{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XOBTWZ6SFPZL6T3U3S7Y3P27NT","short_pith_number":"pith:XOBTWZ6S","schema_version":"1.0","canonical_sha256":"bb833b67d22bf2bf4f74dcbf8dbf5f6cf015accf41390aa46ae636e509a1074e","source":{"kind":"arxiv","id":"2212.04227","version":2},"attestation_state":"computed","paper":{"title":"Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ibrahim Batuhan Akkaya, Ugur Halici","submitted_at":"2022-12-08T12:20:35Z","abstract_excerpt":"Unsupervised source-free domain adaptation methods aim to train a model for the target domain utilizing a pretrained source-domain model and unlabeled target-domain data, particularly when accessibility to source data is restricted due to intellectual property or privacy concerns. Traditional methods usually use self-training with pseudo-labeling, which is often subjected to thresholding based on prediction confidence. However, such thresholding limits the effectiveness of self-training due to insufficient supervision. This issue becomes more severe in a source-free setting, where supervision "},"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":"2212.04227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T12:20:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e4c5e289c1e30b835fdc899e62ec345830ebfdab77a32f9fdf0d9f56be9a4a81","abstract_canon_sha256":"df65912698d2b9e1e2f2e5dabdb62a2412310823bdcb7c8cccb3a12dbfab7ce4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:47.438074Z","signature_b64":"58trsDS7ygYcqPlkycuAnGPHwSPxwRSbh46lNqkQLFIFm8WRUJ2U3bBedMY4mUVrZnfLTpafooRT5w7nr1bLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb833b67d22bf2bf4f74dcbf8dbf5f6cf015accf41390aa46ae636e509a1074e","last_reissued_at":"2026-07-05T08:05:47.437601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:47.437601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ibrahim Batuhan Akkaya, Ugur Halici","submitted_at":"2022-12-08T12:20:35Z","abstract_excerpt":"Unsupervised source-free domain adaptation methods aim to train a model for the target domain utilizing a pretrained source-domain model and unlabeled target-domain data, particularly when accessibility to source data is restricted due to intellectual property or privacy concerns. Traditional methods usually use self-training with pseudo-labeling, which is often subjected to thresholding based on prediction confidence. However, such thresholding limits the effectiveness of self-training due to insufficient supervision. This issue becomes more severe in a source-free setting, where supervision "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04227","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/2212.04227/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":"2212.04227","created_at":"2026-07-05T08:05:47.437661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04227v2","created_at":"2026-07-05T08:05:47.437661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04227","created_at":"2026-07-05T08:05:47.437661+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOBTWZ6SFPZL","created_at":"2026-07-05T08:05:47.437661+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOBTWZ6SFPZL6T3U","created_at":"2026-07-05T08:05:47.437661+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOBTWZ6S","created_at":"2026-07-05T08:05:47.437661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21198","citing_title":"Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOBTWZ6SFPZL6T3U3S7Y3P27NT","json":"https://pith.science/pith/XOBTWZ6SFPZL6T3U3S7Y3P27NT.json","graph_json":"https://pith.science/api/pith-number/XOBTWZ6SFPZL6T3U3S7Y3P27NT/graph.json","events_json":"https://pith.science/api/pith-number/XOBTWZ6SFPZL6T3U3S7Y3P27NT/events.json","paper":"https://pith.science/paper/XOBTWZ6S"},"agent_actions":{"view_html":"https://pith.science/pith/XOBTWZ6SFPZL6T3U3S7Y3P27NT","download_json":"https://pith.science/pith/XOBTWZ6SFPZL6T3U3S7Y3P27NT.json","view_paper":"https://pith.science/paper/XOBTWZ6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04227&json=true","fetch_graph":"https://pith.science/api/pith-number/XOBTWZ6SFPZL6T3U3S7Y3P27NT/graph.json","fetch_events":"https://pith.science/api/pith-number/XOBTWZ6SFPZL6T3U3S7Y3P27NT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOBTWZ6SFPZL6T3U3S7Y3P27NT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOBTWZ6SFPZL6T3U3S7Y3P27NT/action/storage_attestation","attest_author":"https://pith.science/pith/XOBTWZ6SFPZL6T3U3S7Y3P27NT/action/author_attestation","sign_citation":"https://pith.science/pith/XOBTWZ6SFPZL6T3U3S7Y3P27NT/action/citation_signature","submit_replication":"https://pith.science/pith/XOBTWZ6SFPZL6T3U3S7Y3P27NT/action/replication_record"}},"created_at":"2026-07-05T08:05:47.437661+00:00","updated_at":"2026-07-05T08:05:47.437661+00:00"}