{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KXAGYYONERBX65JQBK2UXESDTS","short_pith_number":"pith:KXAGYYON","schema_version":"1.0","canonical_sha256":"55c06c61cd24437f75300ab54b92439c91fbe44e3fb5f96677c2d6c8b4743e26","source":{"kind":"arxiv","id":"1708.00553","version":1},"attestation_state":"computed","paper":{"title":"Low-Rank Hidden State Embeddings for Viterbi Sequence Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew McCallum, David Belanger, Dung Thai, Luke Vilnis, Shikhar Murty, Trapit Bansal","submitted_at":"2017-08-02T00:05:10Z","abstract_excerpt":"In textual information extraction and other sequence labeling tasks it is now common to use recurrent neural networks (such as LSTM) to form rich embedded representations of long-term input co-occurrence patterns. Representation of output co-occurrence patterns is typically limited to a hand-designed graphical model, such as a linear-chain CRF representing short-term Markov dependencies among successive labels. This paper presents a method that learns embedded representations of latent output structure in sequence data. Our model takes the form of a finite-state machine with a large number of "},"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":"1708.00553","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-02T00:05:10Z","cross_cats_sorted":[],"title_canon_sha256":"f23ef02f904677694392d702d96f9aa14815df20bb02ac006842206a4fc68b03","abstract_canon_sha256":"2c0a749f3179d619d943d7313d5e0910db36df5c215763ee3b08ae17fd02856c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:45.433073Z","signature_b64":"/o0VVib8OlhAPd6F001tdI4IzDYYuFxOaT+3GvXN2UOkgMXV0BwSFYFuO/5i288SXYc9NBVDlQy5/IWuw+atAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55c06c61cd24437f75300ab54b92439c91fbe44e3fb5f96677c2d6c8b4743e26","last_reissued_at":"2026-05-18T00:38:45.432454Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:45.432454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Rank Hidden State Embeddings for Viterbi Sequence Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew McCallum, David Belanger, Dung Thai, Luke Vilnis, Shikhar Murty, Trapit Bansal","submitted_at":"2017-08-02T00:05:10Z","abstract_excerpt":"In textual information extraction and other sequence labeling tasks it is now common to use recurrent neural networks (such as LSTM) to form rich embedded representations of long-term input co-occurrence patterns. Representation of output co-occurrence patterns is typically limited to a hand-designed graphical model, such as a linear-chain CRF representing short-term Markov dependencies among successive labels. This paper presents a method that learns embedded representations of latent output structure in sequence data. Our model takes the form of a finite-state machine with a large number of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00553","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1708.00553","created_at":"2026-05-18T00:38:45.432550+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.00553v1","created_at":"2026-05-18T00:38:45.432550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00553","created_at":"2026-05-18T00:38:45.432550+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXAGYYONERBX","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXAGYYONERBX65JQ","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXAGYYON","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXAGYYONERBX65JQBK2UXESDTS","json":"https://pith.science/pith/KXAGYYONERBX65JQBK2UXESDTS.json","graph_json":"https://pith.science/api/pith-number/KXAGYYONERBX65JQBK2UXESDTS/graph.json","events_json":"https://pith.science/api/pith-number/KXAGYYONERBX65JQBK2UXESDTS/events.json","paper":"https://pith.science/paper/KXAGYYON"},"agent_actions":{"view_html":"https://pith.science/pith/KXAGYYONERBX65JQBK2UXESDTS","download_json":"https://pith.science/pith/KXAGYYONERBX65JQBK2UXESDTS.json","view_paper":"https://pith.science/paper/KXAGYYON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.00553&json=true","fetch_graph":"https://pith.science/api/pith-number/KXAGYYONERBX65JQBK2UXESDTS/graph.json","fetch_events":"https://pith.science/api/pith-number/KXAGYYONERBX65JQBK2UXESDTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXAGYYONERBX65JQBK2UXESDTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXAGYYONERBX65JQBK2UXESDTS/action/storage_attestation","attest_author":"https://pith.science/pith/KXAGYYONERBX65JQBK2UXESDTS/action/author_attestation","sign_citation":"https://pith.science/pith/KXAGYYONERBX65JQBK2UXESDTS/action/citation_signature","submit_replication":"https://pith.science/pith/KXAGYYONERBX65JQBK2UXESDTS/action/replication_record"}},"created_at":"2026-05-18T00:38:45.432550+00:00","updated_at":"2026-05-18T00:38:45.432550+00:00"}