{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:FAT3EV2TVGHN7LSEB56WQENS3L","short_pith_number":"pith:FAT3EV2T","schema_version":"1.0","canonical_sha256":"2827b25753a98edfae440f7d6811b2dadfcf70a293a84ac1f602c1bd1198a2ee","source":{"kind":"arxiv","id":"1611.05774","version":2},"attestation_state":"computed","paper":{"title":"What Do Recurrent Neural Network Grammars Learn About Syntax?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adhiguna Kuncoro, Chris Dyer, Graham Neubig, Lingpeng Kong, Miguel Ballesteros, Noah A. Smith","submitted_at":"2016-11-17T16:41:41Z","abstract_excerpt":"Recurrent neural network grammars (RNNG) are a recently proposed probabilistic generative modeling family for natural language. They show state-of-the-art language modeling and parsing performance. We investigate what information they learn, from a linguistic perspective, through various ablations to the model and the data, and by augmenting the model with an attention mechanism (GA-RNNG) to enable closer inspection. We find that explicit modeling of composition is crucial for achieving the best performance. Through the attention mechanism, we find that headedness plays a central role in phras"},"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":"1611.05774","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-17T16:41:41Z","cross_cats_sorted":[],"title_canon_sha256":"2e886b12ee6aa01418636cffb861a01d31f08ae058754a41ad3af5e2e5a4e6fe","abstract_canon_sha256":"d6ea67611b1a65bef8da5b1e5582339530814ab527b3b7865061ef4156538acb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:02.122889Z","signature_b64":"SX0YuO2DiRmYQxv2D+K+nnnhzjU1R4maedx7Gdx8OP4PJc0M+QJbLfccbGoaeV0qCBOMkyRXdlufN31z4EWJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2827b25753a98edfae440f7d6811b2dadfcf70a293a84ac1f602c1bd1198a2ee","last_reissued_at":"2026-05-18T00:53:02.122377Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:02.122377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Do Recurrent Neural Network Grammars Learn About Syntax?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adhiguna Kuncoro, Chris Dyer, Graham Neubig, Lingpeng Kong, Miguel Ballesteros, Noah A. Smith","submitted_at":"2016-11-17T16:41:41Z","abstract_excerpt":"Recurrent neural network grammars (RNNG) are a recently proposed probabilistic generative modeling family for natural language. They show state-of-the-art language modeling and parsing performance. We investigate what information they learn, from a linguistic perspective, through various ablations to the model and the data, and by augmenting the model with an attention mechanism (GA-RNNG) to enable closer inspection. We find that explicit modeling of composition is crucial for achieving the best performance. Through the attention mechanism, we find that headedness plays a central role in phras"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05774","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1611.05774","created_at":"2026-05-18T00:53:02.122463+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05774v2","created_at":"2026-05-18T00:53:02.122463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05774","created_at":"2026-05-18T00:53:02.122463+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAT3EV2TVGHN","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAT3EV2TVGHN7LSE","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAT3EV2T","created_at":"2026-05-18T12:30:15.759754+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/FAT3EV2TVGHN7LSEB56WQENS3L","json":"https://pith.science/pith/FAT3EV2TVGHN7LSEB56WQENS3L.json","graph_json":"https://pith.science/api/pith-number/FAT3EV2TVGHN7LSEB56WQENS3L/graph.json","events_json":"https://pith.science/api/pith-number/FAT3EV2TVGHN7LSEB56WQENS3L/events.json","paper":"https://pith.science/paper/FAT3EV2T"},"agent_actions":{"view_html":"https://pith.science/pith/FAT3EV2TVGHN7LSEB56WQENS3L","download_json":"https://pith.science/pith/FAT3EV2TVGHN7LSEB56WQENS3L.json","view_paper":"https://pith.science/paper/FAT3EV2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05774&json=true","fetch_graph":"https://pith.science/api/pith-number/FAT3EV2TVGHN7LSEB56WQENS3L/graph.json","fetch_events":"https://pith.science/api/pith-number/FAT3EV2TVGHN7LSEB56WQENS3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAT3EV2TVGHN7LSEB56WQENS3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAT3EV2TVGHN7LSEB56WQENS3L/action/storage_attestation","attest_author":"https://pith.science/pith/FAT3EV2TVGHN7LSEB56WQENS3L/action/author_attestation","sign_citation":"https://pith.science/pith/FAT3EV2TVGHN7LSEB56WQENS3L/action/citation_signature","submit_replication":"https://pith.science/pith/FAT3EV2TVGHN7LSEB56WQENS3L/action/replication_record"}},"created_at":"2026-05-18T00:53:02.122463+00:00","updated_at":"2026-05-18T00:53:02.122463+00:00"}