{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:XUKTUDEKPQW3FF4CSYD3NI5E2D","short_pith_number":"pith:XUKTUDEK","canonical_record":{"source":{"id":"1604.00461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-02T04:59:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"762a07509d2d6a1f5f38ec4bb821807fb4c4060b89ae64dcd239f41717eaecef","abstract_canon_sha256":"c5a3fd4cc17541823cb0dd04fbb86a838733659b7e4749a439cf1dde56e38fbe"},"schema_version":"1.0"},"canonical_sha256":"bd153a0c8a7c2db297829607b6a3a4d0f7b2e1bb17e7d5be7bd563d0ee06b78c","source":{"kind":"arxiv","id":"1604.00461","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.00461","created_at":"2026-05-18T01:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"1604.00461v1","created_at":"2026-05-18T01:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00461","created_at":"2026-05-18T01:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"XUKTUDEKPQW3","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XUKTUDEKPQW3FF4C","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XUKTUDEK","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:XUKTUDEKPQW3FF4CSYD3NI5E2D","target":"record","payload":{"canonical_record":{"source":{"id":"1604.00461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-02T04:59:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"762a07509d2d6a1f5f38ec4bb821807fb4c4060b89ae64dcd239f41717eaecef","abstract_canon_sha256":"c5a3fd4cc17541823cb0dd04fbb86a838733659b7e4749a439cf1dde56e38fbe"},"schema_version":"1.0"},"canonical_sha256":"bd153a0c8a7c2db297829607b6a3a4d0f7b2e1bb17e7d5be7bd563d0ee06b78c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:49.554172Z","signature_b64":"KfRz/OjDpLRcBeU06fly7WmKFfuK8i0SRV5IqPZ0DTL51Z1yF+xbl51NO5xwJJ+UMnq1s6S0JaMMGD3GPZ0qCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd153a0c8a7c2db297829607b6a3a4d0f7b2e1bb17e7d5be7bd563d0ee06b78c","last_reissued_at":"2026-05-18T01:17:49.553533Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:49.553533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.00461","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":"2026-05-18T01:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SfuAcVwv9BbBVYOcwvh0+MkLW8LrgsXHDyyGI24ZcMV5g8qFnpUEojujDiZmDWoyIaR7pcHUtANQBCj6UXuQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:30:49.784798Z"},"content_sha256":"8b0210d6e18ee54fdccc9c69cb93fa4c0398a35196d19c31718311cdfc2392c6","schema_version":"1.0","event_id":"sha256:8b0210d6e18ee54fdccc9c69cb93fa4c0398a35196d19c31718311cdfc2392c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:XUKTUDEKPQW3FF4CSYD3NI5E2D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Embedding Lexical Features via Low-Rank Tensors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mark Dredze, Matthew Gormley, Mo Yu, Raman Arora","submitted_at":"2016-04-02T04:59:21Z","abstract_excerpt":"Modern NLP models rely heavily on engineered features, which often combine word and contextual information into complex lexical features. Such combination results in large numbers of features, which can lead to over-fitting. We present a new model that represents complex lexical features---comprised of parts for words, contextual information and labels---in a tensor that captures conjunction information among these parts. We apply low-rank tensor approximations to the corresponding parameter tensors to reduce the parameter space and improve prediction speed. Furthermore, we investigate two met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00461","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":"2026-05-18T01:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LTMKdvRBGVdp9+JtNsHwAJXyv/SvqNV+WVIDaNYMKoX9fyL2zyFup8JYzDM0xkOzkzNWUN/uTKwdnyahqwf2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:30:49.785145Z"},"content_sha256":"45fba60385ea47f77edb0a3b1e03fd8afc47b18f75e14c5d7cf5782d90903758","schema_version":"1.0","event_id":"sha256:45fba60385ea47f77edb0a3b1e03fd8afc47b18f75e14c5d7cf5782d90903758"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUKTUDEKPQW3FF4CSYD3NI5E2D/bundle.json","state_url":"https://pith.science/pith/XUKTUDEKPQW3FF4CSYD3NI5E2D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUKTUDEKPQW3FF4CSYD3NI5E2D/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":"2026-06-01T21:30:49Z","links":{"resolver":"https://pith.science/pith/XUKTUDEKPQW3FF4CSYD3NI5E2D","bundle":"https://pith.science/pith/XUKTUDEKPQW3FF4CSYD3NI5E2D/bundle.json","state":"https://pith.science/pith/XUKTUDEKPQW3FF4CSYD3NI5E2D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUKTUDEKPQW3FF4CSYD3NI5E2D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:XUKTUDEKPQW3FF4CSYD3NI5E2D","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":"c5a3fd4cc17541823cb0dd04fbb86a838733659b7e4749a439cf1dde56e38fbe","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-02T04:59:21Z","title_canon_sha256":"762a07509d2d6a1f5f38ec4bb821807fb4c4060b89ae64dcd239f41717eaecef"},"schema_version":"1.0","source":{"id":"1604.00461","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.00461","created_at":"2026-05-18T01:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"1604.00461v1","created_at":"2026-05-18T01:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00461","created_at":"2026-05-18T01:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"XUKTUDEKPQW3","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XUKTUDEKPQW3FF4C","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XUKTUDEK","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:45fba60385ea47f77edb0a3b1e03fd8afc47b18f75e14c5d7cf5782d90903758","target":"graph","created_at":"2026-05-18T01:17:49Z","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":"Modern NLP models rely heavily on engineered features, which often combine word and contextual information into complex lexical features. Such combination results in large numbers of features, which can lead to over-fitting. We present a new model that represents complex lexical features---comprised of parts for words, contextual information and labels---in a tensor that captures conjunction information among these parts. We apply low-rank tensor approximations to the corresponding parameter tensors to reduce the parameter space and improve prediction speed. Furthermore, we investigate two met","authors_text":"Mark Dredze, Matthew Gormley, Mo Yu, Raman Arora","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-02T04:59:21Z","title":"Embedding Lexical Features via Low-Rank Tensors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00461","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":"sha256:8b0210d6e18ee54fdccc9c69cb93fa4c0398a35196d19c31718311cdfc2392c6","target":"record","created_at":"2026-05-18T01:17:49Z","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":"c5a3fd4cc17541823cb0dd04fbb86a838733659b7e4749a439cf1dde56e38fbe","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-02T04:59:21Z","title_canon_sha256":"762a07509d2d6a1f5f38ec4bb821807fb4c4060b89ae64dcd239f41717eaecef"},"schema_version":"1.0","source":{"id":"1604.00461","kind":"arxiv","version":1}},"canonical_sha256":"bd153a0c8a7c2db297829607b6a3a4d0f7b2e1bb17e7d5be7bd563d0ee06b78c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd153a0c8a7c2db297829607b6a3a4d0f7b2e1bb17e7d5be7bd563d0ee06b78c","first_computed_at":"2026-05-18T01:17:49.553533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:49.553533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KfRz/OjDpLRcBeU06fly7WmKFfuK8i0SRV5IqPZ0DTL51Z1yF+xbl51NO5xwJJ+UMnq1s6S0JaMMGD3GPZ0qCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:49.554172Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.00461","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b0210d6e18ee54fdccc9c69cb93fa4c0398a35196d19c31718311cdfc2392c6","sha256:45fba60385ea47f77edb0a3b1e03fd8afc47b18f75e14c5d7cf5782d90903758"],"state_sha256":"a6e07bc86c78f5ce5c34e870afac824d6a0a21fa71f2b86cb4129575392f16e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iz6qSGFianr3Adx7yLAE/EyohKZ8EEPAD3Qj1Zj/6uu/bosdw21YQJJNMqq4M5OoBINzA+WQd3KyLX20KhIOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:30:49.787188Z","bundle_sha256":"0ccb7a6215844783b258d1a7888ee165928f89895ed5bb797d0f3e7523c6a288"}}