{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A6K4VWWSH3ZVUSKVBPI7RHQ5K2","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":"00caddd7147009ff951525cfcdc18e35555d785e5a16ad472a85d3b7658b83a9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-08T16:55:21Z","title_canon_sha256":"4630330bf55425a994ccaf0138a6c7c3aca8829127477f9ff48f002f4689ffd9"},"schema_version":"1.0","source":{"id":"2402.05819","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05819","created_at":"2026-07-05T07:43:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05819v1","created_at":"2026-07-05T07:43:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05819","created_at":"2026-07-05T07:43:03Z"},{"alias_kind":"pith_short_12","alias_value":"A6K4VWWSH3ZV","created_at":"2026-07-05T07:43:03Z"},{"alias_kind":"pith_short_16","alias_value":"A6K4VWWSH3ZVUSKV","created_at":"2026-07-05T07:43:03Z"},{"alias_kind":"pith_short_8","alias_value":"A6K4VWWS","created_at":"2026-07-05T07:43:03Z"}],"graph_snapshots":[{"event_id":"sha256:d39aea3e7429efc407eb33f6986f95ac6aae17f0277cea9b7630c4cafae5152e","target":"graph","created_at":"2026-07-05T07:43:03Z","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/2402.05819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoken language understanding tasks that require semantic comprehension. Existing works often rely on additional speech-text data as intermediate targets, which is costly in the real-world setting. To address this challenge, we propose Pseudo-Word HuBERT (PW-HuBERT), a framework that integrates pseudo word-level targets into the training process, where the targets are derived from a","authors_text":"David Harwath, Hsuan-Fu Wang, Hung-Chieh Fang, Hung-yi Lee, Layne Berry, Nai-Xuan Ye, Puyuan Peng, Yi-Jen Shih","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-08T16:55:21Z","title":"Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05819","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":"sha256:14368513bdf2e725a321cbc8a1a83621a69517b6a3bf3f1563f026507b7d9100","target":"record","created_at":"2026-07-05T07:43:03Z","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":"00caddd7147009ff951525cfcdc18e35555d785e5a16ad472a85d3b7658b83a9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-08T16:55:21Z","title_canon_sha256":"4630330bf55425a994ccaf0138a6c7c3aca8829127477f9ff48f002f4689ffd9"},"schema_version":"1.0","source":{"id":"2402.05819","kind":"arxiv","version":1}},"canonical_sha256":"0795cadad23ef35a49550bd1f89e1d56aab2c981fd50411ede840450f0551a69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0795cadad23ef35a49550bd1f89e1d56aab2c981fd50411ede840450f0551a69","first_computed_at":"2026-07-05T07:43:03.847152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:03.847152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pr6HeK8b2NsRtk9Aj2nd4YPp/StCK5J6CChU8rydu0ikLfTlaDaY9DRhEzJMpkNQUEvs4EKOAHROZC6NXTcUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:03.847587Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05819","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14368513bdf2e725a321cbc8a1a83621a69517b6a3bf3f1563f026507b7d9100","sha256:d39aea3e7429efc407eb33f6986f95ac6aae17f0277cea9b7630c4cafae5152e"],"state_sha256":"3284621a96df16f92a358047d86d64040663358d6b62b955f040c4ef90631da9"}