{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5PCY2EMFBT47AA5SSUPEJFK25C","short_pith_number":"pith:5PCY2EMF","schema_version":"1.0","canonical_sha256":"ebc58d11850cf9f003b2951e44955ae8a845ffaa53e3fc5e04dc74f3c6ad8722","source":{"kind":"arxiv","id":"2201.01922","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Neighborhood Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Luis Goncalves, Pengkai Zhu, Stefano Soatto, Vijay Mahadevan, Yuanjun Xiong, Zhaowei Cai, Zhuowen Tu","submitted_at":"2022-01-06T04:58:31Z","abstract_excerpt":"We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to neighbors by the target (student) model. The target model aims to mimic the local structure of the source representation space using a contrastive loss. CNA is an unsupervised learning algorithm that does not require ground-truth labels for the individual samples. CNA is illustrated in three scenarios: manifold learning, where the model maintains the local top"},"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":"2201.01922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-06T04:58:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8c7ff3fa9c6c6e1316c120b88f8b33745f70bdd093408c925615364cdf2bc263","abstract_canon_sha256":"ba41d01d9c1b6ea1fbd31104fe3b2843f4fd013a1e37c48260774d4e6a19ff10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:28.050111Z","signature_b64":"O0cJtp9WEKAYLkJbvV+KP4IB+B3skjbPbzCcr+DKZQ9MBtCIZqTXWYSPqxtGjB+pQ/jf+OcnC6E0Gjj8cMIPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebc58d11850cf9f003b2951e44955ae8a845ffaa53e3fc5e04dc74f3c6ad8722","last_reissued_at":"2026-07-05T03:46:28.049585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:28.049585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Neighborhood Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Luis Goncalves, Pengkai Zhu, Stefano Soatto, Vijay Mahadevan, Yuanjun Xiong, Zhaowei Cai, Zhuowen Tu","submitted_at":"2022-01-06T04:58:31Z","abstract_excerpt":"We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to neighbors by the target (student) model. The target model aims to mimic the local structure of the source representation space using a contrastive loss. CNA is an unsupervised learning algorithm that does not require ground-truth labels for the individual samples. CNA is illustrated in three scenarios: manifold learning, where the model maintains the local top"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01922","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/2201.01922/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":"2201.01922","created_at":"2026-07-05T03:46:28.049647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.01922v1","created_at":"2026-07-05T03:46:28.049647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01922","created_at":"2026-07-05T03:46:28.049647+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PCY2EMFBT47","created_at":"2026-07-05T03:46:28.049647+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PCY2EMFBT47AA5S","created_at":"2026-07-05T03:46:28.049647+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PCY2EMF","created_at":"2026-07-05T03:46:28.049647+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/5PCY2EMFBT47AA5SSUPEJFK25C","json":"https://pith.science/pith/5PCY2EMFBT47AA5SSUPEJFK25C.json","graph_json":"https://pith.science/api/pith-number/5PCY2EMFBT47AA5SSUPEJFK25C/graph.json","events_json":"https://pith.science/api/pith-number/5PCY2EMFBT47AA5SSUPEJFK25C/events.json","paper":"https://pith.science/paper/5PCY2EMF"},"agent_actions":{"view_html":"https://pith.science/pith/5PCY2EMFBT47AA5SSUPEJFK25C","download_json":"https://pith.science/pith/5PCY2EMFBT47AA5SSUPEJFK25C.json","view_paper":"https://pith.science/paper/5PCY2EMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.01922&json=true","fetch_graph":"https://pith.science/api/pith-number/5PCY2EMFBT47AA5SSUPEJFK25C/graph.json","fetch_events":"https://pith.science/api/pith-number/5PCY2EMFBT47AA5SSUPEJFK25C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PCY2EMFBT47AA5SSUPEJFK25C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PCY2EMFBT47AA5SSUPEJFK25C/action/storage_attestation","attest_author":"https://pith.science/pith/5PCY2EMFBT47AA5SSUPEJFK25C/action/author_attestation","sign_citation":"https://pith.science/pith/5PCY2EMFBT47AA5SSUPEJFK25C/action/citation_signature","submit_replication":"https://pith.science/pith/5PCY2EMFBT47AA5SSUPEJFK25C/action/replication_record"}},"created_at":"2026-07-05T03:46:28.049647+00:00","updated_at":"2026-07-05T03:46:28.049647+00:00"}