{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HGSG2EVMYBACRKLH67M2GQHX6Q","short_pith_number":"pith:HGSG2EVM","canonical_record":{"source":{"id":"1904.04900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T20:39:07Z","cross_cats_sorted":[],"title_canon_sha256":"28763960536b104648733b2d8b722c380c98b38919e173ead299c9e4ed1cbaa4","abstract_canon_sha256":"e4ad6fb03955fa40bd8a62d05a0bcf4b4c487c3b44bc866caf55eff7c8fe4e20"},"schema_version":"1.0"},"canonical_sha256":"39a46d12acc04028a967f7d9a340f7f409436aee3005c14f1a8f43ce258887ed","source":{"kind":"arxiv","id":"1904.04900","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04900","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04900v1","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04900","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"HGSG2EVMYBAC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HGSG2EVMYBACRKLH","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HGSG2EVM","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HGSG2EVMYBACRKLH67M2GQHX6Q","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T20:39:07Z","cross_cats_sorted":[],"title_canon_sha256":"28763960536b104648733b2d8b722c380c98b38919e173ead299c9e4ed1cbaa4","abstract_canon_sha256":"e4ad6fb03955fa40bd8a62d05a0bcf4b4c487c3b44bc866caf55eff7c8fe4e20"},"schema_version":"1.0"},"canonical_sha256":"39a46d12acc04028a967f7d9a340f7f409436aee3005c14f1a8f43ce258887ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:57.720689Z","signature_b64":"icK83hOM00AfzkvDLe7vrU4l7NYUvSD8QZkXFRx4XnooFiZStaOZcLRkpUelSQHZDaYwkmy8qYxVUtFiXtteAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39a46d12acc04028a967f7d9a340f7f409436aee3005c14f1a8f43ce258887ed","last_reissued_at":"2026-05-17T23:48:57.720253Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:57.720253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04900","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":"2026-05-17T23:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NuXc7V1NNz5IA7GQuC34vmeu83A1/CkZAZaBNcHC5DLfIYjUXGTSxD8Dp1lwu+dRPeAsb3ZdYShYP7emIGHLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T01:58:52.671185Z"},"content_sha256":"f3b045cd133f89b29af13b8ca897eddedd07878d717f0cc19c6ce86800ccde6a","schema_version":"1.0","event_id":"sha256:f3b045cd133f89b29af13b8ca897eddedd07878d717f0cc19c6ce86800ccde6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HGSG2EVMYBACRKLH67M2GQHX6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Selection with Cluster-Based Language Difference Models and Cynical Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amittai Axelrod, Luc\\'ia Santamar\\'ia","submitted_at":"2019-04-09T20:39:07Z","abstract_excerpt":"We present and apply two methods for addressing the problem of selecting relevant training data out of a general pool for use in tasks such as machine translation. Building on existing work on class-based language difference models, we first introduce a cluster-based method that uses Brown clusters to condense the vocabulary of the corpora. Secondly, we implement the cynical data selection method, which incrementally constructs a training corpus to efficiently model the task corpus. Both the cluster-based and the cynical data selection approaches are used for the first time within a machine tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04900","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":"2026-05-17T23:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8GzVxhtE+NoCfMWHHPOFk7+PkmldwVpJGSwTd1mjtghmHVriNHIz2rCeD5Rm/fvYexb/12hrg3rnaKqoGMuZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T01:58:52.671931Z"},"content_sha256":"aa7276c2ddb4172bbc08466fdad13fdafcd7c8e9a0680bfbf7dd8f4c988e305f","schema_version":"1.0","event_id":"sha256:aa7276c2ddb4172bbc08466fdad13fdafcd7c8e9a0680bfbf7dd8f4c988e305f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HGSG2EVMYBACRKLH67M2GQHX6Q/bundle.json","state_url":"https://pith.science/pith/HGSG2EVMYBACRKLH67M2GQHX6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HGSG2EVMYBACRKLH67M2GQHX6Q/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":"2026-06-12T01:58:52Z","links":{"resolver":"https://pith.science/pith/HGSG2EVMYBACRKLH67M2GQHX6Q","bundle":"https://pith.science/pith/HGSG2EVMYBACRKLH67M2GQHX6Q/bundle.json","state":"https://pith.science/pith/HGSG2EVMYBACRKLH67M2GQHX6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HGSG2EVMYBACRKLH67M2GQHX6Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HGSG2EVMYBACRKLH67M2GQHX6Q","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":"e4ad6fb03955fa40bd8a62d05a0bcf4b4c487c3b44bc866caf55eff7c8fe4e20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T20:39:07Z","title_canon_sha256":"28763960536b104648733b2d8b722c380c98b38919e173ead299c9e4ed1cbaa4"},"schema_version":"1.0","source":{"id":"1904.04900","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04900","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04900v1","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04900","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"HGSG2EVMYBAC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HGSG2EVMYBACRKLH","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HGSG2EVM","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:aa7276c2ddb4172bbc08466fdad13fdafcd7c8e9a0680bfbf7dd8f4c988e305f","target":"graph","created_at":"2026-05-17T23:48:57Z","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":"We present and apply two methods for addressing the problem of selecting relevant training data out of a general pool for use in tasks such as machine translation. Building on existing work on class-based language difference models, we first introduce a cluster-based method that uses Brown clusters to condense the vocabulary of the corpora. Secondly, we implement the cynical data selection method, which incrementally constructs a training corpus to efficiently model the task corpus. Both the cluster-based and the cynical data selection approaches are used for the first time within a machine tr","authors_text":"Amittai Axelrod, Luc\\'ia Santamar\\'ia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T20:39:07Z","title":"Data Selection with Cluster-Based Language Difference Models and Cynical Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04900","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:f3b045cd133f89b29af13b8ca897eddedd07878d717f0cc19c6ce86800ccde6a","target":"record","created_at":"2026-05-17T23:48:57Z","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":"e4ad6fb03955fa40bd8a62d05a0bcf4b4c487c3b44bc866caf55eff7c8fe4e20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-09T20:39:07Z","title_canon_sha256":"28763960536b104648733b2d8b722c380c98b38919e173ead299c9e4ed1cbaa4"},"schema_version":"1.0","source":{"id":"1904.04900","kind":"arxiv","version":1}},"canonical_sha256":"39a46d12acc04028a967f7d9a340f7f409436aee3005c14f1a8f43ce258887ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39a46d12acc04028a967f7d9a340f7f409436aee3005c14f1a8f43ce258887ed","first_computed_at":"2026-05-17T23:48:57.720253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:57.720253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"icK83hOM00AfzkvDLe7vrU4l7NYUvSD8QZkXFRx4XnooFiZStaOZcLRkpUelSQHZDaYwkmy8qYxVUtFiXtteAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:57.720689Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04900","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3b045cd133f89b29af13b8ca897eddedd07878d717f0cc19c6ce86800ccde6a","sha256:aa7276c2ddb4172bbc08466fdad13fdafcd7c8e9a0680bfbf7dd8f4c988e305f"],"state_sha256":"f6c21b16aaaff97c46310b50cb0c48d62fb7b5512188a676722d848a95289c85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CQSIDXiv1xG94i+HJQQYNqrjCnSAk25i4F0ePXQk4xQjhRzSYIaww76L8oag5YZ7dhGui+fpwYwzAdh5a5tAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T01:58:52.676341Z","bundle_sha256":"57c5d28faa31ec754048e7e5be9c3ef93bb51d912d74fd7e5aead1f3836597ea"}}