{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ULF3KC6726TNTMP3GBDEDQCZK5","short_pith_number":"pith:ULF3KC67","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"},"canonical_sha256":"a2cbb50bdfd7a6d9b1fb304641c059576378a0cd4196be7747141e87740328f2","source":{"kind":"arxiv","id":"1607.00570","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.00570","created_at":"2026-05-18T01:11:34Z"},{"alias_kind":"arxiv_version","alias_value":"1607.00570v1","created_at":"2026-05-18T01:11:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00570","created_at":"2026-05-18T01:11:34Z"},{"alias_kind":"pith_short_12","alias_value":"ULF3KC6726TN","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"ULF3KC6726TNTMP3","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"ULF3KC67","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ULF3KC6726TNTMP3GBDEDQCZK5","target":"record","payload":{"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"},"canonical_sha256":"a2cbb50bdfd7a6d9b1fb304641c059576378a0cd4196be7747141e87740328f2","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"},"source_kind":"arxiv","source_id":"1607.00570","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:11:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rBAyGBJs94Q+b2y0kHcZSBREQT6/hJoEWWpZ9N3jL9HP0iISK4qIQxZ7g7oSEN1EYudAn6CZdLLPQYRF3l/+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T21:46:12.222742Z"},"content_sha256":"dfb53c49f5131fb4ddb8ff4887582f1f8ecfeae038ac66dce152f7eda8df3915","schema_version":"1.0","event_id":"sha256:dfb53c49f5131fb4ddb8ff4887582f1f8ecfeae038ac66dce152f7eda8df3915"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ULF3KC6726TNTMP3GBDEDQCZK5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:11:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGjncIdf6vfW83wjCuLUlX2sENa3BolCif+d/ByGGesw8Toc48QjUC/Ba/8VQu/KI5ZeoIIqn+A/Eupq1jemDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T21:46:12.223428Z"},"content_sha256":"a1adc0ecaaad4f83268aec03263f7a54904ba69b921c7a46f9c05f195985c4dd","schema_version":"1.0","event_id":"sha256:a1adc0ecaaad4f83268aec03263f7a54904ba69b921c7a46f9c05f195985c4dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5/bundle.json","state_url":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULF3KC6726TNTMP3GBDEDQCZK5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-04T21:46:12Z","links":{"resolver":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5","bundle":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5/bundle.json","state":"https://pith.science/pith/ULF3KC6726TNTMP3GBDEDQCZK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULF3KC6726TNTMP3GBDEDQCZK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ULF3KC6726TNTMP3GBDEDQCZK5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0832faaece39edad93d110bb7a5489aa9661bcdb50737ea70f82af5abc6914d1","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-07-02T23:10:09Z","title_canon_sha256":"890968575458691df525756c3ef8721048409ab2a85d295d5e7f20a75d6d2a22"},"schema_version":"1.0","source":{"id":"1607.00570","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.00570","created_at":"2026-05-18T01:11:34Z"},{"alias_kind":"arxiv_version","alias_value":"1607.00570v1","created_at":"2026-05-18T01:11:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00570","created_at":"2026-05-18T01:11:34Z"},{"alias_kind":"pith_short_12","alias_value":"ULF3KC6726TN","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"ULF3KC6726TNTMP3","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"ULF3KC67","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:a1adc0ecaaad4f83268aec03263f7a54904ba69b921c7a46f9c05f195985c4dd","target":"graph","created_at":"2026-05-18T01:11:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Bart Dhoedt, Cedric De Boom, Steven Van Canneyt, Thomas Demeester","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-07-02T23:10:09Z","title":"Representation learning for very short texts using weighted word embedding aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00570","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dfb53c49f5131fb4ddb8ff4887582f1f8ecfeae038ac66dce152f7eda8df3915","target":"record","created_at":"2026-05-18T01:11:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0832faaece39edad93d110bb7a5489aa9661bcdb50737ea70f82af5abc6914d1","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-07-02T23:10:09Z","title_canon_sha256":"890968575458691df525756c3ef8721048409ab2a85d295d5e7f20a75d6d2a22"},"schema_version":"1.0","source":{"id":"1607.00570","kind":"arxiv","version":1}},"canonical_sha256":"a2cbb50bdfd7a6d9b1fb304641c059576378a0cd4196be7747141e87740328f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2cbb50bdfd7a6d9b1fb304641c059576378a0cd4196be7747141e87740328f2","first_computed_at":"2026-05-18T01:11:34.734226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:11:34.734226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d558X8HllzvAbey4bSsO4vR00wLnSDE26CZa/hDLE2fBcUgkpO9EHzJA4ACA6JeGZMTHKumgq9oMLF+qRq4KCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:11:34.734624Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.00570","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfb53c49f5131fb4ddb8ff4887582f1f8ecfeae038ac66dce152f7eda8df3915","sha256:a1adc0ecaaad4f83268aec03263f7a54904ba69b921c7a46f9c05f195985c4dd"],"state_sha256":"de08b666f699de19b644032da0f164dc0a999fa1b4b3fb1f60f44c7097a0c13c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j4uV8ItvCnarD8nmBhdy02lqGUFimsR5x4KQ15poo0WcZjE3s0jzcfyBcUZ1OD4wH8oYcgcFOri/JRv0mf1MDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T21:46:12.226653Z","bundle_sha256":"1bdb066aca91f1a05a4132e842b55adb8f9b688552f64d97d26b04fe092d102f"}}