{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XJOBPDZMMZANKAN3KQUBBJDOKL","short_pith_number":"pith:XJOBPDZM","schema_version":"1.0","canonical_sha256":"ba5c178f2c6640d501bb542810a46e52ec62df5f0540dd8591bb9e0be523beea","source":{"kind":"arxiv","id":"2212.06486","version":1},"attestation_state":"computed","paper":{"title":"Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jin Xie, Kaiyou Song, Shan Zhang, Tong Wang, Zihao An, Zimeng Luo","submitted_at":"2022-12-13T11:13:59Z","abstract_excerpt":"In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented \"views\" of the same image closer while pushing all other images further apart, which has been proven to be effective. However, it is unavoidable to construct undesirable views containing different semantic concepts during the augmentation procedure. It would damage the semantic consistency of representation to pull these augmentations closer in the feature space indiscriminately. In this study, we introduce feature-level augmentation and propose a novel semantics-consis"},"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":"2212.06486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-13T11:13:59Z","cross_cats_sorted":[],"title_canon_sha256":"88398ca42e1fb5bfc94a81c76756740a2c2a9e914cafb6ade8e06ce2d15b969f","abstract_canon_sha256":"3ee5c317f7202e87a1139c3748a405fea55579ddac8e4e9599f10472ad3deaa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:50.878591Z","signature_b64":"dODI97+VtoD4chi5y6a5jI37lj7+u3InvQ+85TGDa/AVE/SBFLSwBn/Lbd3CmJ4WuTHKtsUAyNbXTDZSOMUCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba5c178f2c6640d501bb542810a46e52ec62df5f0540dd8591bb9e0be523beea","last_reissued_at":"2026-07-05T05:24:50.878206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:50.878206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jin Xie, Kaiyou Song, Shan Zhang, Tong Wang, Zihao An, Zimeng Luo","submitted_at":"2022-12-13T11:13:59Z","abstract_excerpt":"In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented \"views\" of the same image closer while pushing all other images further apart, which has been proven to be effective. However, it is unavoidable to construct undesirable views containing different semantic concepts during the augmentation procedure. It would damage the semantic consistency of representation to pull these augmentations closer in the feature space indiscriminately. In this study, we introduce feature-level augmentation and propose a novel semantics-consis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06486","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/2212.06486/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":"2212.06486","created_at":"2026-07-05T05:24:50.878261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.06486v1","created_at":"2026-07-05T05:24:50.878261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06486","created_at":"2026-07-05T05:24:50.878261+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJOBPDZMMZAN","created_at":"2026-07-05T05:24:50.878261+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJOBPDZMMZANKAN3","created_at":"2026-07-05T05:24:50.878261+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJOBPDZM","created_at":"2026-07-05T05:24:50.878261+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/XJOBPDZMMZANKAN3KQUBBJDOKL","json":"https://pith.science/pith/XJOBPDZMMZANKAN3KQUBBJDOKL.json","graph_json":"https://pith.science/api/pith-number/XJOBPDZMMZANKAN3KQUBBJDOKL/graph.json","events_json":"https://pith.science/api/pith-number/XJOBPDZMMZANKAN3KQUBBJDOKL/events.json","paper":"https://pith.science/paper/XJOBPDZM"},"agent_actions":{"view_html":"https://pith.science/pith/XJOBPDZMMZANKAN3KQUBBJDOKL","download_json":"https://pith.science/pith/XJOBPDZMMZANKAN3KQUBBJDOKL.json","view_paper":"https://pith.science/paper/XJOBPDZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.06486&json=true","fetch_graph":"https://pith.science/api/pith-number/XJOBPDZMMZANKAN3KQUBBJDOKL/graph.json","fetch_events":"https://pith.science/api/pith-number/XJOBPDZMMZANKAN3KQUBBJDOKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJOBPDZMMZANKAN3KQUBBJDOKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJOBPDZMMZANKAN3KQUBBJDOKL/action/storage_attestation","attest_author":"https://pith.science/pith/XJOBPDZMMZANKAN3KQUBBJDOKL/action/author_attestation","sign_citation":"https://pith.science/pith/XJOBPDZMMZANKAN3KQUBBJDOKL/action/citation_signature","submit_replication":"https://pith.science/pith/XJOBPDZMMZANKAN3KQUBBJDOKL/action/replication_record"}},"created_at":"2026-07-05T05:24:50.878261+00:00","updated_at":"2026-07-05T05:24:50.878261+00:00"}