{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HK4VGE4JVMNWIBZCT7VIEIZGTQ","short_pith_number":"pith:HK4VGE4J","canonical_record":{"source":{"id":"1902.09092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-25T05:04:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55cc4c8657e1c4015810816db8eaa1d2f39812f5defbbaba459c43206a149083","abstract_canon_sha256":"f3f3208ec1b20c8751f79c530a8d851da53e1066fe1db68d6bf44a934c35d834"},"schema_version":"1.0"},"canonical_sha256":"3ab9531389ab1b6407229fea8223269c10c00466c4b90b4bdf9624e3459326bc","source":{"kind":"arxiv","id":"1902.09092","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09092","created_at":"2026-05-17T23:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09092v1","created_at":"2026-05-17T23:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09092","created_at":"2026-05-17T23:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"HK4VGE4JVMNW","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HK4VGE4JVMNWIBZC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HK4VGE4J","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HK4VGE4JVMNWIBZCT7VIEIZGTQ","target":"record","payload":{"canonical_record":{"source":{"id":"1902.09092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-25T05:04:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55cc4c8657e1c4015810816db8eaa1d2f39812f5defbbaba459c43206a149083","abstract_canon_sha256":"f3f3208ec1b20c8751f79c530a8d851da53e1066fe1db68d6bf44a934c35d834"},"schema_version":"1.0"},"canonical_sha256":"3ab9531389ab1b6407229fea8223269c10c00466c4b90b4bdf9624e3459326bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:46.683109Z","signature_b64":"CsSP/oWKDAaNnI1cO59wNHGhAp4/IOzr1Az0GgpphdL/3NN0PLNVtBj9DfaGwkYEprhGtUC0NBRUWBuHUY3jCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ab9531389ab1b6407229fea8223269c10c00466c4b90b4bdf9624e3459326bc","last_reissued_at":"2026-05-17T23:52:46.682490Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:46.682490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.09092","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":"2026-05-17T23:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lTF1YRJ4v/YrAVxk0213imNQxZQqpFR+S+Ze1NQ6k1UIX4PawEAAR3aWnO1taXHBvKLna1NiuXzxMVwCn3xIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T06:33:39.022256Z"},"content_sha256":"ce7f14f175d56119693c5f89d881eafa26929188f52ce936297b640d03e12fe1","schema_version":"1.0","event_id":"sha256:ce7f14f175d56119693c5f89d881eafa26929188f52ce936297b640d03e12fe1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HK4VGE4JVMNWIBZCT7VIEIZGTQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transfer Learning for Sequences via Learning to Collocate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangyu Zheng, Sihang Jiang, Wanyun Cui, Wei Wang, Zhiqiang Shen","submitted_at":"2019-02-25T05:04:11Z","abstract_excerpt":"Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfer learning, usually enabled by recurrent neural network (RNN), represents the sequential information transfer. RNN uses a chain of repeating cells to model the sequence data. However, previous studies of neural network based transfer learning simply represents the whole sentence by a single vector, which is unfeasible for seq2seq and sequence labeling. Meanwhile, such layer-wise transfer learning mechanisms lose the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09092","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":"2026-05-17T23:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tzhgAKaZVX8zh5o4oklln1SFf3jJOKnpKIR9BIZi0G56w3ctwot6dTp/0DXeXW6/UO06gQlsFZjglpRnJUcjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T06:33:39.022615Z"},"content_sha256":"e25add4ad876120d747645d6bdf12f72aaee6f6c40cf3b95c1a452c1d0539b42","schema_version":"1.0","event_id":"sha256:e25add4ad876120d747645d6bdf12f72aaee6f6c40cf3b95c1a452c1d0539b42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HK4VGE4JVMNWIBZCT7VIEIZGTQ/bundle.json","state_url":"https://pith.science/pith/HK4VGE4JVMNWIBZCT7VIEIZGTQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HK4VGE4JVMNWIBZCT7VIEIZGTQ/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":"2026-06-02T06:33:39Z","links":{"resolver":"https://pith.science/pith/HK4VGE4JVMNWIBZCT7VIEIZGTQ","bundle":"https://pith.science/pith/HK4VGE4JVMNWIBZCT7VIEIZGTQ/bundle.json","state":"https://pith.science/pith/HK4VGE4JVMNWIBZCT7VIEIZGTQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HK4VGE4JVMNWIBZCT7VIEIZGTQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HK4VGE4JVMNWIBZCT7VIEIZGTQ","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":"f3f3208ec1b20c8751f79c530a8d851da53e1066fe1db68d6bf44a934c35d834","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-25T05:04:11Z","title_canon_sha256":"55cc4c8657e1c4015810816db8eaa1d2f39812f5defbbaba459c43206a149083"},"schema_version":"1.0","source":{"id":"1902.09092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09092","created_at":"2026-05-17T23:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09092v1","created_at":"2026-05-17T23:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09092","created_at":"2026-05-17T23:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"HK4VGE4JVMNW","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HK4VGE4JVMNWIBZC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HK4VGE4J","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:e25add4ad876120d747645d6bdf12f72aaee6f6c40cf3b95c1a452c1d0539b42","target":"graph","created_at":"2026-05-17T23:52:46Z","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":"Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfer learning, usually enabled by recurrent neural network (RNN), represents the sequential information transfer. RNN uses a chain of repeating cells to model the sequence data. However, previous studies of neural network based transfer learning simply represents the whole sentence by a single vector, which is unfeasible for seq2seq and sequence labeling. Meanwhile, such layer-wise transfer learning mechanisms lose the ","authors_text":"Guangyu Zheng, Sihang Jiang, Wanyun Cui, Wei Wang, Zhiqiang Shen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-25T05:04:11Z","title":"Transfer Learning for Sequences via Learning to Collocate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09092","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:ce7f14f175d56119693c5f89d881eafa26929188f52ce936297b640d03e12fe1","target":"record","created_at":"2026-05-17T23:52:46Z","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":"f3f3208ec1b20c8751f79c530a8d851da53e1066fe1db68d6bf44a934c35d834","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-25T05:04:11Z","title_canon_sha256":"55cc4c8657e1c4015810816db8eaa1d2f39812f5defbbaba459c43206a149083"},"schema_version":"1.0","source":{"id":"1902.09092","kind":"arxiv","version":1}},"canonical_sha256":"3ab9531389ab1b6407229fea8223269c10c00466c4b90b4bdf9624e3459326bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ab9531389ab1b6407229fea8223269c10c00466c4b90b4bdf9624e3459326bc","first_computed_at":"2026-05-17T23:52:46.682490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:46.682490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CsSP/oWKDAaNnI1cO59wNHGhAp4/IOzr1Az0GgpphdL/3NN0PLNVtBj9DfaGwkYEprhGtUC0NBRUWBuHUY3jCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:46.683109Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.09092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce7f14f175d56119693c5f89d881eafa26929188f52ce936297b640d03e12fe1","sha256:e25add4ad876120d747645d6bdf12f72aaee6f6c40cf3b95c1a452c1d0539b42"],"state_sha256":"f9d449e98b966ac03fe03150d586dc9ef1cac4c8f875566de5a88cb85b82d14e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vlGcSvK1DDW486AOaS1JUjGoToHAL2rLGbUJ/Mo5bjCgmIBzLlpjzO/ePayAPMRRmqtaDA6kj8sFw96+EjjFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T06:33:39.024497Z","bundle_sha256":"4fd9d2476095b0c23e6d3003f6954a8bc8a08aada133433b9b0ea98f368f84c7"}}