{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4T3TOVISQ2Z2DPIVZ3AWRO5RK4","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":"36478dd9499109834de5e0cd798d80941a295c5422b2fe694e5a98b61b0d36a4","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-28T20:41:17Z","title_canon_sha256":"9b8d0476933932e8a897bd41ab2026771bbd93b0036332b5f7f85b92b98223c7"},"schema_version":"1.0","source":{"id":"2203.15081","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15081","created_at":"2026-07-05T06:21:46Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15081v5","created_at":"2026-07-05T06:21:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15081","created_at":"2026-07-05T06:21:46Z"},{"alias_kind":"pith_short_12","alias_value":"4T3TOVISQ2Z2","created_at":"2026-07-05T06:21:46Z"},{"alias_kind":"pith_short_16","alias_value":"4T3TOVISQ2Z2DPIV","created_at":"2026-07-05T06:21:46Z"},{"alias_kind":"pith_short_8","alias_value":"4T3TOVIS","created_at":"2026-07-05T06:21:46Z"}],"graph_snapshots":[{"event_id":"sha256:0e81379b75dd270795d56487ec30ed1ca60108207085f1aeed635cab9dcb827a","target":"graph","created_at":"2026-07-05T06:21:46Z","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/2203.15081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a method for visually-grounded spoken term discovery. After training either a HuBERT or wav2vec2.0 model to associate spoken captions with natural images, we show that powerful word segmentation and clustering capability emerges within the model's self-attention heads. Our experiments reveal that this ability is not present to nearly the same extent in the base HuBERT and wav2vec2.0 models, suggesting that the visual grounding task is a crucial component of the word discovery capability we observe. We also evaluate our method on the Buckeye word segmentation and ZeroSpeech spoken te","authors_text":"David Harwath, Puyuan Peng","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-28T20:41:17Z","title":"Word Discovery in Visually Grounded, Self-Supervised Speech Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15081","kind":"arxiv","version":5},"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":"sha256:2bf5781b38d5a6c92a2bb9721f46ce61f858f9c19f998b77e8127a2f18351661","target":"record","created_at":"2026-07-05T06:21:46Z","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":"36478dd9499109834de5e0cd798d80941a295c5422b2fe694e5a98b61b0d36a4","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-28T20:41:17Z","title_canon_sha256":"9b8d0476933932e8a897bd41ab2026771bbd93b0036332b5f7f85b92b98223c7"},"schema_version":"1.0","source":{"id":"2203.15081","kind":"arxiv","version":5}},"canonical_sha256":"e4f737551286b3a1bd15cec168bbb1573f9cf68dbd5e682fe6d5746ce9834276","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4f737551286b3a1bd15cec168bbb1573f9cf68dbd5e682fe6d5746ce9834276","first_computed_at":"2026-07-05T06:21:46.402569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:46.402569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ro2MUmw4xU0JBmtuPu0w3M/153y2Tt4KTaec8L8UHx3DRhem7lf96Nq/Qsv9LmFJkqxj4txsGvBxRS827XxhCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:46.402985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.15081","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bf5781b38d5a6c92a2bb9721f46ce61f858f9c19f998b77e8127a2f18351661","sha256:0e81379b75dd270795d56487ec30ed1ca60108207085f1aeed635cab9dcb827a"],"state_sha256":"fac83d135af9f425d7aa1785a1a97653bcb90f17d33af408a3aa3021f29487b0"}