{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4CHWW74NJQWAPR3E52Y5OMGOE7","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":"24bd20fae9f131de7f35efb23a0b747fe1c9a5f79912b8023c89167e33195857","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T05:49:34Z","title_canon_sha256":"6d985a60cd71e1ea0add380652df168d5fd073d72341f8d11a5f15358f67cfea"},"schema_version":"1.0","source":{"id":"1902.04247","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04247","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04247v2","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04247","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"4CHWW74NJQWA","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4CHWW74NJQWAPR3E","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4CHWW74N","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:525ce1c9e655d69d1d9d8c6545c67c780e033da85e47aeaa806ea645c60ef811","target":"graph","created_at":"2026-05-17T23:54:06Z","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":"Learning sentence vectors from an unlabeled corpus has attracted attention because such vectors can represent sentences in a lower dimensional and continuous space. Simple heuristics using pre-trained word vectors are widely applied to machine learning tasks. However, they are not well understood from a theoretical perspective. We analyze learning sentence vectors from a transfer learning perspective by using a PAC-Bayes bound that enables us to understand existing heuristics. We show that simple heuristics such as averaging and inverse document frequency weighted averaging are derived by our ","authors_text":"Issei Sato, Kento Nozawa","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T05:49:34Z","title":"PAC-Bayes Analysis of Sentence Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04247","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":"sha256:0e384d93542be7807773e1c8aaa67bf65cd78df39ee266c7950f304c1cdfb666","target":"record","created_at":"2026-05-17T23:54:06Z","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":"24bd20fae9f131de7f35efb23a0b747fe1c9a5f79912b8023c89167e33195857","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T05:49:34Z","title_canon_sha256":"6d985a60cd71e1ea0add380652df168d5fd073d72341f8d11a5f15358f67cfea"},"schema_version":"1.0","source":{"id":"1902.04247","kind":"arxiv","version":2}},"canonical_sha256":"e08f6b7f8d4c2c07c764eeb1d730ce27cddd2e3d807d54efe4d850c01ee160bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e08f6b7f8d4c2c07c764eeb1d730ce27cddd2e3d807d54efe4d850c01ee160bf","first_computed_at":"2026-05-17T23:54:06.623822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:06.623822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r3hJlMt1wdHp3dxpcHV46W687WvOZE9ifHxuMbvWfvR5bbZOgf2NjLrJF7a3wE2KoIHHsCD49l1eJ3WVChfVBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:06.624344Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.04247","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e384d93542be7807773e1c8aaa67bf65cd78df39ee266c7950f304c1cdfb666","sha256:525ce1c9e655d69d1d9d8c6545c67c780e033da85e47aeaa806ea645c60ef811"],"state_sha256":"82e54539190517cc0a1fe6fd554b8ef53f57bec743e9d31a1fc4331ca3f44235"}