{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GFYSPF6T5QVC3ACIW57HS6QONS","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":"f4f3d870f120101c0d34b895a6aba99d3dfa3b758587ba7f6b62be0b3583a8fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T20:01:51Z","title_canon_sha256":"79c2abb71d66c40fe39edfc211f381430f927486e4eb8fa1ac733fc87a4dda31"},"schema_version":"1.0","source":{"id":"1909.04130","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.04130","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"1909.04130v1","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04130","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"GFYSPF6T5QVC","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"GFYSPF6T5QVC3ACI","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"GFYSPF6T","created_at":"2026-07-05T00:03:18Z"}],"graph_snapshots":[{"event_id":"sha256:7279fdd9e7a17908279d606c0f09c62ce94e5e274ba4d83b2e22da90e23b718c","target":"graph","created_at":"2026-07-05T00:03:18Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.04130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep, possibly bidirectional, neural network with an objective related to language modeling, for which training data is plentiful; and (ii) using the trained network to derive contextual representations that are far richer than standard linear word embeddings such as word2vec, and thus result in important gains. In this work, we wonder whether the opposite perspective i","authors_text":"Jerome R. Bellegarda, Lyan Verwimp","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T20:01:51Z","title":"Reverse Transfer Learning: Can Word Embeddings Trained for Different NLP Tasks Improve Neural Language Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04130","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:da56095f9ca6a0f46411aa8428b4b64440a9739a4a62afc3b900b4fea21cdfee","target":"record","created_at":"2026-07-05T00:03:18Z","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":"f4f3d870f120101c0d34b895a6aba99d3dfa3b758587ba7f6b62be0b3583a8fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T20:01:51Z","title_canon_sha256":"79c2abb71d66c40fe39edfc211f381430f927486e4eb8fa1ac733fc87a4dda31"},"schema_version":"1.0","source":{"id":"1909.04130","kind":"arxiv","version":1}},"canonical_sha256":"31712797d3ec2a2d8048b77e797a0e6c9c2231369da9db2a4d01201e95aafc5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31712797d3ec2a2d8048b77e797a0e6c9c2231369da9db2a4d01201e95aafc5b","first_computed_at":"2026-07-05T00:03:18.965951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:03:18.965951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UCTm4O/IHGPrXfqL7gecm/2C7E2U4s7TC5XE9K4jW1im29L9H580fnylZJLLcSOFsN1H9WZesOT0N5naWo21DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:03:18.966362Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.04130","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da56095f9ca6a0f46411aa8428b4b64440a9739a4a62afc3b900b4fea21cdfee","sha256:7279fdd9e7a17908279d606c0f09c62ce94e5e274ba4d83b2e22da90e23b718c"],"state_sha256":"9349c7813ff44adb8423cff8463a88e56a71b6ca99d66dc56d606d0f714eff78"}