{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TLJENBLTSRYFHE2WFQFHEOLG3W","short_pith_number":"pith:TLJENBLT","schema_version":"1.0","canonical_sha256":"9ad246857394705393562c0a723966ddbad8e6dcfc9cce4fa763b0f7cb10c150","source":{"kind":"arxiv","id":"2511.02496","version":2},"attestation_state":"computed","paper":{"title":"Geometry as a Missing Axis of Representation Quality: The Variational Geometric Information Bottleneck under Data Scarcity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ronald Katende","submitted_at":"2025-11-04T11:33:54Z","abstract_excerpt":"We study latent geometry as an explicit component of representation quality in data-scarce learning. For an encoder (\\phi), we define (Q_{\\beta,\\gamma}(\\phi)=I(\\phi(X);Y)-\\beta\\mathcal C(\\phi)-\\gamma d_{\\mathrm{int}}(\\phi)), combining task-relevant information with penalties for curvature and intrinsic latent dimension. Thus geometry becomes part of the bottleneck criterion, not only a post hoc diagnostic.\n  Under smooth-manifold, loss-transfer, and estimator-concentration assumptions, we derive non-asymptotic low-label generalization bounds where intrinsic dimension and covering complexity en"},"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":"2511.02496","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-04T11:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"70515ed04188de791210159d944516e3dbc4c1a787930a805449a756882563a2","abstract_canon_sha256":"52f43c33e9c333abe8b8675db1d71d941c88cc0aa99ba68887ac683af36ba0c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:14.377520Z","signature_b64":"4tyQeLuYuzs7r809fouMmxj8fny9uBFeVsem/mVPyjm6RRpnjs1LsqmKA+x9K5AQM1SQYQJsB/ZXfnBuLOd3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ad246857394705393562c0a723966ddbad8e6dcfc9cce4fa763b0f7cb10c150","last_reissued_at":"2026-07-03T01:17:14.377056Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:14.377056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometry as a Missing Axis of Representation Quality: The Variational Geometric Information Bottleneck under Data Scarcity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ronald Katende","submitted_at":"2025-11-04T11:33:54Z","abstract_excerpt":"We study latent geometry as an explicit component of representation quality in data-scarce learning. For an encoder (\\phi), we define (Q_{\\beta,\\gamma}(\\phi)=I(\\phi(X);Y)-\\beta\\mathcal C(\\phi)-\\gamma d_{\\mathrm{int}}(\\phi)), combining task-relevant information with penalties for curvature and intrinsic latent dimension. Thus geometry becomes part of the bottleneck criterion, not only a post hoc diagnostic.\n  Under smooth-manifold, loss-transfer, and estimator-concentration assumptions, we derive non-asymptotic low-label generalization bounds where intrinsic dimension and covering complexity en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.02496","kind":"arxiv","version":2},"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/2511.02496/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":"2511.02496","created_at":"2026-07-03T01:17:14.377113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.02496v2","created_at":"2026-07-03T01:17:14.377113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.02496","created_at":"2026-07-03T01:17:14.377113+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLJENBLTSRYF","created_at":"2026-07-03T01:17:14.377113+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLJENBLTSRYFHE2W","created_at":"2026-07-03T01:17:14.377113+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLJENBLT","created_at":"2026-07-03T01:17:14.377113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.29004","citing_title":"Auditing Training-Free 3D Shape Retrieval with Diffused Geodesic Moments","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLJENBLTSRYFHE2WFQFHEOLG3W","json":"https://pith.science/pith/TLJENBLTSRYFHE2WFQFHEOLG3W.json","graph_json":"https://pith.science/api/pith-number/TLJENBLTSRYFHE2WFQFHEOLG3W/graph.json","events_json":"https://pith.science/api/pith-number/TLJENBLTSRYFHE2WFQFHEOLG3W/events.json","paper":"https://pith.science/paper/TLJENBLT"},"agent_actions":{"view_html":"https://pith.science/pith/TLJENBLTSRYFHE2WFQFHEOLG3W","download_json":"https://pith.science/pith/TLJENBLTSRYFHE2WFQFHEOLG3W.json","view_paper":"https://pith.science/paper/TLJENBLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.02496&json=true","fetch_graph":"https://pith.science/api/pith-number/TLJENBLTSRYFHE2WFQFHEOLG3W/graph.json","fetch_events":"https://pith.science/api/pith-number/TLJENBLTSRYFHE2WFQFHEOLG3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLJENBLTSRYFHE2WFQFHEOLG3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLJENBLTSRYFHE2WFQFHEOLG3W/action/storage_attestation","attest_author":"https://pith.science/pith/TLJENBLTSRYFHE2WFQFHEOLG3W/action/author_attestation","sign_citation":"https://pith.science/pith/TLJENBLTSRYFHE2WFQFHEOLG3W/action/citation_signature","submit_replication":"https://pith.science/pith/TLJENBLTSRYFHE2WFQFHEOLG3W/action/replication_record"}},"created_at":"2026-07-03T01:17:14.377113+00:00","updated_at":"2026-07-03T01:17:14.377113+00:00"}