{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AHDF4BYXC6CKXPY5HKOHM3GSD7","short_pith_number":"pith:AHDF4BYX","schema_version":"1.0","canonical_sha256":"01c65e07171784abbf1d3a9c766cd21fcfacf018a75982ee30981f58e0a0d1cc","source":{"kind":"arxiv","id":"2507.01721","version":1},"attestation_state":"computed","paper":{"title":"Soft Self-labeling and Potts Relaxations for Weakly-Supervised Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yuri Boykov, Zhongwen Zhang","submitted_at":"2025-07-02T13:52:34Z","abstract_excerpt":"We consider weakly supervised segmentation where only a fraction of pixels have ground truth labels (scribbles) and focus on a self-labeling approach optimizing relaxations of the standard unsupervised CRF/Potts loss on unlabeled pixels. While WSSS methods can directly optimize such losses via gradient descent, prior work suggests that higher-order optimization can improve network training by introducing hidden pseudo-labels and powerful CRF sub-problem solvers, e.g. graph cut. However, previously used hard pseudo-labels can not represent class uncertainty or errors, which motivates soft self-"},"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":"2507.01721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T13:52:34Z","cross_cats_sorted":[],"title_canon_sha256":"b80f34e1bc498ac3b81e0b915a7fd00e685612f66cd79d7ec518b67828cdaa4f","abstract_canon_sha256":"97b20264dac468f7bff9204ae66bfd7818c5aec0cc3e2f5365bdffc51ac33fb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:54.049272Z","signature_b64":"yFoufshXehrXt5SmXPztVyoXRZQ51GIHLRMgd7xCUSVqlqpCFClPiMmLAXdcz1tBFHc0ofxyQmyBQiCAxmxWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01c65e07171784abbf1d3a9c766cd21fcfacf018a75982ee30981f58e0a0d1cc","last_reissued_at":"2026-07-05T11:30:54.048819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:54.048819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft Self-labeling and Potts Relaxations for Weakly-Supervised Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yuri Boykov, Zhongwen Zhang","submitted_at":"2025-07-02T13:52:34Z","abstract_excerpt":"We consider weakly supervised segmentation where only a fraction of pixels have ground truth labels (scribbles) and focus on a self-labeling approach optimizing relaxations of the standard unsupervised CRF/Potts loss on unlabeled pixels. While WSSS methods can directly optimize such losses via gradient descent, prior work suggests that higher-order optimization can improve network training by introducing hidden pseudo-labels and powerful CRF sub-problem solvers, e.g. graph cut. However, previously used hard pseudo-labels can not represent class uncertainty or errors, which motivates soft self-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01721","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/2507.01721/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":"2507.01721","created_at":"2026-07-05T11:30:54.048872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01721v1","created_at":"2026-07-05T11:30:54.048872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01721","created_at":"2026-07-05T11:30:54.048872+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHDF4BYXC6CK","created_at":"2026-07-05T11:30:54.048872+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHDF4BYXC6CKXPY5","created_at":"2026-07-05T11:30:54.048872+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHDF4BYX","created_at":"2026-07-05T11:30:54.048872+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/AHDF4BYXC6CKXPY5HKOHM3GSD7","json":"https://pith.science/pith/AHDF4BYXC6CKXPY5HKOHM3GSD7.json","graph_json":"https://pith.science/api/pith-number/AHDF4BYXC6CKXPY5HKOHM3GSD7/graph.json","events_json":"https://pith.science/api/pith-number/AHDF4BYXC6CKXPY5HKOHM3GSD7/events.json","paper":"https://pith.science/paper/AHDF4BYX"},"agent_actions":{"view_html":"https://pith.science/pith/AHDF4BYXC6CKXPY5HKOHM3GSD7","download_json":"https://pith.science/pith/AHDF4BYXC6CKXPY5HKOHM3GSD7.json","view_paper":"https://pith.science/paper/AHDF4BYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01721&json=true","fetch_graph":"https://pith.science/api/pith-number/AHDF4BYXC6CKXPY5HKOHM3GSD7/graph.json","fetch_events":"https://pith.science/api/pith-number/AHDF4BYXC6CKXPY5HKOHM3GSD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHDF4BYXC6CKXPY5HKOHM3GSD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHDF4BYXC6CKXPY5HKOHM3GSD7/action/storage_attestation","attest_author":"https://pith.science/pith/AHDF4BYXC6CKXPY5HKOHM3GSD7/action/author_attestation","sign_citation":"https://pith.science/pith/AHDF4BYXC6CKXPY5HKOHM3GSD7/action/citation_signature","submit_replication":"https://pith.science/pith/AHDF4BYXC6CKXPY5HKOHM3GSD7/action/replication_record"}},"created_at":"2026-07-05T11:30:54.048872+00:00","updated_at":"2026-07-05T11:30:54.048872+00:00"}