{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ULF3KC6726TNTMP3GBDEDQCZK5","short_pith_number":"pith:ULF3KC67","schema_version":"1.0","canonical_sha256":"a2cbb50bdfd7a6d9b1fb304641c059576378a0cd4196be7747141e87740328f2","source":{"kind":"arxiv","id":"1607.00570","version":1},"attestation_state":"computed","paper":{"title":"Representation learning for very short texts using weighted word embedding aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bart Dhoedt, Cedric De Boom, Steven Van Canneyt, Thomas Demeester","submitted_at":"2016-07-02T23:10:09Z","abstract_excerpt":"Short text messages such as tweets are very noisy and sparse in their use of vocabulary. Traditional textual representations, such as tf-idf, have difficulty grasping the semantic meaning of such texts, which is important in applications such as event detection, opinion mining, news recommendation, etc. We constructed a method based on semantic word embeddings and frequency information to arrive at low-dimensional representations for short texts designed to capture semantic similarity. For this purpose we designed a weight-based model and a learning procedure based on a novel median-based loss"},"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":"1607.00570","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-07-02T23:10:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"890968575458691df525756c3ef8721048409ab2a85d295d5e7f20a75d6d2a22","abstract_canon_sha256":"0832faaece39edad93d110bb7a5489aa9661bcdb50737ea70f82af5abc6914d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:34.734624Z","signature_b64":"d558X8HllzvAbey4bSsO4vR00wLnSDE26CZa/hDLE2fBcUgkpO9EHzJA4ACA6JeGZMTHKumgq9oMLF+qRq4KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2cbb50bdfd7a6d9b1fb304641c059576378a0cd4196be7747141e87740328f2","last_reissued_at":"2026-05-18T01:11:34.734226Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:34.734226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation learning for very short texts using weighted word embedding aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bart Dhoedt, Cedric De Boom, Steven Van Canneyt, Thomas Demeester","submitted_at":"2016-07-02T23:10:09Z","abstract_excerpt":"Short text messages such as tweets are very noisy and sparse in their use of vocabulary. Traditional textual representations, such as tf-idf, have difficulty grasping the semantic meaning of such texts, which is important in applications such as event detection, opinion mining, news recommendation, etc. We constructed a method based on semantic word embeddings and frequency information to arrive at low-dimensional representations for short texts designed to capture semantic similarity. For this purpose we designed a weight-based model and a learning procedure based on a novel median-based loss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00570","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":""},"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":"1607.00570","created_at":"2026-05-18T01:11:34.734291+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.00570v1","created_at":"2026-05-18T01:11:34.734291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00570","created_at":"2026-05-18T01:11:34.734291+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULF3KC6726TN","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULF3KC6726TNTMP3","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULF3KC67","created_at":"2026-05-18T12:30:46.583412+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/ULF3KC6726TNTMP3GBDEDQCZK5","json":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5.json","graph_json":"https://pith.science/api/pith-number/ULF3KC6726TNTMP3GBDEDQCZK5/graph.json","events_json":"https://pith.science/api/pith-number/ULF3KC6726TNTMP3GBDEDQCZK5/events.json","paper":"https://pith.science/paper/ULF3KC67"},"agent_actions":{"view_html":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5","download_json":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5.json","view_paper":"https://pith.science/paper/ULF3KC67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.00570&json=true","fetch_graph":"https://pith.science/api/pith-number/ULF3KC6726TNTMP3GBDEDQCZK5/graph.json","fetch_events":"https://pith.science/api/pith-number/ULF3KC6726TNTMP3GBDEDQCZK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5/action/storage_attestation","attest_author":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5/action/author_attestation","sign_citation":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5/action/citation_signature","submit_replication":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5/action/replication_record"}},"created_at":"2026-05-18T01:11:34.734291+00:00","updated_at":"2026-05-18T01:11:34.734291+00:00"}