{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:J6UMRJ5PEUU7LQ3MS72SRPIFWI","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":"5698974bd7c219e5f1ac584a0bdad16d5f411b87da563a3497a7cbb823e7bc0f","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2021-02-03T08:13:21Z","title_canon_sha256":"d0c6636994034118012e9dc4ddbcd6d295dddd09afc92d80d471ffaab4c70f4b"},"schema_version":"1.0","source":{"id":"2102.01930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01930","created_at":"2026-07-05T02:12:35Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01930v1","created_at":"2026-07-05T02:12:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01930","created_at":"2026-07-05T02:12:35Z"},{"alias_kind":"pith_short_12","alias_value":"J6UMRJ5PEUU7","created_at":"2026-07-05T02:12:35Z"},{"alias_kind":"pith_short_16","alias_value":"J6UMRJ5PEUU7LQ3M","created_at":"2026-07-05T02:12:35Z"},{"alias_kind":"pith_short_8","alias_value":"J6UMRJ5P","created_at":"2026-07-05T02:12:35Z"}],"graph_snapshots":[{"event_id":"sha256:646770503545cc41a2fdc39f1941f8a17de8fa2227c8889f9765b61b059e1c5d","target":"graph","created_at":"2026-07-05T02:12:35Z","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/2102.01930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. In the design of MGF, speech hierarchy is taken into consideration. Specifically, we propose to use generative learning approaches to capture fine-grained information at small time scales and use discriminative learning approaches to distill coarse-grained or semantic information at large time scales. For phoneme-scale learning, we borrow idea from the masked language model but tailor it for the continuous speech signal by replacing classification loss with a contrastive los","authors_text":"Chong Luo, Chuanxin Tang, Dacheng Yin, Wenjun Zeng, Yucheng Zhao, Zheng-Jun Zha, Zhiyuan Zhao","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2021-02-03T08:13:21Z","title":"General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01930","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:ae5bae1e18f43737fa67e62dcd92d7e92bf4b7c6b9ab4e3586106e73b7e2b9de","target":"record","created_at":"2026-07-05T02:12:35Z","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":"5698974bd7c219e5f1ac584a0bdad16d5f411b87da563a3497a7cbb823e7bc0f","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2021-02-03T08:13:21Z","title_canon_sha256":"d0c6636994034118012e9dc4ddbcd6d295dddd09afc92d80d471ffaab4c70f4b"},"schema_version":"1.0","source":{"id":"2102.01930","kind":"arxiv","version":1}},"canonical_sha256":"4fa8c8a7af2529f5c36c97f528bd05b2286121c135ff73ee3f976106082317be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fa8c8a7af2529f5c36c97f528bd05b2286121c135ff73ee3f976106082317be","first_computed_at":"2026-07-05T02:12:35.018796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:12:35.018796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PiDM5Td1YMzRT5uowujfzoXfox44XqZMQN1OSC7E1tUslNQeaB6aJAE2E3mZof+jd6PLKvzPzIPk8rIBVo+fCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:12:35.019163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.01930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae5bae1e18f43737fa67e62dcd92d7e92bf4b7c6b9ab4e3586106e73b7e2b9de","sha256:646770503545cc41a2fdc39f1941f8a17de8fa2227c8889f9765b61b059e1c5d"],"state_sha256":"c4665eab5242962e05e6dcd439e92e12255ca3ccb33bd31418ab74381b6779df"}