","updated_at":"2026-07-05T04:48:44.600121+00:00"}