{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:DDO4OWND5BNXWTD2ULL2OYJPDE","short_pith_number":"pith:DDO4OWND","canonical_record":{"source":{"id":"1511.05389","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-17T13:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"cba59eab08f9d73860e62e171f951e52df063309a580b383f69e6eac906e7375","abstract_canon_sha256":"096cbccf318909d54de3d8096eb8d484546f2758f726f7352eeba76cfdcc0e7a"},"schema_version":"1.0"},"canonical_sha256":"18ddc759a3e85b7b4c7aa2d7a7612f192153930ebb29c5c01e782af78c011477","source":{"kind":"arxiv","id":"1511.05389","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05389","created_at":"2026-05-18T01:19:47Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05389v4","created_at":"2026-05-18T01:19:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05389","created_at":"2026-05-18T01:19:47Z"},{"alias_kind":"pith_short_12","alias_value":"DDO4OWND5BNX","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"DDO4OWND5BNXWTD2","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"DDO4OWND","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:DDO4OWND5BNXWTD2ULL2OYJPDE","target":"record","payload":{"canonical_record":{"source":{"id":"1511.05389","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-17T13:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"cba59eab08f9d73860e62e171f951e52df063309a580b383f69e6eac906e7375","abstract_canon_sha256":"096cbccf318909d54de3d8096eb8d484546f2758f726f7352eeba76cfdcc0e7a"},"schema_version":"1.0"},"canonical_sha256":"18ddc759a3e85b7b4c7aa2d7a7612f192153930ebb29c5c01e782af78c011477","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:47.670518Z","signature_b64":"aykxrVFQZfzMkIERFxEmnGEVjK4xMSusMI3P9MS/keSoXz4Jmo7fkqrmJ86ukVIY/SvOknGLSQGEvHX8F6GHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18ddc759a3e85b7b4c7aa2d7a7612f192153930ebb29c5c01e782af78c011477","last_reissued_at":"2026-05-18T01:19:47.669972Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:47.669972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.05389","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:19:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4sCDJh41HtAqTH6xXYBZnQVL+UBbxg5o+ueTFy2WMAo+m/c41+hS2JqxzwCGtIQx3drQurWfUwoMTIoYqGRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T05:19:27.596782Z"},"content_sha256":"a81287473a0059adedcf98fb1e397d64be24eaca1f2a8d3d456c0b3e1c9661b5","schema_version":"1.0","event_id":"sha256:a81287473a0059adedcf98fb1e397d64be24eaca1f2a8d3d456c0b3e1c9661b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:DDO4OWND5BNXWTD2ULL2OYJPDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to retrieve out-of-vocabulary words in speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dominique Fohr, Georges Linar\\`es, Imran Sheikh, Irina Illina","submitted_at":"2015-11-17T13:18:07Z","abstract_excerpt":"Many Proper Names (PNs) are Out-Of-Vocabulary (OOV) words for speech recognition systems used to process diachronic audio data. To help recovery of the PNs missed by the system, relevant OOV PNs can be retrieved out of the many OOVs by exploiting semantic context of the spoken content. In this paper, we propose two neural network models targeted to retrieve OOV PNs relevant to an audio document: (a) Document level Continuous Bag of Words (D-CBOW), (b) Document level Continuous Bag of Weighted Words (D-CBOW2). Both these models take document words as input and learn with an objective to maximis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05389","kind":"arxiv","version":4},"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":"2026-05-18T01:19:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S8IEZbj/RcUjS/EQYihs9s1mfQBB6jgdVtC0l801tk+C2bVb1BSD+knyAQDtg+9V9NLWypZ2Khuzx0GARd6ZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T05:19:27.597365Z"},"content_sha256":"0c430170ad14b2ff439ad86903cbcbac4c28f95972cf97ef992c747f521824da","schema_version":"1.0","event_id":"sha256:0c430170ad14b2ff439ad86903cbcbac4c28f95972cf97ef992c747f521824da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DDO4OWND5BNXWTD2ULL2OYJPDE/bundle.json","state_url":"https://pith.science/pith/DDO4OWND5BNXWTD2ULL2OYJPDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DDO4OWND5BNXWTD2ULL2OYJPDE/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":"2026-06-12T05:19:27Z","links":{"resolver":"https://pith.science/pith/DDO4OWND5BNXWTD2ULL2OYJPDE","bundle":"https://pith.science/pith/DDO4OWND5BNXWTD2ULL2OYJPDE/bundle.json","state":"https://pith.science/pith/DDO4OWND5BNXWTD2ULL2OYJPDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DDO4OWND5BNXWTD2ULL2OYJPDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:DDO4OWND5BNXWTD2ULL2OYJPDE","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":"096cbccf318909d54de3d8096eb8d484546f2758f726f7352eeba76cfdcc0e7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-17T13:18:07Z","title_canon_sha256":"cba59eab08f9d73860e62e171f951e52df063309a580b383f69e6eac906e7375"},"schema_version":"1.0","source":{"id":"1511.05389","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05389","created_at":"2026-05-18T01:19:47Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05389v4","created_at":"2026-05-18T01:19:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05389","created_at":"2026-05-18T01:19:47Z"},{"alias_kind":"pith_short_12","alias_value":"DDO4OWND5BNX","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"DDO4OWND5BNXWTD2","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"DDO4OWND","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:0c430170ad14b2ff439ad86903cbcbac4c28f95972cf97ef992c747f521824da","target":"graph","created_at":"2026-05-18T01:19:47Z","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":"Many Proper Names (PNs) are Out-Of-Vocabulary (OOV) words for speech recognition systems used to process diachronic audio data. To help recovery of the PNs missed by the system, relevant OOV PNs can be retrieved out of the many OOVs by exploiting semantic context of the spoken content. In this paper, we propose two neural network models targeted to retrieve OOV PNs relevant to an audio document: (a) Document level Continuous Bag of Words (D-CBOW), (b) Document level Continuous Bag of Weighted Words (D-CBOW2). Both these models take document words as input and learn with an objective to maximis","authors_text":"Dominique Fohr, Georges Linar\\`es, Imran Sheikh, Irina Illina","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-17T13:18:07Z","title":"Learning to retrieve out-of-vocabulary words in speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05389","kind":"arxiv","version":4},"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:a81287473a0059adedcf98fb1e397d64be24eaca1f2a8d3d456c0b3e1c9661b5","target":"record","created_at":"2026-05-18T01:19:47Z","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":"096cbccf318909d54de3d8096eb8d484546f2758f726f7352eeba76cfdcc0e7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-17T13:18:07Z","title_canon_sha256":"cba59eab08f9d73860e62e171f951e52df063309a580b383f69e6eac906e7375"},"schema_version":"1.0","source":{"id":"1511.05389","kind":"arxiv","version":4}},"canonical_sha256":"18ddc759a3e85b7b4c7aa2d7a7612f192153930ebb29c5c01e782af78c011477","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18ddc759a3e85b7b4c7aa2d7a7612f192153930ebb29c5c01e782af78c011477","first_computed_at":"2026-05-18T01:19:47.669972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:19:47.669972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aykxrVFQZfzMkIERFxEmnGEVjK4xMSusMI3P9MS/keSoXz4Jmo7fkqrmJ86ukVIY/SvOknGLSQGEvHX8F6GHDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:19:47.670518Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.05389","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a81287473a0059adedcf98fb1e397d64be24eaca1f2a8d3d456c0b3e1c9661b5","sha256:0c430170ad14b2ff439ad86903cbcbac4c28f95972cf97ef992c747f521824da"],"state_sha256":"063a77a1a2738820779a82c0d17ec06f2897a840beffe741d67423cbfc4f05e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2qQnxF60opTTxIczwmenz8xSa9PifPdeUnxHucbOZhMZfCBWgSd3Vfa4P9q8oa3f/WutdN4jdy/iFzn08u1xDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T05:19:27.599636Z","bundle_sha256":"cfe818d4d76dc8a5d4f62d60d2ab12d71a34c7cc75d324f7667b153035c88614"}}