{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YIXYCFWDQ6FD7WBVTWQGDJ7CQI","short_pith_number":"pith:YIXYCFWD","canonical_record":{"source":{"id":"1906.09532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-23T02:00:40Z","cross_cats_sorted":[],"title_canon_sha256":"e10008d6788204df2bb9b4f2712e096a4fd4106c97ac7d0f14840bea2672eb58","abstract_canon_sha256":"55ce37f0b72802e2eb34d8dc18e11fc72d0816e5f8d4afa0677da5cbeb2a9aa3"},"schema_version":"1.0"},"canonical_sha256":"c22f8116c3878a3fd8359da061a7e2823f014dc7531fda3d02e43f379705e7cf","source":{"kind":"arxiv","id":"1906.09532","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09532","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09532v1","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09532","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"YIXYCFWDQ6FD","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YIXYCFWDQ6FD7WBV","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YIXYCFWD","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YIXYCFWDQ6FD7WBVTWQGDJ7CQI","target":"record","payload":{"canonical_record":{"source":{"id":"1906.09532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-23T02:00:40Z","cross_cats_sorted":[],"title_canon_sha256":"e10008d6788204df2bb9b4f2712e096a4fd4106c97ac7d0f14840bea2672eb58","abstract_canon_sha256":"55ce37f0b72802e2eb34d8dc18e11fc72d0816e5f8d4afa0677da5cbeb2a9aa3"},"schema_version":"1.0"},"canonical_sha256":"c22f8116c3878a3fd8359da061a7e2823f014dc7531fda3d02e43f379705e7cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:37.698637Z","signature_b64":"eOjc5HIxhVrKorFRNg6ZKFcDYMN1Yervoo53TuDZCUTL/gCAMWLRcBc5YzDoYQD+REQTla4Q58FgxL3lILMpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c22f8116c3878a3fd8359da061a7e2823f014dc7531fda3d02e43f379705e7cf","last_reissued_at":"2026-05-17T23:42:37.697886Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:37.697886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.09532","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":"2026-05-17T23:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dgoEcH5pADDVDUG3jhY6d3SR7dZinO6tG4u+87S5BoQshzsrfGwnlj4yO3yckSggDyqend7zD8Uj8GpqeiTyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:54:29.414069Z"},"content_sha256":"860341c5240ce70553c2693aef200e685c59cff61126fb05d0441cf180b8a06c","schema_version":"1.0","event_id":"sha256:860341c5240ce70553c2693aef200e685c59cff61126fb05d0441cf180b8a06c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YIXYCFWDQ6FD7WBVTWQGDJ7CQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Smaller Text Classifiers with Discriminative Cluster Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Gimpel, Mingda Chen","submitted_at":"2019-06-23T02:00:40Z","abstract_excerpt":"Word embedding parameters often dominate overall model sizes in neural methods for natural language processing. We reduce deployed model sizes of text classifiers by learning a hard word clustering in an end-to-end manner. We use the Gumbel-Softmax distribution to maximize over the latent clustering while minimizing the task loss. We propose variations that selectively assign additional parameters to words, which further improves accuracy while still remaining parameter-efficient."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09532","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":"2026-05-17T23:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ktwkOW1nc0D4zal6SOCNXgKj+Ssrg1vxd+LK1rGt026Yl0g3XjAMCSZDBEGgrX+jPE2xn07eMmYcAJzuRWZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:54:29.414427Z"},"content_sha256":"7afe29e42ff09bc1856e9e76fde566b57383db55d678ca935e7783bc604dfab5","schema_version":"1.0","event_id":"sha256:7afe29e42ff09bc1856e9e76fde566b57383db55d678ca935e7783bc604dfab5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIXYCFWDQ6FD7WBVTWQGDJ7CQI/bundle.json","state_url":"https://pith.science/pith/YIXYCFWDQ6FD7WBVTWQGDJ7CQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIXYCFWDQ6FD7WBVTWQGDJ7CQI/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":"2026-06-20T02:54:29Z","links":{"resolver":"https://pith.science/pith/YIXYCFWDQ6FD7WBVTWQGDJ7CQI","bundle":"https://pith.science/pith/YIXYCFWDQ6FD7WBVTWQGDJ7CQI/bundle.json","state":"https://pith.science/pith/YIXYCFWDQ6FD7WBVTWQGDJ7CQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIXYCFWDQ6FD7WBVTWQGDJ7CQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YIXYCFWDQ6FD7WBVTWQGDJ7CQI","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":"55ce37f0b72802e2eb34d8dc18e11fc72d0816e5f8d4afa0677da5cbeb2a9aa3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-23T02:00:40Z","title_canon_sha256":"e10008d6788204df2bb9b4f2712e096a4fd4106c97ac7d0f14840bea2672eb58"},"schema_version":"1.0","source":{"id":"1906.09532","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09532","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09532v1","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09532","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"YIXYCFWDQ6FD","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YIXYCFWDQ6FD7WBV","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YIXYCFWD","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:7afe29e42ff09bc1856e9e76fde566b57383db55d678ca935e7783bc604dfab5","target":"graph","created_at":"2026-05-17T23:42:37Z","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":"Word embedding parameters often dominate overall model sizes in neural methods for natural language processing. We reduce deployed model sizes of text classifiers by learning a hard word clustering in an end-to-end manner. We use the Gumbel-Softmax distribution to maximize over the latent clustering while minimizing the task loss. We propose variations that selectively assign additional parameters to words, which further improves accuracy while still remaining parameter-efficient.","authors_text":"Kevin Gimpel, Mingda Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-23T02:00:40Z","title":"Smaller Text Classifiers with Discriminative Cluster Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09532","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":"sha256:860341c5240ce70553c2693aef200e685c59cff61126fb05d0441cf180b8a06c","target":"record","created_at":"2026-05-17T23:42:37Z","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":"55ce37f0b72802e2eb34d8dc18e11fc72d0816e5f8d4afa0677da5cbeb2a9aa3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-23T02:00:40Z","title_canon_sha256":"e10008d6788204df2bb9b4f2712e096a4fd4106c97ac7d0f14840bea2672eb58"},"schema_version":"1.0","source":{"id":"1906.09532","kind":"arxiv","version":1}},"canonical_sha256":"c22f8116c3878a3fd8359da061a7e2823f014dc7531fda3d02e43f379705e7cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c22f8116c3878a3fd8359da061a7e2823f014dc7531fda3d02e43f379705e7cf","first_computed_at":"2026-05-17T23:42:37.697886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:37.697886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eOjc5HIxhVrKorFRNg6ZKFcDYMN1Yervoo53TuDZCUTL/gCAMWLRcBc5YzDoYQD+REQTla4Q58FgxL3lILMpCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:37.698637Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09532","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:860341c5240ce70553c2693aef200e685c59cff61126fb05d0441cf180b8a06c","sha256:7afe29e42ff09bc1856e9e76fde566b57383db55d678ca935e7783bc604dfab5"],"state_sha256":"74d1f11b69f92df966b22b1fd884a63fc21864d2760c0696a7575ade8f79f6f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kmSVpUZWvAJN2bYiA7nkAXu3+8OLb614R5oqRRCylgUuJ2jH+vxngAhrdXt0E4WZ6Ir51ETPnLco7sdSnkR/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T02:54:29.416623Z","bundle_sha256":"76df3d7e9336b76e5a569a198a6a04094d95a6ea1cb02ae3f9db47684af84739"}}