{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M2L4IGU6LO7N7ZUCYHHMDQI2BA","short_pith_number":"pith:M2L4IGU6","schema_version":"1.0","canonical_sha256":"6697c41a9e5bbedfe682c1cec1c11a08273697b03faefa643b904de60205639b","source":{"kind":"arxiv","id":"2209.06993","version":2},"attestation_state":"computed","paper":{"title":"Learning from Future: A Novel Self-Training Framework for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Jingjing Fei, Liwei Wu, Qingjie Liu, Rui Zhao, Wei Li, Ye Du, Yujun Shen, Zehua Fu","submitted_at":"2022-09-15T01:39:46Z","abstract_excerpt":"Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active attempts typically employ a momentum teacher for pseudo-label prediction yet observe the confirmation bias issue, where the incorrect predictions may provide wrong supervision signals and get accumulated in the training process. The primary cause of such a drawback is that the prevailing self-training framework acts as guiding the current state with previous k"},"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":"2209.06993","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-15T01:39:46Z","cross_cats_sorted":[],"title_canon_sha256":"f1465b796b709ad8fa50a2c0422dfe36e8463c60e9271469cfbe30d74408b7c4","abstract_canon_sha256":"8ed4e313d61fca4eb861935d521733889c42354d359bf3e6c1d362593c1f7a85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:39.700907Z","signature_b64":"kN/41TiE4I664/JJh8Ih38lHGziwrp1gwpHbpxsyKAMP4KilRcgAbiX/Rwdw6fNvA7C/b+8idBAxWl3SmxruBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6697c41a9e5bbedfe682c1cec1c11a08273697b03faefa643b904de60205639b","last_reissued_at":"2026-07-05T04:58:39.700494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:39.700494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Future: A Novel Self-Training Framework for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Jingjing Fei, Liwei Wu, Qingjie Liu, Rui Zhao, Wei Li, Ye Du, Yujun Shen, Zehua Fu","submitted_at":"2022-09-15T01:39:46Z","abstract_excerpt":"Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active attempts typically employ a momentum teacher for pseudo-label prediction yet observe the confirmation bias issue, where the incorrect predictions may provide wrong supervision signals and get accumulated in the training process. The primary cause of such a drawback is that the prevailing self-training framework acts as guiding the current state with previous k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06993","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/2209.06993/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":"2209.06993","created_at":"2026-07-05T04:58:39.700549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.06993v2","created_at":"2026-07-05T04:58:39.700549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06993","created_at":"2026-07-05T04:58:39.700549+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2L4IGU6LO7N","created_at":"2026-07-05T04:58:39.700549+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2L4IGU6LO7N7ZUC","created_at":"2026-07-05T04:58:39.700549+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2L4IGU6","created_at":"2026-07-05T04:58:39.700549+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/M2L4IGU6LO7N7ZUCYHHMDQI2BA","json":"https://pith.science/pith/M2L4IGU6LO7N7ZUCYHHMDQI2BA.json","graph_json":"https://pith.science/api/pith-number/M2L4IGU6LO7N7ZUCYHHMDQI2BA/graph.json","events_json":"https://pith.science/api/pith-number/M2L4IGU6LO7N7ZUCYHHMDQI2BA/events.json","paper":"https://pith.science/paper/M2L4IGU6"},"agent_actions":{"view_html":"https://pith.science/pith/M2L4IGU6LO7N7ZUCYHHMDQI2BA","download_json":"https://pith.science/pith/M2L4IGU6LO7N7ZUCYHHMDQI2BA.json","view_paper":"https://pith.science/paper/M2L4IGU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.06993&json=true","fetch_graph":"https://pith.science/api/pith-number/M2L4IGU6LO7N7ZUCYHHMDQI2BA/graph.json","fetch_events":"https://pith.science/api/pith-number/M2L4IGU6LO7N7ZUCYHHMDQI2BA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2L4IGU6LO7N7ZUCYHHMDQI2BA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2L4IGU6LO7N7ZUCYHHMDQI2BA/action/storage_attestation","attest_author":"https://pith.science/pith/M2L4IGU6LO7N7ZUCYHHMDQI2BA/action/author_attestation","sign_citation":"https://pith.science/pith/M2L4IGU6LO7N7ZUCYHHMDQI2BA/action/citation_signature","submit_replication":"https://pith.science/pith/M2L4IGU6LO7N7ZUCYHHMDQI2BA/action/replication_record"}},"created_at":"2026-07-05T04:58:39.700549+00:00","updated_at":"2026-07-05T04:58:39.700549+00:00"}