{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:GUE3NJYU6W2FFVV6J25K4TZSPJ","short_pith_number":"pith:GUE3NJYU","canonical_record":{"source":{"id":"1506.04940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-16T12:31:43Z","cross_cats_sorted":[],"title_canon_sha256":"13d27669446a94ec37b77fd54c1d164f4fc30d1980d55142a9cd7a155dbc4493","abstract_canon_sha256":"eb040898f8f44b388f48762174d1ebcf820a9635c4488ac17cee23b3df4e3658"},"schema_version":"1.0"},"canonical_sha256":"3509b6a714f5b452d6be4ebaae4f327a435cd0a1d2f38b4cb6608fe088cb3b67","source":{"kind":"arxiv","id":"1506.04940","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04940","created_at":"2026-05-18T01:48:05Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04940v1","created_at":"2026-05-18T01:48:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04940","created_at":"2026-05-18T01:48:05Z"},{"alias_kind":"pith_short_12","alias_value":"GUE3NJYU6W2F","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"GUE3NJYU6W2FFVV6","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"GUE3NJYU","created_at":"2026-05-18T12:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:GUE3NJYU6W2FFVV6J25K4TZSPJ","target":"record","payload":{"canonical_record":{"source":{"id":"1506.04940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-16T12:31:43Z","cross_cats_sorted":[],"title_canon_sha256":"13d27669446a94ec37b77fd54c1d164f4fc30d1980d55142a9cd7a155dbc4493","abstract_canon_sha256":"eb040898f8f44b388f48762174d1ebcf820a9635c4488ac17cee23b3df4e3658"},"schema_version":"1.0"},"canonical_sha256":"3509b6a714f5b452d6be4ebaae4f327a435cd0a1d2f38b4cb6608fe088cb3b67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:48:05.434377Z","signature_b64":"Ad9wxnsQF8uZLNwrwX9k9jiXSPk4iorTl7d5k2vR5i2k1KAxK0pWbYN6d4khPLyJ6xNbH7bJBJdcPTQ/glosBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3509b6a714f5b452d6be4ebaae4f327a435cd0a1d2f38b4cb6608fe088cb3b67","last_reissued_at":"2026-05-18T01:48:05.433827Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:48:05.433827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.04940","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":"2026-05-18T01:48:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AOHtgpd1Vw81LXVPPC2Reo1tHkO7tiXE3rcqIeNZntR7ftiI9Vp/GjMb3yqxR+wxHSn/zI8DK0fO9egKHEYRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:27:12.692003Z"},"content_sha256":"e2baa10383f3959170d2a4afc8afad7a0091eb575c5e4b430e5ceb20925f5ff2","schema_version":"1.0","event_id":"sha256:e2baa10383f3959170d2a4afc8afad7a0091eb575c5e4b430e5ceb20925f5ff2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:GUE3NJYU6W2FFVV6J25K4TZSPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recognize Foreign Low-Frequency Words with Similar Pairs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Wang, Xiaoxi Wang, Xi Ma, Zhiyong Zhang","submitted_at":"2015-06-16T12:31:43Z","abstract_excerpt":"Low-frequency words place a major challenge for automatic speech recognition (ASR). The probabilities of these words, which are often important name entities, are generally under-estimated by the language model (LM) due to their limited occurrences in the training data. Recently, we proposed a word-pair approach to deal with the problem, which borrows information of frequent words to enhance the probabilities of low-frequency words. This paper presents an extension to the word-pair method by involving multiple `predicting words' to produce better estimation for low-frequency words. We also emp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04940","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":"2026-05-18T01:48:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iOmmB1qKhlkL7zYp37EDTkdXZYfiLWomoJ2qICAbUdnbDWKvy1AzXny8Y1U+mWVngtOVyD2CdDgy0mViDWc2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:27:12.692365Z"},"content_sha256":"70679f0494ac39f5a6b05ce3afcd2150c830563b27420641927226d7a816ff0a","schema_version":"1.0","event_id":"sha256:70679f0494ac39f5a6b05ce3afcd2150c830563b27420641927226d7a816ff0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUE3NJYU6W2FFVV6J25K4TZSPJ/bundle.json","state_url":"https://pith.science/pith/GUE3NJYU6W2FFVV6J25K4TZSPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUE3NJYU6W2FFVV6J25K4TZSPJ/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":"2026-06-01T08:27:12Z","links":{"resolver":"https://pith.science/pith/GUE3NJYU6W2FFVV6J25K4TZSPJ","bundle":"https://pith.science/pith/GUE3NJYU6W2FFVV6J25K4TZSPJ/bundle.json","state":"https://pith.science/pith/GUE3NJYU6W2FFVV6J25K4TZSPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUE3NJYU6W2FFVV6J25K4TZSPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:GUE3NJYU6W2FFVV6J25K4TZSPJ","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":"eb040898f8f44b388f48762174d1ebcf820a9635c4488ac17cee23b3df4e3658","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-16T12:31:43Z","title_canon_sha256":"13d27669446a94ec37b77fd54c1d164f4fc30d1980d55142a9cd7a155dbc4493"},"schema_version":"1.0","source":{"id":"1506.04940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04940","created_at":"2026-05-18T01:48:05Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04940v1","created_at":"2026-05-18T01:48:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04940","created_at":"2026-05-18T01:48:05Z"},{"alias_kind":"pith_short_12","alias_value":"GUE3NJYU6W2F","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"GUE3NJYU6W2FFVV6","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"GUE3NJYU","created_at":"2026-05-18T12:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:70679f0494ac39f5a6b05ce3afcd2150c830563b27420641927226d7a816ff0a","target":"graph","created_at":"2026-05-18T01:48:05Z","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":"Low-frequency words place a major challenge for automatic speech recognition (ASR). The probabilities of these words, which are often important name entities, are generally under-estimated by the language model (LM) due to their limited occurrences in the training data. Recently, we proposed a word-pair approach to deal with the problem, which borrows information of frequent words to enhance the probabilities of low-frequency words. This paper presents an extension to the word-pair method by involving multiple `predicting words' to produce better estimation for low-frequency words. We also emp","authors_text":"Dong Wang, Xiaoxi Wang, Xi Ma, Zhiyong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-16T12:31:43Z","title":"Recognize Foreign Low-Frequency Words with Similar Pairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04940","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:e2baa10383f3959170d2a4afc8afad7a0091eb575c5e4b430e5ceb20925f5ff2","target":"record","created_at":"2026-05-18T01:48:05Z","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":"eb040898f8f44b388f48762174d1ebcf820a9635c4488ac17cee23b3df4e3658","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-16T12:31:43Z","title_canon_sha256":"13d27669446a94ec37b77fd54c1d164f4fc30d1980d55142a9cd7a155dbc4493"},"schema_version":"1.0","source":{"id":"1506.04940","kind":"arxiv","version":1}},"canonical_sha256":"3509b6a714f5b452d6be4ebaae4f327a435cd0a1d2f38b4cb6608fe088cb3b67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3509b6a714f5b452d6be4ebaae4f327a435cd0a1d2f38b4cb6608fe088cb3b67","first_computed_at":"2026-05-18T01:48:05.433827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:48:05.433827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ad9wxnsQF8uZLNwrwX9k9jiXSPk4iorTl7d5k2vR5i2k1KAxK0pWbYN6d4khPLyJ6xNbH7bJBJdcPTQ/glosBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:48:05.434377Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.04940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2baa10383f3959170d2a4afc8afad7a0091eb575c5e4b430e5ceb20925f5ff2","sha256:70679f0494ac39f5a6b05ce3afcd2150c830563b27420641927226d7a816ff0a"],"state_sha256":"1680c56dcf568bece30e7251e634bc70bc81fa1c1cd05264c17541214c8cf1bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rdhPNaSPonESuGTQ4DI7VflQJCg2wldvmrsR5rWkEeUv0Yl5nDrvOLNGzQ1pfPDr7/gP4cYJmylXbUP5W9/qDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T08:27:12.694280Z","bundle_sha256":"327dd81173e3f769bf8c81213c8cdb28efcfaf5719bdb314cc54b1697c56d1f1"}}