{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HNIWDXFBNMXJUGNK3XOXSSHY7X","short_pith_number":"pith:HNIWDXFB","schema_version":"1.0","canonical_sha256":"3b5161dca16b2e9a19aadddd7948f8fdfa94d71e6d6865944d1597630a0abce1","source":{"kind":"arxiv","id":"2504.16692","version":1},"attestation_state":"computed","paper":{"title":"Energy-Based Pseudo-Label Refining for Source-free Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Sun, Huiyu Zhou, Jiamei Liu, Ningzhong Liu, Xinru Meng","submitted_at":"2025-04-23T13:26:58Z","abstract_excerpt":"Source-free domain adaptation (SFDA), which involves adapting models without access to source data, is both demanding and challenging. Existing SFDA techniques typically rely on pseudo-labels generated from confidence levels, leading to negative transfer due to significant noise. To tackle this problem, Energy-Based Pseudo-Label Refining (EBPR) is proposed for SFDA. Pseudo-labels are created for all sample clusters according to their energy scores. Global and class energy thresholds are computed to selectively filter pseudo-labels. Furthermore, a contrastive learning strategy is introduced to "},"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":"2504.16692","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-23T13:26:58Z","cross_cats_sorted":[],"title_canon_sha256":"0217a4deabf59f15c94123b7121ef2a71de0008f6e951f1ba001bd7b42388e9c","abstract_canon_sha256":"4d058646362c6103d1143a7f627022d60f66d07d517328cf447a4ed04e88ce56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:03.337283Z","signature_b64":"OUawz8jke2AGzPDh+LaSBdGxhZwbssQPHWsNKVdZC68B5ayEgfYpx3XEbwJLZMXHV+g7F5Cno5XIqz2kca0tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b5161dca16b2e9a19aadddd7948f8fdfa94d71e6d6865944d1597630a0abce1","last_reissued_at":"2026-07-05T10:53:03.336787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:03.336787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-Based Pseudo-Label Refining for Source-free Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Sun, Huiyu Zhou, Jiamei Liu, Ningzhong Liu, Xinru Meng","submitted_at":"2025-04-23T13:26:58Z","abstract_excerpt":"Source-free domain adaptation (SFDA), which involves adapting models without access to source data, is both demanding and challenging. Existing SFDA techniques typically rely on pseudo-labels generated from confidence levels, leading to negative transfer due to significant noise. To tackle this problem, Energy-Based Pseudo-Label Refining (EBPR) is proposed for SFDA. Pseudo-labels are created for all sample clusters according to their energy scores. Global and class energy thresholds are computed to selectively filter pseudo-labels. Furthermore, a contrastive learning strategy is introduced to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16692","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/2504.16692/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":"2504.16692","created_at":"2026-07-05T10:53:03.336849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16692v1","created_at":"2026-07-05T10:53:03.336849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16692","created_at":"2026-07-05T10:53:03.336849+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNIWDXFBNMXJ","created_at":"2026-07-05T10:53:03.336849+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNIWDXFBNMXJUGNK","created_at":"2026-07-05T10:53:03.336849+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNIWDXFB","created_at":"2026-07-05T10:53:03.336849+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/HNIWDXFBNMXJUGNK3XOXSSHY7X","json":"https://pith.science/pith/HNIWDXFBNMXJUGNK3XOXSSHY7X.json","graph_json":"https://pith.science/api/pith-number/HNIWDXFBNMXJUGNK3XOXSSHY7X/graph.json","events_json":"https://pith.science/api/pith-number/HNIWDXFBNMXJUGNK3XOXSSHY7X/events.json","paper":"https://pith.science/paper/HNIWDXFB"},"agent_actions":{"view_html":"https://pith.science/pith/HNIWDXFBNMXJUGNK3XOXSSHY7X","download_json":"https://pith.science/pith/HNIWDXFBNMXJUGNK3XOXSSHY7X.json","view_paper":"https://pith.science/paper/HNIWDXFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16692&json=true","fetch_graph":"https://pith.science/api/pith-number/HNIWDXFBNMXJUGNK3XOXSSHY7X/graph.json","fetch_events":"https://pith.science/api/pith-number/HNIWDXFBNMXJUGNK3XOXSSHY7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNIWDXFBNMXJUGNK3XOXSSHY7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNIWDXFBNMXJUGNK3XOXSSHY7X/action/storage_attestation","attest_author":"https://pith.science/pith/HNIWDXFBNMXJUGNK3XOXSSHY7X/action/author_attestation","sign_citation":"https://pith.science/pith/HNIWDXFBNMXJUGNK3XOXSSHY7X/action/citation_signature","submit_replication":"https://pith.science/pith/HNIWDXFBNMXJUGNK3XOXSSHY7X/action/replication_record"}},"created_at":"2026-07-05T10:53:03.336849+00:00","updated_at":"2026-07-05T10:53:03.336849+00:00"}