{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LUYOOUC5JCCVBISNJ735ZJUII2","short_pith_number":"pith:LUYOOUC5","schema_version":"1.0","canonical_sha256":"5d30e7505d488550a24d4ff7dca68846830c9db74e2cbd7a240aa1980dfe158b","source":{"kind":"arxiv","id":"2501.15201","version":1},"attestation_state":"computed","paper":{"title":"A Training-free Synthetic Data Selection Method for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingfeng Zhang, Hao Tang, Jian Pang, Siyue Yu","submitted_at":"2025-01-25T12:53:14Z","abstract_excerpt":"Training semantic segmenter with synthetic data has been attracting great attention due to its easy accessibility and huge quantities. Most previous methods focused on producing large-scale synthetic image-annotation samples and then training the segmenter with all of them. However, such a solution remains a main challenge in that the poor-quality samples are unavoidable, and using them to train the model will damage the training process. In this paper, we propose a training-free Synthetic Data Selection (SDS) strategy with CLIP to select high-quality samples for building a reliable synthetic "},"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":"2501.15201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T12:53:14Z","cross_cats_sorted":[],"title_canon_sha256":"0e716d5d2b8ec492052a9d47a7134d640057c175c11d289a9dc5c0c447ecb9ad","abstract_canon_sha256":"0dd5234a4378e3998842b89a7e89b8b1ee2631b98a8119ffef3e126cd0130325"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:25.660837Z","signature_b64":"8mm7viboUY+s6gu117vDXJt0STuWOquNY6fSPTvkmdu9U4roMRbnuR1kno2BODs1xa7KsJ4ESzug3qKeZqsKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d30e7505d488550a24d4ff7dca68846830c9db74e2cbd7a240aa1980dfe158b","last_reissued_at":"2026-07-05T10:05:25.660359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:25.660359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Training-free Synthetic Data Selection Method for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingfeng Zhang, Hao Tang, Jian Pang, Siyue Yu","submitted_at":"2025-01-25T12:53:14Z","abstract_excerpt":"Training semantic segmenter with synthetic data has been attracting great attention due to its easy accessibility and huge quantities. Most previous methods focused on producing large-scale synthetic image-annotation samples and then training the segmenter with all of them. However, such a solution remains a main challenge in that the poor-quality samples are unavoidable, and using them to train the model will damage the training process. In this paper, we propose a training-free Synthetic Data Selection (SDS) strategy with CLIP to select high-quality samples for building a reliable synthetic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15201","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/2501.15201/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":"2501.15201","created_at":"2026-07-05T10:05:25.660415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15201v1","created_at":"2026-07-05T10:05:25.660415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15201","created_at":"2026-07-05T10:05:25.660415+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUYOOUC5JCCV","created_at":"2026-07-05T10:05:25.660415+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUYOOUC5JCCVBISN","created_at":"2026-07-05T10:05:25.660415+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUYOOUC5","created_at":"2026-07-05T10:05:25.660415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09699","citing_title":"A Real-Calibrated Synthetic-First Data Engine","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUYOOUC5JCCVBISNJ735ZJUII2","json":"https://pith.science/pith/LUYOOUC5JCCVBISNJ735ZJUII2.json","graph_json":"https://pith.science/api/pith-number/LUYOOUC5JCCVBISNJ735ZJUII2/graph.json","events_json":"https://pith.science/api/pith-number/LUYOOUC5JCCVBISNJ735ZJUII2/events.json","paper":"https://pith.science/paper/LUYOOUC5"},"agent_actions":{"view_html":"https://pith.science/pith/LUYOOUC5JCCVBISNJ735ZJUII2","download_json":"https://pith.science/pith/LUYOOUC5JCCVBISNJ735ZJUII2.json","view_paper":"https://pith.science/paper/LUYOOUC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15201&json=true","fetch_graph":"https://pith.science/api/pith-number/LUYOOUC5JCCVBISNJ735ZJUII2/graph.json","fetch_events":"https://pith.science/api/pith-number/LUYOOUC5JCCVBISNJ735ZJUII2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUYOOUC5JCCVBISNJ735ZJUII2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUYOOUC5JCCVBISNJ735ZJUII2/action/storage_attestation","attest_author":"https://pith.science/pith/LUYOOUC5JCCVBISNJ735ZJUII2/action/author_attestation","sign_citation":"https://pith.science/pith/LUYOOUC5JCCVBISNJ735ZJUII2/action/citation_signature","submit_replication":"https://pith.science/pith/LUYOOUC5JCCVBISNJ735ZJUII2/action/replication_record"}},"created_at":"2026-07-05T10:05:25.660415+00:00","updated_at":"2026-07-05T10:05:25.660415+00:00"}