{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3IXZN4AVGNKFZCTFUAEEP27Z2Q","short_pith_number":"pith:3IXZN4AV","schema_version":"1.0","canonical_sha256":"da2f96f01533545c8a65a00847ebf9d408a18c2311344309da4701dac2a10f51","source":{"kind":"arxiv","id":"2403.08293","version":3},"attestation_state":"computed","paper":{"title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kewei Tu, Pengyu Ji, Qingyang Zhu, Wei Wu, Xiang Hu","submitted_at":"2024-03-13T06:54:47Z","abstract_excerpt":"A syntactic language model (SLM) incrementally generates a sentence with its syntactic tree in a left-to-right manner. We present Generative Pretrained Structured Transformers (GPST), an unsupervised SLM at scale capable of being pre-trained from scratch on raw texts with high parallelism. GPST circumvents the limitations of previous SLMs such as relying on gold trees and sequential training. It consists of two components, a usual SLM supervised by a uni-directional language modeling loss, and an additional composition model, which induces syntactic parse trees and computes constituent represe"},"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":"2403.08293","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T06:54:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f3f5368f09d00e34211d7767c0ea990ff7e3a4cadaa78ac333ad8595c5042e4","abstract_canon_sha256":"0aea5237cbc828c4f32a0143303395bd5f55b10097ba61c214f3d14c3f054ec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:38.365943Z","signature_b64":"of3DNeCDvQ5WaJlwStPxhRd+KtvaryRUDzPZrNVX519Y4xTO9pQHS13IcPjMFbabKbFxHgY0ss+t7HmVIBlfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da2f96f01533545c8a65a00847ebf9d408a18c2311344309da4701dac2a10f51","last_reissued_at":"2026-07-05T08:32:38.365420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:38.365420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kewei Tu, Pengyu Ji, Qingyang Zhu, Wei Wu, Xiang Hu","submitted_at":"2024-03-13T06:54:47Z","abstract_excerpt":"A syntactic language model (SLM) incrementally generates a sentence with its syntactic tree in a left-to-right manner. We present Generative Pretrained Structured Transformers (GPST), an unsupervised SLM at scale capable of being pre-trained from scratch on raw texts with high parallelism. GPST circumvents the limitations of previous SLMs such as relying on gold trees and sequential training. It consists of two components, a usual SLM supervised by a uni-directional language modeling loss, and an additional composition model, which induces syntactic parse trees and computes constituent represe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08293","kind":"arxiv","version":3},"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/2403.08293/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":"2403.08293","created_at":"2026-07-05T08:32:38.365475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08293v3","created_at":"2026-07-05T08:32:38.365475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08293","created_at":"2026-07-05T08:32:38.365475+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IXZN4AVGNKF","created_at":"2026-07-05T08:32:38.365475+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IXZN4AVGNKFZCTF","created_at":"2026-07-05T08:32:38.365475+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IXZN4AV","created_at":"2026-07-05T08:32:38.365475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18885","citing_title":"Sneaking Syntax into Transformer Language Models with Tree Regularization","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q","json":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q.json","graph_json":"https://pith.science/api/pith-number/3IXZN4AVGNKFZCTFUAEEP27Z2Q/graph.json","events_json":"https://pith.science/api/pith-number/3IXZN4AVGNKFZCTFUAEEP27Z2Q/events.json","paper":"https://pith.science/paper/3IXZN4AV"},"agent_actions":{"view_html":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q","download_json":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q.json","view_paper":"https://pith.science/paper/3IXZN4AV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08293&json=true","fetch_graph":"https://pith.science/api/pith-number/3IXZN4AVGNKFZCTFUAEEP27Z2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/3IXZN4AVGNKFZCTFUAEEP27Z2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/action/storage_attestation","attest_author":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/action/author_attestation","sign_citation":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/action/citation_signature","submit_replication":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/action/replication_record"}},"created_at":"2026-07-05T08:32:38.365475+00:00","updated_at":"2026-07-05T08:32:38.365475+00:00"}