{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QSSPSIEGDFLYLZFTWO2AGROTQJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"388678ef1108ef5658009a4780ea84dc86acde6e905df5c1b1a50f449df1b7f1","cross_cats_sorted":["eess.AS","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-17T08:39:09Z","title_canon_sha256":"c647fa3102200075f0bb2a7414fd29a790f3b1bba0dd6510cef06aacdae405ef"},"schema_version":"1.0","source":{"id":"2606.19398","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19398","created_at":"2026-06-19T16:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19398v1","created_at":"2026-06-19T16:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19398","created_at":"2026-06-19T16:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"QSSPSIEGDFLY","created_at":"2026-06-19T16:12:24Z"},{"alias_kind":"pith_short_16","alias_value":"QSSPSIEGDFLYLZFT","created_at":"2026-06-19T16:12:24Z"},{"alias_kind":"pith_short_8","alias_value":"QSSPSIEG","created_at":"2026-06-19T16:12:24Z"}],"graph_snapshots":[{"event_id":"sha256:cb878910c0f82c44c5d48ee19e79c059e2e850a58223e68701f91a76778746ac","target":"graph","created_at":"2026-06-19T16:12:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.19398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised speech encoders are predominantly trained by predicting discrete hard cluster IDs at masked positions, a recipe that collapses acoustic ambiguity at category boundaries and requires interrupting training to re-cluster the entire corpus between iterations. We introduce S-JEPA, a JEPA-style encoder-predictor pair trained to match the soft posteriors of a Gaussian Mixture Model at masked positions via KL divergence. Training runs as one continuous optimization trajectory in two phases: a fixed GMM over MFCC features, then an online GMM over encoder features, with the input layer s","authors_text":"Aaron Elkins, Adrian Kieback, Aman Chadha, Georgios Ioannides, Judah Goldfeder, Linsey Pang, Ravid Shwartz-Ziv, Yann LeCun","cross_cats":["eess.AS","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-17T08:39:09Z","title":"S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19398","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:91c2ffbc72d6352cc23622c66151d0537420506ab145a5f212bf0b288ec5033e","target":"record","created_at":"2026-06-19T16:12:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"388678ef1108ef5658009a4780ea84dc86acde6e905df5c1b1a50f449df1b7f1","cross_cats_sorted":["eess.AS","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-17T08:39:09Z","title_canon_sha256":"c647fa3102200075f0bb2a7414fd29a790f3b1bba0dd6510cef06aacdae405ef"},"schema_version":"1.0","source":{"id":"2606.19398","kind":"arxiv","version":1}},"canonical_sha256":"84a4f92086195785e4b3b3b40345d3824d89ee8a91b9d529c5115cb620687b63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84a4f92086195785e4b3b3b40345d3824d89ee8a91b9d529c5115cb620687b63","first_computed_at":"2026-06-19T16:12:24.532994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:24.532994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SbyNDuZApPIshQfzJ5Tn0EPqlxFIHAEPdAufmhn0C1l9G6rZAC/VyQSei12niQ92GRy4ymDlAiUDyo9TndHHAw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:24.533354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19398","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91c2ffbc72d6352cc23622c66151d0537420506ab145a5f212bf0b288ec5033e","sha256:cb878910c0f82c44c5d48ee19e79c059e2e850a58223e68701f91a76778746ac"],"state_sha256":"c7dc8f9fa2e370a69a16b9940b9510b71c61ac8e9a38f3fc629125031b5a05e0"}