{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I6V3SFT3OOPGM4YV6KIPI4FLXJ","short_pith_number":"pith:I6V3SFT3","schema_version":"1.0","canonical_sha256":"47abb9167b739e667315f290f470abba6c60685be2fded3f1a41fd199ac1458c","source":{"kind":"arxiv","id":"1906.03753","version":2},"attestation_state":"computed","paper":{"title":"Out-of-Vocabulary Embedding Imputation with Grounded Language Information by Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Eric Darve, Vin Sachidananda, Ziyi Yang","submitted_at":"2019-06-10T01:10:34Z","abstract_excerpt":"Due to the ubiquitous use of embeddings as input representations for a wide range of natural language tasks, imputation of embeddings for rare and unseen words is a critical problem in language processing. Embedding imputation involves learning representations for rare or unseen words during the training of an embedding model, often in a post-hoc manner. In this paper, we propose an approach for embedding imputation which uses grounded information in the form of a knowledge graph. This is in contrast to existing approaches which typically make use of vector space properties or subword informat"},"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":"1906.03753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-10T01:10:34Z","cross_cats_sorted":[],"title_canon_sha256":"f68c9b79eea95e04cfe79d8dad715e7a5288b0a711461be1678e1d523c72abef","abstract_canon_sha256":"2e1fcce7b6e0ac765bf652e9ecdea45eb70eec70c7d849448a7edbd82640fe06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:23.734804Z","signature_b64":"cKkgOIGK3M6gItJsEmssCzGNNhVTdZC/kHrkTS1alFBqpQ1Qq7RUX394IqQnuZZpcC+8+Py2pn2GzNwfej3UCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47abb9167b739e667315f290f470abba6c60685be2fded3f1a41fd199ac1458c","last_reissued_at":"2026-07-05T01:08:23.734392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:23.734392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out-of-Vocabulary Embedding Imputation with Grounded Language Information by Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Eric Darve, Vin Sachidananda, Ziyi Yang","submitted_at":"2019-06-10T01:10:34Z","abstract_excerpt":"Due to the ubiquitous use of embeddings as input representations for a wide range of natural language tasks, imputation of embeddings for rare and unseen words is a critical problem in language processing. Embedding imputation involves learning representations for rare or unseen words during the training of an embedding model, often in a post-hoc manner. In this paper, we propose an approach for embedding imputation which uses grounded information in the form of a knowledge graph. This is in contrast to existing approaches which typically make use of vector space properties or subword informat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03753","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.03753/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":"1906.03753","created_at":"2026-07-05T01:08:23.734452+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.03753v2","created_at":"2026-07-05T01:08:23.734452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03753","created_at":"2026-07-05T01:08:23.734452+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6V3SFT3OOPG","created_at":"2026-07-05T01:08:23.734452+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6V3SFT3OOPGM4YV","created_at":"2026-07-05T01:08:23.734452+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6V3SFT3","created_at":"2026-07-05T01:08:23.734452+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/I6V3SFT3OOPGM4YV6KIPI4FLXJ","json":"https://pith.science/pith/I6V3SFT3OOPGM4YV6KIPI4FLXJ.json","graph_json":"https://pith.science/api/pith-number/I6V3SFT3OOPGM4YV6KIPI4FLXJ/graph.json","events_json":"https://pith.science/api/pith-number/I6V3SFT3OOPGM4YV6KIPI4FLXJ/events.json","paper":"https://pith.science/paper/I6V3SFT3"},"agent_actions":{"view_html":"https://pith.science/pith/I6V3SFT3OOPGM4YV6KIPI4FLXJ","download_json":"https://pith.science/pith/I6V3SFT3OOPGM4YV6KIPI4FLXJ.json","view_paper":"https://pith.science/paper/I6V3SFT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.03753&json=true","fetch_graph":"https://pith.science/api/pith-number/I6V3SFT3OOPGM4YV6KIPI4FLXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/I6V3SFT3OOPGM4YV6KIPI4FLXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6V3SFT3OOPGM4YV6KIPI4FLXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6V3SFT3OOPGM4YV6KIPI4FLXJ/action/storage_attestation","attest_author":"https://pith.science/pith/I6V3SFT3OOPGM4YV6KIPI4FLXJ/action/author_attestation","sign_citation":"https://pith.science/pith/I6V3SFT3OOPGM4YV6KIPI4FLXJ/action/citation_signature","submit_replication":"https://pith.science/pith/I6V3SFT3OOPGM4YV6KIPI4FLXJ/action/replication_record"}},"created_at":"2026-07-05T01:08:23.734452+00:00","updated_at":"2026-07-05T01:08:23.734452+00:00"}