{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6BVVIPXFR3WXPXNG347F5E64EV","short_pith_number":"pith:6BVVIPXF","schema_version":"1.0","canonical_sha256":"f06b543ee58eed77dda6df3e5e93dc2563ac3b012d6d6ea562276f17d3e828a3","source":{"kind":"arxiv","id":"2310.07654","version":1},"attestation_state":"computed","paper":{"title":"Audio-Visual Neural Syntax Acquisition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","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","submitted_at":"2023-10-11T16:54:57Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.07654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T16:54:57Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"328ce0f072599a5076800864c32b189013e3fbd3eeb280a7b96463c5f0593622","abstract_canon_sha256":"3efb49c97fe5319da989b37ccccf6aad4d03b51f124d12e4488151080bc660b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:48.179427Z","signature_b64":"FbhGPe6A0XP3uy+nw/ZKgVlIQ0MKS5hfOYNNBxqrkKv4q8P8vJJHe+zLf6LeAitKVnJa6NmzyQxF3WJ1r1sdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f06b543ee58eed77dda6df3e5e93dc2563ac3b012d6d6ea562276f17d3e828a3","last_reissued_at":"2026-07-05T06:59:48.178920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:48.178920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Neural Syntax Acquisition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","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","submitted_at":"2023-10-11T16:54:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07654","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.07654/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.07654","created_at":"2026-07-05T06:59:48.178977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07654v1","created_at":"2026-07-05T06:59:48.178977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07654","created_at":"2026-07-05T06:59:48.178977+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BVVIPXFR3WX","created_at":"2026-07-05T06:59:48.178977+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BVVIPXFR3WXPXNG","created_at":"2026-07-05T06:59:48.178977+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BVVIPXF","created_at":"2026-07-05T06:59:48.178977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BVVIPXFR3WXPXNG347F5E64EV","json":"https://pith.science/pith/6BVVIPXFR3WXPXNG347F5E64EV.json","graph_json":"https://pith.science/api/pith-number/6BVVIPXFR3WXPXNG347F5E64EV/graph.json","events_json":"https://pith.science/api/pith-number/6BVVIPXFR3WXPXNG347F5E64EV/events.json","paper":"https://pith.science/paper/6BVVIPXF"},"agent_actions":{"view_html":"https://pith.science/pith/6BVVIPXFR3WXPXNG347F5E64EV","download_json":"https://pith.science/pith/6BVVIPXFR3WXPXNG347F5E64EV.json","view_paper":"https://pith.science/paper/6BVVIPXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07654&json=true","fetch_graph":"https://pith.science/api/pith-number/6BVVIPXFR3WXPXNG347F5E64EV/graph.json","fetch_events":"https://pith.science/api/pith-number/6BVVIPXFR3WXPXNG347F5E64EV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BVVIPXFR3WXPXNG347F5E64EV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BVVIPXFR3WXPXNG347F5E64EV/action/storage_attestation","attest_author":"https://pith.science/pith/6BVVIPXFR3WXPXNG347F5E64EV/action/author_attestation","sign_citation":"https://pith.science/pith/6BVVIPXFR3WXPXNG347F5E64EV/action/citation_signature","submit_replication":"https://pith.science/pith/6BVVIPXFR3WXPXNG347F5E64EV/action/replication_record"}},"created_at":"2026-07-05T06:59:48.178977+00:00","updated_at":"2026-07-05T06:59:48.178977+00:00"}