{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4CHWW74NJQWAPR3E52Y5OMGOE7","short_pith_number":"pith:4CHWW74N","canonical_record":{"source":{"id":"1902.04247","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T05:49:34Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"6d985a60cd71e1ea0add380652df168d5fd073d72341f8d11a5f15358f67cfea","abstract_canon_sha256":"24bd20fae9f131de7f35efb23a0b747fe1c9a5f79912b8023c89167e33195857"},"schema_version":"1.0"},"canonical_sha256":"e08f6b7f8d4c2c07c764eeb1d730ce27cddd2e3d807d54efe4d850c01ee160bf","source":{"kind":"arxiv","id":"1902.04247","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4CHWW74NJQWAPR3E52Y5OMGOE7","target":"record","payload":{"canonical_record":{"source":{"id":"1902.04247","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T05:49:34Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"6d985a60cd71e1ea0add380652df168d5fd073d72341f8d11a5f15358f67cfea","abstract_canon_sha256":"24bd20fae9f131de7f35efb23a0b747fe1c9a5f79912b8023c89167e33195857"},"schema_version":"1.0"},"canonical_sha256":"e08f6b7f8d4c2c07c764eeb1d730ce27cddd2e3d807d54efe4d850c01ee160bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:06.624344Z","signature_b64":"r3hJlMt1wdHp3dxpcHV46W687WvOZE9ifHxuMbvWfvR5bbZOgf2NjLrJF7a3wE2KoIHHsCD49l1eJ3WVChfVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e08f6b7f8d4c2c07c764eeb1d730ce27cddd2e3d807d54efe4d850c01ee160bf","last_reissued_at":"2026-05-17T23:54:06.623822Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:06.623822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.04247","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NyMj908119u2W37aHUN0zu0KAm3eSgFJyP0uLVIUNsxxaZSgu/uE9vPty1SNrcZJM+NBwiw47XEBce8WdsBnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T10:57:21.713466Z"},"content_sha256":"0e384d93542be7807773e1c8aaa67bf65cd78df39ee266c7950f304c1cdfb666","schema_version":"1.0","event_id":"sha256:0e384d93542be7807773e1c8aaa67bf65cd78df39ee266c7950f304c1cdfb666"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4CHWW74NJQWAPR3E52Y5OMGOE7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAC-Bayes Analysis of Sentence Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Issei Sato, Kento Nozawa","submitted_at":"2019-02-12T05:49:34Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04247","kind":"arxiv","version":2},"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":"2026-05-17T23:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VOtElVQrXwEQ1nJUeA1G5GNHhipNJQtcRaDDpulb5T4PQbC1PtOCvf0fVlt7G6gCdBDAZEQAdfbDSTQ46k8FAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T10:57:21.713839Z"},"content_sha256":"525ce1c9e655d69d1d9d8c6545c67c780e033da85e47aeaa806ea645c60ef811","schema_version":"1.0","event_id":"sha256:525ce1c9e655d69d1d9d8c6545c67c780e033da85e47aeaa806ea645c60ef811"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4CHWW74NJQWAPR3E52Y5OMGOE7/bundle.json","state_url":"https://pith.science/pith/4CHWW74NJQWAPR3E52Y5OMGOE7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4CHWW74NJQWAPR3E52Y5OMGOE7/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":"2026-07-24T10:57:21Z","links":{"resolver":"https://pith.science/pith/4CHWW74NJQWAPR3E52Y5OMGOE7","bundle":"https://pith.science/pith/4CHWW74NJQWAPR3E52Y5OMGOE7/bundle.json","state":"https://pith.science/pith/4CHWW74NJQWAPR3E52Y5OMGOE7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4CHWW74NJQWAPR3E52Y5OMGOE7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/IeA/ha67mzLj0yqWtc903i2dVE2UhOem8TES2z3mxBYdVIq9bm6GfcCU362DDL45sjNpJE48/c66k8S1ZkICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T10:57:21.715973Z","bundle_sha256":"27846b2da2b5b5214dfb72e9f7c22456aa0fa566d100b05bdc25992921ab4cc9"}}