{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XS7TPDSEC7OTKSNWTGWAZMEJW5","short_pith_number":"pith:XS7TPDSE","schema_version":"1.0","canonical_sha256":"bcbf378e4417dd3549b699ac0cb089b779ffd5f8f650d734dd487575872bc189","source":{"kind":"arxiv","id":"2606.30356","version":1},"attestation_state":"computed","paper":{"title":"OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Karl El Hajal, Mathew Magimai.-Doss","submitted_at":"2026-06-29T14:24:19Z","abstract_excerpt":"We propose Online Latent prediction with Invariant Views and rEconstruction (OLIVE), a self-supervised speech representation learning framework that jointly optimizes analysis and synthesis objectives. OLIVE combines view-augmented masked latent prediction with waveform reconstruction under a unified objective. Reconstruction constrains early encoder features to retain signal-level information, while masked latent prediction shapes later contextual representations toward invariance for robust downstream performance. We show that these objectives enable representations that support a broad rang"},"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":"2606.30356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T14:24:19Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8aff5f9870f43a00cf727b191e1036185bd0cedd02069501f867537c29ffa5c7","abstract_canon_sha256":"0d9958f532d56027c448727ed38247849ef8a0c4c22da475914d5dadb2a8cfd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:11.687902Z","signature_b64":"j2/WeUBVnU9OvQihX2VL8mxKDp/WYsiD7c/e9UU9YXCxOpA024jW7aMhxV1/gv9DUhPh6m9rp9/uirq60B4ECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcbf378e4417dd3549b699ac0cb089b779ffd5f8f650d734dd487575872bc189","last_reissued_at":"2026-06-30T02:18:11.687321Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:11.687321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Karl El Hajal, Mathew Magimai.-Doss","submitted_at":"2026-06-29T14:24:19Z","abstract_excerpt":"We propose Online Latent prediction with Invariant Views and rEconstruction (OLIVE), a self-supervised speech representation learning framework that jointly optimizes analysis and synthesis objectives. OLIVE combines view-augmented masked latent prediction with waveform reconstruction under a unified objective. Reconstruction constrains early encoder features to retain signal-level information, while masked latent prediction shapes later contextual representations toward invariance for robust downstream performance. We show that these objectives enable representations that support a broad rang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30356","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/2606.30356/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":"2606.30356","created_at":"2026-06-30T02:18:11.687404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30356v1","created_at":"2026-06-30T02:18:11.687404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30356","created_at":"2026-06-30T02:18:11.687404+00:00"},{"alias_kind":"pith_short_12","alias_value":"XS7TPDSEC7OT","created_at":"2026-06-30T02:18:11.687404+00:00"},{"alias_kind":"pith_short_16","alias_value":"XS7TPDSEC7OTKSNW","created_at":"2026-06-30T02:18:11.687404+00:00"},{"alias_kind":"pith_short_8","alias_value":"XS7TPDSE","created_at":"2026-06-30T02:18:11.687404+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/XS7TPDSEC7OTKSNWTGWAZMEJW5","json":"https://pith.science/pith/XS7TPDSEC7OTKSNWTGWAZMEJW5.json","graph_json":"https://pith.science/api/pith-number/XS7TPDSEC7OTKSNWTGWAZMEJW5/graph.json","events_json":"https://pith.science/api/pith-number/XS7TPDSEC7OTKSNWTGWAZMEJW5/events.json","paper":"https://pith.science/paper/XS7TPDSE"},"agent_actions":{"view_html":"https://pith.science/pith/XS7TPDSEC7OTKSNWTGWAZMEJW5","download_json":"https://pith.science/pith/XS7TPDSEC7OTKSNWTGWAZMEJW5.json","view_paper":"https://pith.science/paper/XS7TPDSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30356&json=true","fetch_graph":"https://pith.science/api/pith-number/XS7TPDSEC7OTKSNWTGWAZMEJW5/graph.json","fetch_events":"https://pith.science/api/pith-number/XS7TPDSEC7OTKSNWTGWAZMEJW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XS7TPDSEC7OTKSNWTGWAZMEJW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XS7TPDSEC7OTKSNWTGWAZMEJW5/action/storage_attestation","attest_author":"https://pith.science/pith/XS7TPDSEC7OTKSNWTGWAZMEJW5/action/author_attestation","sign_citation":"https://pith.science/pith/XS7TPDSEC7OTKSNWTGWAZMEJW5/action/citation_signature","submit_replication":"https://pith.science/pith/XS7TPDSEC7OTKSNWTGWAZMEJW5/action/replication_record"}},"created_at":"2026-06-30T02:18:11.687404+00:00","updated_at":"2026-06-30T02:18:11.687404+00:00"}