{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XZE5YF4SRX7VMEB75X67MFX3DQ","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":"860e49e161e64c18991eab71e772b51895bf3f6833d40d5a341a51dd09f7b57e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-14T02:02:18Z","title_canon_sha256":"58275b91433dbfc96ee53d159c9f2e42190a9e2423e73460f4fd7f351c846c9c"},"schema_version":"1.0","source":{"id":"1811.05542","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05542","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05542v2","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05542","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"XZE5YF4SRX7V","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"XZE5YF4SRX7VMEB7","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"XZE5YF4S","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:55959c9b132e249a4923344c9035984079ad7bb5b6e5304c3f2138a575379ae2","target":"graph","created_at":"2026-05-17T23:55:33Z","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":"In this paper, we compare various methods to compress a text using a neural model. We find that extracting tokens as latent variables significantly outperforms the state-of-the-art discrete latent variable models such as VQ-VAE. Furthermore, we compare various extractive compression schemes. There are two best-performing methods that perform equally. One method is to simply choose the tokens with the highest tf-idf scores. Another is to train a bidirectional language model similar to ELMo and choose the tokens with the highest loss. If we consider any subsequence of a text to be a text in a br","authors_text":"Aran Komatsuzaki","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-14T02:02:18Z","title":"Extractive Summary as Discrete Latent Variables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05542","kind":"arxiv","version":2},"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":"sha256:8b60d6fd6ddb93616336f9e90baf1e98892b4a298013650109b0d68e8acb0b1e","target":"record","created_at":"2026-05-17T23:55:33Z","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":"860e49e161e64c18991eab71e772b51895bf3f6833d40d5a341a51dd09f7b57e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-14T02:02:18Z","title_canon_sha256":"58275b91433dbfc96ee53d159c9f2e42190a9e2423e73460f4fd7f351c846c9c"},"schema_version":"1.0","source":{"id":"1811.05542","kind":"arxiv","version":2}},"canonical_sha256":"be49dc17928dff56103fedfdf616fb1c0190ac9eaed529dcf8ecae36f7159416","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be49dc17928dff56103fedfdf616fb1c0190ac9eaed529dcf8ecae36f7159416","first_computed_at":"2026-05-17T23:55:33.925227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:33.925227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8+rtkyr6t6/Sd36361+iRnc+20xGei16BtyxURqF0nyXlDlpekW3nscLDrGj45DD3U3ejyxKmI7oeDHkOtg8Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:33.925624Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.05542","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b60d6fd6ddb93616336f9e90baf1e98892b4a298013650109b0d68e8acb0b1e","sha256:55959c9b132e249a4923344c9035984079ad7bb5b6e5304c3f2138a575379ae2"],"state_sha256":"6e116023e38a9b5a1e76b0a0c4078161d2f4bdb8040e014c8dad382925e9ab81"}