{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7T2OO4CGQESNF7FUBDROKFYGUS","short_pith_number":"pith:7T2OO4CG","schema_version":"1.0","canonical_sha256":"fcf4e770468124d2fcb408e2e51706a48f4253831e80d693a9e5c7095058786a","source":{"kind":"arxiv","id":"1811.11456","version":2},"attestation_state":"computed","paper":{"title":"GIRNet: Interleaved Multi-Task Recurrent State Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Divam Gupta, Soumen Chakrabarti, Tanmoy Chakraborty","submitted_at":"2018-11-28T09:20:13Z","abstract_excerpt":"In several natural language tasks, labeled sequences are available in separate domains (say, languages), but the goal is to label sequences with mixed domain (such as code-switched text). Or, we may have available models for labeling whole passages (say, with sentiments), which we would like to exploit toward better position-specific label inference (say, target-dependent sentiment annotation). A key characteristic shared across such tasks is that different positions in a primary instance can benefit from different `experts' trained from auxiliary data, but labeled primary instances are scarce"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1811.11456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-28T09:20:13Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"4e9e05f64e0cef06371e2515eba771397b71f50a25a71be71443c679560f0991","abstract_canon_sha256":"851fbec5850ff7d89f524752d9e755bad70f64206b63c44fd398741da80e99d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:30.693868Z","signature_b64":"2u2LNIDhQuY1QO3ZWWgl0FuS8qLzEItHlBfdM1onwrLIN0QnPGfZ1FnTusurR3/zV7Zu3g2pYWYGRl9H9KM3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcf4e770468124d2fcb408e2e51706a48f4253831e80d693a9e5c7095058786a","last_reissued_at":"2026-05-17T23:57:30.693243Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:30.693243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GIRNet: Interleaved Multi-Task Recurrent State Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Divam Gupta, Soumen Chakrabarti, Tanmoy Chakraborty","submitted_at":"2018-11-28T09:20:13Z","abstract_excerpt":"In several natural language tasks, labeled sequences are available in separate domains (say, languages), but the goal is to label sequences with mixed domain (such as code-switched text). Or, we may have available models for labeling whole passages (say, with sentiments), which we would like to exploit toward better position-specific label inference (say, target-dependent sentiment annotation). A key characteristic shared across such tasks is that different positions in a primary instance can benefit from different `experts' trained from auxiliary data, but labeled primary instances are scarce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11456","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1811.11456","created_at":"2026-05-17T23:57:30.693394+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11456v2","created_at":"2026-05-17T23:57:30.693394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11456","created_at":"2026-05-17T23:57:30.693394+00:00"},{"alias_kind":"pith_short_12","alias_value":"7T2OO4CGQESN","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7T2OO4CGQESNF7FU","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7T2OO4CG","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04072","citing_title":"Multitask Learning for Blackmarket Tweet Detection","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7T2OO4CGQESNF7FUBDROKFYGUS","json":"https://pith.science/pith/7T2OO4CGQESNF7FUBDROKFYGUS.json","graph_json":"https://pith.science/api/pith-number/7T2OO4CGQESNF7FUBDROKFYGUS/graph.json","events_json":"https://pith.science/api/pith-number/7T2OO4CGQESNF7FUBDROKFYGUS/events.json","paper":"https://pith.science/paper/7T2OO4CG"},"agent_actions":{"view_html":"https://pith.science/pith/7T2OO4CGQESNF7FUBDROKFYGUS","download_json":"https://pith.science/pith/7T2OO4CGQESNF7FUBDROKFYGUS.json","view_paper":"https://pith.science/paper/7T2OO4CG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11456&json=true","fetch_graph":"https://pith.science/api/pith-number/7T2OO4CGQESNF7FUBDROKFYGUS/graph.json","fetch_events":"https://pith.science/api/pith-number/7T2OO4CGQESNF7FUBDROKFYGUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7T2OO4CGQESNF7FUBDROKFYGUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7T2OO4CGQESNF7FUBDROKFYGUS/action/storage_attestation","attest_author":"https://pith.science/pith/7T2OO4CGQESNF7FUBDROKFYGUS/action/author_attestation","sign_citation":"https://pith.science/pith/7T2OO4CGQESNF7FUBDROKFYGUS/action/citation_signature","submit_replication":"https://pith.science/pith/7T2OO4CGQESNF7FUBDROKFYGUS/action/replication_record"}},"created_at":"2026-05-17T23:57:30.693394+00:00","updated_at":"2026-05-17T23:57:30.693394+00:00"}