{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4L3I3M5NT2F3COEHL3VOSGWIFH","short_pith_number":"pith:4L3I3M5N","schema_version":"1.0","canonical_sha256":"e2f68db3ad9e8bb138875eeae91ac829c8dd31007123c99c641c9ce3c88390f9","source":{"kind":"arxiv","id":"2311.04561","version":3},"attestation_state":"computed","paper":{"title":"Information-Theoretic Generalization Bounds for Transductive Learning and its Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huayi Tang, Yong Liu","submitted_at":"2023-11-08T09:48:42Z","abstract_excerpt":"In this paper, we establish generalization bounds for transductive learning algorithms in the context of information theory and PAC-Bayes, covering both the random sampling and the random splitting setting. First, we show that the transductive generalization gap can be controlled by the mutual information between training label selection and the hypothesis. Next, we propose the concept of transductive supersample and use it to derive transductive information-theoretic bounds involving conditional mutual information and different information measures. We further establish transductive PAC-Bayes"},"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":"2311.04561","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-08T09:48:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2390845e8f80fb9cfa825748a85fcbc13622f1a90d0fe9c8d9f51dfaa16e1a87","abstract_canon_sha256":"ded63d5d7f6a910130a1e5dba12c30c035265040f66d99a7bd8c1136a89a9954"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:42.128606Z","signature_b64":"dX5nFZvvdN43WO7uTLvpLB5D6cQFnhcfrtIdL8djLq4MQQwzOnoMS/+JDsLmQZmL1RplHeJyFZ4q/SNRDuLzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2f68db3ad9e8bb138875eeae91ac829c8dd31007123c99c641c9ce3c88390f9","last_reissued_at":"2026-07-05T10:02:42.128152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:42.128152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information-Theoretic Generalization Bounds for Transductive Learning and its Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huayi Tang, Yong Liu","submitted_at":"2023-11-08T09:48:42Z","abstract_excerpt":"In this paper, we establish generalization bounds for transductive learning algorithms in the context of information theory and PAC-Bayes, covering both the random sampling and the random splitting setting. First, we show that the transductive generalization gap can be controlled by the mutual information between training label selection and the hypothesis. Next, we propose the concept of transductive supersample and use it to derive transductive information-theoretic bounds involving conditional mutual information and different information measures. We further establish transductive PAC-Bayes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04561","kind":"arxiv","version":3},"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/2311.04561/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":"2311.04561","created_at":"2026-07-05T10:02:42.128223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04561v3","created_at":"2026-07-05T10:02:42.128223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04561","created_at":"2026-07-05T10:02:42.128223+00:00"},{"alias_kind":"pith_short_12","alias_value":"4L3I3M5NT2F3","created_at":"2026-07-05T10:02:42.128223+00:00"},{"alias_kind":"pith_short_16","alias_value":"4L3I3M5NT2F3COEH","created_at":"2026-07-05T10:02:42.128223+00:00"},{"alias_kind":"pith_short_8","alias_value":"4L3I3M5N","created_at":"2026-07-05T10:02:42.128223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06894","citing_title":"Learning from one graph: transductive learning guarantees via the geometry of small random worlds","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4L3I3M5NT2F3COEHL3VOSGWIFH","json":"https://pith.science/pith/4L3I3M5NT2F3COEHL3VOSGWIFH.json","graph_json":"https://pith.science/api/pith-number/4L3I3M5NT2F3COEHL3VOSGWIFH/graph.json","events_json":"https://pith.science/api/pith-number/4L3I3M5NT2F3COEHL3VOSGWIFH/events.json","paper":"https://pith.science/paper/4L3I3M5N"},"agent_actions":{"view_html":"https://pith.science/pith/4L3I3M5NT2F3COEHL3VOSGWIFH","download_json":"https://pith.science/pith/4L3I3M5NT2F3COEHL3VOSGWIFH.json","view_paper":"https://pith.science/paper/4L3I3M5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04561&json=true","fetch_graph":"https://pith.science/api/pith-number/4L3I3M5NT2F3COEHL3VOSGWIFH/graph.json","fetch_events":"https://pith.science/api/pith-number/4L3I3M5NT2F3COEHL3VOSGWIFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4L3I3M5NT2F3COEHL3VOSGWIFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4L3I3M5NT2F3COEHL3VOSGWIFH/action/storage_attestation","attest_author":"https://pith.science/pith/4L3I3M5NT2F3COEHL3VOSGWIFH/action/author_attestation","sign_citation":"https://pith.science/pith/4L3I3M5NT2F3COEHL3VOSGWIFH/action/citation_signature","submit_replication":"https://pith.science/pith/4L3I3M5NT2F3COEHL3VOSGWIFH/action/replication_record"}},"created_at":"2026-07-05T10:02:42.128223+00:00","updated_at":"2026-07-05T10:02:42.128223+00:00"}