{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UBBZUYMGRKYLUQUR72GUUMIH7R","short_pith_number":"pith:UBBZUYMG","schema_version":"1.0","canonical_sha256":"a0439a61868ab0ba4291fe8d4a3107fc79078f3b1406f9a156ba2744373bed57","source":{"kind":"arxiv","id":"2105.00957","version":2},"attestation_state":"computed","paper":{"title":"Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jyh-Jing Hwang, Stella X. Yu, Tsung-Wei Ke","submitted_at":"2021-05-03T15:49:01Z","abstract_excerpt":"Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles. This task is challenging, as coarse annotations (tags, boxes) lack precise pixel localization whereas sparse annotations (points, scribbles) lack broad region coverage. Existing methods tackle these two types of weak supervision differently: Class activation maps are used to localize coarse labels and iteratively refine the segmentation model, whereas conditional random fields are used to pro"},"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":"2105.00957","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-03T15:49:01Z","cross_cats_sorted":[],"title_canon_sha256":"8665b45dcac4b82bbf3376ad5b28ee4f7f9b003a77cff86e1687595156c194c0","abstract_canon_sha256":"627c95cac00a8538d581ea3dfca4271e006ee5c6eb70dfc0fa170365a34bf418"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:20.503002Z","signature_b64":"FVcq9QrS8AlQ8iGlZu01J2JlcAbCMRnCO6qS2ytZCYicOX6Z0/Rmr5pTm2Qxc4pKYE0BQUPRhFSXowfTdnv7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0439a61868ab0ba4291fe8d4a3107fc79078f3b1406f9a156ba2744373bed57","last_reissued_at":"2026-07-05T02:39:20.502552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:20.502552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jyh-Jing Hwang, Stella X. Yu, Tsung-Wei Ke","submitted_at":"2021-05-03T15:49:01Z","abstract_excerpt":"Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles. This task is challenging, as coarse annotations (tags, boxes) lack precise pixel localization whereas sparse annotations (points, scribbles) lack broad region coverage. Existing methods tackle these two types of weak supervision differently: Class activation maps are used to localize coarse labels and iteratively refine the segmentation model, whereas conditional random fields are used to pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00957","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/2105.00957/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":"2105.00957","created_at":"2026-07-05T02:39:20.502612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.00957v2","created_at":"2026-07-05T02:39:20.502612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00957","created_at":"2026-07-05T02:39:20.502612+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBBZUYMGRKYL","created_at":"2026-07-05T02:39:20.502612+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBBZUYMGRKYLUQUR","created_at":"2026-07-05T02:39:20.502612+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBBZUYMG","created_at":"2026-07-05T02:39:20.502612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01721","citing_title":"Soft Self-labeling and Potts Relaxations for Weakly-Supervised Segmentation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBBZUYMGRKYLUQUR72GUUMIH7R","json":"https://pith.science/pith/UBBZUYMGRKYLUQUR72GUUMIH7R.json","graph_json":"https://pith.science/api/pith-number/UBBZUYMGRKYLUQUR72GUUMIH7R/graph.json","events_json":"https://pith.science/api/pith-number/UBBZUYMGRKYLUQUR72GUUMIH7R/events.json","paper":"https://pith.science/paper/UBBZUYMG"},"agent_actions":{"view_html":"https://pith.science/pith/UBBZUYMGRKYLUQUR72GUUMIH7R","download_json":"https://pith.science/pith/UBBZUYMGRKYLUQUR72GUUMIH7R.json","view_paper":"https://pith.science/paper/UBBZUYMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.00957&json=true","fetch_graph":"https://pith.science/api/pith-number/UBBZUYMGRKYLUQUR72GUUMIH7R/graph.json","fetch_events":"https://pith.science/api/pith-number/UBBZUYMGRKYLUQUR72GUUMIH7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBBZUYMGRKYLUQUR72GUUMIH7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBBZUYMGRKYLUQUR72GUUMIH7R/action/storage_attestation","attest_author":"https://pith.science/pith/UBBZUYMGRKYLUQUR72GUUMIH7R/action/author_attestation","sign_citation":"https://pith.science/pith/UBBZUYMGRKYLUQUR72GUUMIH7R/action/citation_signature","submit_replication":"https://pith.science/pith/UBBZUYMGRKYLUQUR72GUUMIH7R/action/replication_record"}},"created_at":"2026-07-05T02:39:20.502612+00:00","updated_at":"2026-07-05T02:39:20.502612+00:00"}