{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J4L3N7IMA4FFXVAUV2AXPUOGPD","short_pith_number":"pith:J4L3N7IM","schema_version":"1.0","canonical_sha256":"4f17b6fd0c070a5bd414ae8177d1c678ecd0ba61cf7a858c069ad44c5a34d36c","source":{"kind":"arxiv","id":"2607.16725","version":1},"attestation_state":"computed","paper":{"title":"Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changyu Liu, Jian Huang, Yuling Jiao","submitted_at":"2026-07-18T09:21:53Z","abstract_excerpt":"Conditional generative modeling remains a challenging problem in semi-supervised settings where labeled data is scarce but unlabeled samples are abundant. To effectively leverage structural information embedded within the unlabeled dataset and compensate for sparse conditioning signals, we propose a semi-supervised framework combining conditional stochastic interpolation with low-dimensional latent representations. RepG decomposes generation into two stages: label-dependent latent sampling and high-dimensional reconstruction. This isolates the supervised learning of conditional dependencies 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":"2607.16725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-18T09:21:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a2fb4f0261fc4bea003524b304b8698d1f2edf6682bd92d1fff8195758f3d2d","abstract_canon_sha256":"ae1526235dc3186a03ae7217b92c8ac4a31dfe146acbf4c009daa9b0b874935a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:23.757416Z","signature_b64":"nnaZIBtv3F/6tXPQoXyiDPjLg7efsUcX/SH1m8ECLZzwkCTlx0wPq5jqzl31KvXrYlp6wywaln9QS0Up859rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f17b6fd0c070a5bd414ae8177d1c678ecd0ba61cf7a858c069ad44c5a34d36c","last_reissued_at":"2026-07-21T01:20:23.756572Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:23.756572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changyu Liu, Jian Huang, Yuling Jiao","submitted_at":"2026-07-18T09:21:53Z","abstract_excerpt":"Conditional generative modeling remains a challenging problem in semi-supervised settings where labeled data is scarce but unlabeled samples are abundant. To effectively leverage structural information embedded within the unlabeled dataset and compensate for sparse conditioning signals, we propose a semi-supervised framework combining conditional stochastic interpolation with low-dimensional latent representations. RepG decomposes generation into two stages: label-dependent latent sampling and high-dimensional reconstruction. This isolates the supervised learning of conditional dependencies to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16725","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/2607.16725/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":"2607.16725","created_at":"2026-07-21T01:20:23.756999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16725v1","created_at":"2026-07-21T01:20:23.756999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16725","created_at":"2026-07-21T01:20:23.756999+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4L3N7IMA4FF","created_at":"2026-07-21T01:20:23.756999+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4L3N7IMA4FFXVAU","created_at":"2026-07-21T01:20:23.756999+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4L3N7IM","created_at":"2026-07-21T01:20:23.756999+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/J4L3N7IMA4FFXVAUV2AXPUOGPD","json":"https://pith.science/pith/J4L3N7IMA4FFXVAUV2AXPUOGPD.json","graph_json":"https://pith.science/api/pith-number/J4L3N7IMA4FFXVAUV2AXPUOGPD/graph.json","events_json":"https://pith.science/api/pith-number/J4L3N7IMA4FFXVAUV2AXPUOGPD/events.json","paper":"https://pith.science/paper/J4L3N7IM"},"agent_actions":{"view_html":"https://pith.science/pith/J4L3N7IMA4FFXVAUV2AXPUOGPD","download_json":"https://pith.science/pith/J4L3N7IMA4FFXVAUV2AXPUOGPD.json","view_paper":"https://pith.science/paper/J4L3N7IM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16725&json=true","fetch_graph":"https://pith.science/api/pith-number/J4L3N7IMA4FFXVAUV2AXPUOGPD/graph.json","fetch_events":"https://pith.science/api/pith-number/J4L3N7IMA4FFXVAUV2AXPUOGPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4L3N7IMA4FFXVAUV2AXPUOGPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4L3N7IMA4FFXVAUV2AXPUOGPD/action/storage_attestation","attest_author":"https://pith.science/pith/J4L3N7IMA4FFXVAUV2AXPUOGPD/action/author_attestation","sign_citation":"https://pith.science/pith/J4L3N7IMA4FFXVAUV2AXPUOGPD/action/citation_signature","submit_replication":"https://pith.science/pith/J4L3N7IMA4FFXVAUV2AXPUOGPD/action/replication_record"}},"created_at":"2026-07-21T01:20:23.756999+00:00","updated_at":"2026-07-21T01:20:23.756999+00:00"}