{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2MJUNPPIOSFLP2TUI73SVHVPH4","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":"d47c753725a3a7a1edec119320043f9108f3919287207c4ec08990aae3f2dafe","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-02-07T22:09:54Z","title_canon_sha256":"36463a86653d1efab4d88bc42ef674625f9c98fe95f5ebe89f747203a9c109d5"},"schema_version":"1.0","source":{"id":"2202.03543","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03543","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03543v2","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03543","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"2MJUNPPIOSFL","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"2MJUNPPIOSFLP2TU","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"2MJUNPPI","created_at":"2026-07-05T04:01:34Z"}],"graph_snapshots":[{"event_id":"sha256:4ec52503bc716f7fcd2474bbfb1bc7b47d2734c40d8faef163063745541949fc","target":"graph","created_at":"2026-07-05T04:01:34Z","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/2202.03543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we describe our submissions to the ZeroSpeech 2021 Challenge and SUPERB benchmark. Our submissions are based on the recently proposed FaST-VGS model, which is a Transformer-based model that learns to associate raw speech waveforms with semantically related images, all without the use of any transcriptions of the speech. Additionally, we introduce a novel extension of this model, FaST-VGS+, which is learned in a multi-task fashion with a masked language modeling objective in addition to the visual grounding objective. On ZeroSpeech 2021, we show that our models perform competitiv","authors_text":"David Harwath, Puyuan Peng","cross_cats":["cs.CL","cs.CV","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-02-07T22:09:54Z","title":"Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03543","kind":"arxiv","version":2},"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:b8532a79ac784634f41de8318f490ac7a9e8209b0dc8d107e5ad3220025fa3c4","target":"record","created_at":"2026-07-05T04:01:34Z","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":"d47c753725a3a7a1edec119320043f9108f3919287207c4ec08990aae3f2dafe","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-02-07T22:09:54Z","title_canon_sha256":"36463a86653d1efab4d88bc42ef674625f9c98fe95f5ebe89f747203a9c109d5"},"schema_version":"1.0","source":{"id":"2202.03543","kind":"arxiv","version":2}},"canonical_sha256":"d31346bde8748ab7ea7447f72a9eaf3f32792dfb662ef5afe5ffac00bb840223","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d31346bde8748ab7ea7447f72a9eaf3f32792dfb662ef5afe5ffac00bb840223","first_computed_at":"2026-07-05T04:01:34.388356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:34.388356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oYnZ5QLmqIzeFhDdRhBGAbU2ECoS//X/7nQPz/oX02qIa2hbMJg+VOy4eQ6q/xybS8XkVZmP1xv1netyFHHMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:34.388830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.03543","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8532a79ac784634f41de8318f490ac7a9e8209b0dc8d107e5ad3220025fa3c4","sha256:4ec52503bc716f7fcd2474bbfb1bc7b47d2734c40d8faef163063745541949fc"],"state_sha256":"4883290e0ef1501df86f623e3a2d92928d7f3bf5e5f24321e6ac535879a41e90"}