{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OVNWGGZVSG7L5ILIU5BBCWSFUN","short_pith_number":"pith:OVNWGGZV","schema_version":"1.0","canonical_sha256":"755b631b3591bebea168a742115a45a377188f8c55ac963bcc7e0ccb52a33f8f","source":{"kind":"arxiv","id":"2605.29987","version":1},"attestation_state":"computed","paper":{"title":"MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dang Hong Nguyen, Huy-Hieu Pham, Nhi Ngoc-Yen Nguyen","submitted_at":"2026-05-28T14:22:25Z","abstract_excerpt":"Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse. To address this, we introduce MIC, a framework that optimizes the geometric landscape of multi-granular embeddings through isotropic subspace alignment. MIC employs Soft Collapse Regularization (SCR) to mitigate redundancy between prefix and residual subspaces via cross-correlation penalties, alongside Spectral Isotropy Regularization (SIR) to ensure hyper-spherical uniformity in low-dimensional prefixes. By unifying these strategi"},"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":"2605.29987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T14:22:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a3e5d9a1e82377c00a336603f4d5682ac948fcc1e6507fa0a6ba49fa167a342e","abstract_canon_sha256":"52dbf4f08e7283d996311ebbd746eec6ea01d865e634722983d5b87f14b4060e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:05.570568Z","signature_b64":"myEonMiBJnphE5esyvlGNkgcRhkovS5rQqmd7GDKneItY3nh/ykaPKIjDmD2dVSaAOKOQ5ZZ6o19Q0ahdMxQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"755b631b3591bebea168a742115a45a377188f8c55ac963bcc7e0ccb52a33f8f","last_reissued_at":"2026-05-29T02:06:05.569767Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:05.569767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dang Hong Nguyen, Huy-Hieu Pham, Nhi Ngoc-Yen Nguyen","submitted_at":"2026-05-28T14:22:25Z","abstract_excerpt":"Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse. To address this, we introduce MIC, a framework that optimizes the geometric landscape of multi-granular embeddings through isotropic subspace alignment. MIC employs Soft Collapse Regularization (SCR) to mitigate redundancy between prefix and residual subspaces via cross-correlation penalties, alongside Spectral Isotropy Regularization (SIR) to ensure hyper-spherical uniformity in low-dimensional prefixes. By unifying these strategi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29987","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/2605.29987/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":"2605.29987","created_at":"2026-05-29T02:06:05.569861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29987v1","created_at":"2026-05-29T02:06:05.569861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29987","created_at":"2026-05-29T02:06:05.569861+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVNWGGZVSG7L","created_at":"2026-05-29T02:06:05.569861+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVNWGGZVSG7L5ILI","created_at":"2026-05-29T02:06:05.569861+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVNWGGZV","created_at":"2026-05-29T02:06:05.569861+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/OVNWGGZVSG7L5ILIU5BBCWSFUN","json":"https://pith.science/pith/OVNWGGZVSG7L5ILIU5BBCWSFUN.json","graph_json":"https://pith.science/api/pith-number/OVNWGGZVSG7L5ILIU5BBCWSFUN/graph.json","events_json":"https://pith.science/api/pith-number/OVNWGGZVSG7L5ILIU5BBCWSFUN/events.json","paper":"https://pith.science/paper/OVNWGGZV"},"agent_actions":{"view_html":"https://pith.science/pith/OVNWGGZVSG7L5ILIU5BBCWSFUN","download_json":"https://pith.science/pith/OVNWGGZVSG7L5ILIU5BBCWSFUN.json","view_paper":"https://pith.science/paper/OVNWGGZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29987&json=true","fetch_graph":"https://pith.science/api/pith-number/OVNWGGZVSG7L5ILIU5BBCWSFUN/graph.json","fetch_events":"https://pith.science/api/pith-number/OVNWGGZVSG7L5ILIU5BBCWSFUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVNWGGZVSG7L5ILIU5BBCWSFUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVNWGGZVSG7L5ILIU5BBCWSFUN/action/storage_attestation","attest_author":"https://pith.science/pith/OVNWGGZVSG7L5ILIU5BBCWSFUN/action/author_attestation","sign_citation":"https://pith.science/pith/OVNWGGZVSG7L5ILIU5BBCWSFUN/action/citation_signature","submit_replication":"https://pith.science/pith/OVNWGGZVSG7L5ILIU5BBCWSFUN/action/replication_record"}},"created_at":"2026-05-29T02:06:05.569861+00:00","updated_at":"2026-05-29T02:06:05.569861+00:00"}