{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6BVVIPXFR3WXPXNG347F5E64EV","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":"3efb49c97fe5319da989b37ccccf6aad4d03b51f124d12e4488151080bc660b7","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T16:54:57Z","title_canon_sha256":"328ce0f072599a5076800864c32b189013e3fbd3eeb280a7b96463c5f0593622"},"schema_version":"1.0","source":{"id":"2310.07654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07654","created_at":"2026-07-05T06:59:48Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07654v1","created_at":"2026-07-05T06:59:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07654","created_at":"2026-07-05T06:59:48Z"},{"alias_kind":"pith_short_12","alias_value":"6BVVIPXFR3WX","created_at":"2026-07-05T06:59:48Z"},{"alias_kind":"pith_short_16","alias_value":"6BVVIPXFR3WXPXNG","created_at":"2026-07-05T06:59:48Z"},{"alias_kind":"pith_short_8","alias_value":"6BVVIPXF","created_at":"2026-07-05T06:59:48Z"}],"graph_snapshots":[{"event_id":"sha256:e6a07d3261ee8f3377b138785da4d984cda7896aaf6ea96e2c538cfc4ce63449","target":"graph","created_at":"2026-07-05T06:59:48Z","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/2310.07654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study phrase structure induction from visually-grounded speech. The core idea is to first segment the speech waveform into sequences of word segments, and subsequently induce phrase structure using the inferred segment-level continuous representations. We present the Audio-Visual Neural Syntax Learner (AV-NSL) that learns phrase structure by listening to audio and looking at images, without ever being exposed to text. By training on paired images and spoken captions, AV-NSL exhibits the capability to infer meaningful phrase structures that are comparable to those derived by naturally-superv","authors_text":"Cheng-I Jeff Lai, David Cox, David Harwath, Freda Shi, James Glass, Karen Livescu, Kevin Gimpel, Puyuan Peng, Saurabhchand Bhati, Shiyu Chang, Yang Zhang, Yoon Kim, Yung-Sung Chuang","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T16:54:57Z","title":"Audio-Visual Neural Syntax Acquisition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07654","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:c50cae67950dd49538294295e490fbcb66e7335d53b897f97e39befc6474f746","target":"record","created_at":"2026-07-05T06:59:48Z","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":"3efb49c97fe5319da989b37ccccf6aad4d03b51f124d12e4488151080bc660b7","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T16:54:57Z","title_canon_sha256":"328ce0f072599a5076800864c32b189013e3fbd3eeb280a7b96463c5f0593622"},"schema_version":"1.0","source":{"id":"2310.07654","kind":"arxiv","version":1}},"canonical_sha256":"f06b543ee58eed77dda6df3e5e93dc2563ac3b012d6d6ea562276f17d3e828a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f06b543ee58eed77dda6df3e5e93dc2563ac3b012d6d6ea562276f17d3e828a3","first_computed_at":"2026-07-05T06:59:48.178920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:48.178920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FbhGPe6A0XP3uy+nw/ZKgVlIQ0MKS5hfOYNNBxqrkKv4q8P8vJJHe+zLf6LeAitKVnJa6NmzyQxF3WJ1r1sdCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:48.179427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c50cae67950dd49538294295e490fbcb66e7335d53b897f97e39befc6474f746","sha256:e6a07d3261ee8f3377b138785da4d984cda7896aaf6ea96e2c538cfc4ce63449"],"state_sha256":"cfe49f0d5db2307718d4e586d58c47cfb4ca2f962cf72acaa8a52f8dbb9ad179"}