{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZYEYPULIQXMOQVD52BW4UGY7GZ","short_pith_number":"pith:ZYEYPULI","canonical_record":{"source":{"id":"1804.04475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-12T12:46:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f7a0f6d22c047a1af67c5103dd260dc83de7844e1643c0fff4e4bf6abce3b94a","abstract_canon_sha256":"b219a0a9166795a5b1ea2d6b869c7f9f38cba078a4f31e675e9b1cdb7614d154"},"schema_version":"1.0"},"canonical_sha256":"ce0987d16885d8e8547dd06dca1b1f3660a0c7f91369e7b94b9e11008e9ba3fd","source":{"kind":"arxiv","id":"1804.04475","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04475","created_at":"2026-05-18T00:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04475v1","created_at":"2026-05-18T00:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04475","created_at":"2026-05-18T00:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZYEYPULIQXMO","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZYEYPULIQXMOQVD5","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZYEYPULI","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZYEYPULIQXMOQVD52BW4UGY7GZ","target":"record","payload":{"canonical_record":{"source":{"id":"1804.04475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-12T12:46:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f7a0f6d22c047a1af67c5103dd260dc83de7844e1643c0fff4e4bf6abce3b94a","abstract_canon_sha256":"b219a0a9166795a5b1ea2d6b869c7f9f38cba078a4f31e675e9b1cdb7614d154"},"schema_version":"1.0"},"canonical_sha256":"ce0987d16885d8e8547dd06dca1b1f3660a0c7f91369e7b94b9e11008e9ba3fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:37.430305Z","signature_b64":"QIgzxRCjyLhxYWfD3Q2sFFEJD3q6+qSPBv7MWUM49VTjViAx66pM4djv8khJrpTFBDhVsHsBjE39ScNk5KvDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce0987d16885d8e8547dd06dca1b1f3660a0c7f91369e7b94b9e11008e9ba3fd","last_reissued_at":"2026-05-18T00:18:37.429786Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:37.429786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.04475","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":"2026-05-18T00:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hTk2LLZzstz5QdiaSl5GRwUnrhM5SV+YSmbec+PVTinmAeYjitswtVfnc7BNJdO3imCsPZyrt8aByoRsTE65Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:11:22.618710Z"},"content_sha256":"1208c9c882add16751d083dad40ae9583763e8f4ecdca7f366d41f2b76f48202","schema_version":"1.0","event_id":"sha256:1208c9c882add16751d083dad40ae9583763e8f4ecdca7f366d41f2b76f48202"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZYEYPULIQXMOQVD52BW4UGY7GZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Multilingual Embeddings for Cross-Lingual Information Retrieval in the Presence of Topically Aligned Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Arnab Bhattacharya, Kripabandhu Ghosh, Mitodru Niyogi","submitted_at":"2018-04-12T12:46:08Z","abstract_excerpt":"Cross-lingual information retrieval is a challenging task in the absence of aligned parallel corpora. In this paper, we address this problem by considering topically aligned corpora designed for evaluating an IR setup. To emphasize, we neither use any sentence-aligned corpora or document-aligned corpora, nor do we use any language specific resources such as dictionary, thesaurus, or grammar rules. Instead, we use an embedding into a common space and learn word correspondences directly from there. We test our proposed approach for bilingual IR on standard FIRE datasets for Bangla, Hindi and Eng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04475","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":"2026-05-18T00:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Glrl0EEEuZUWnRRnL1nzVf63RdzTzCY7mc6SAWxUT3E5U2qIPa++GJvM0+URt5DAGnJfGy5s0yvh8ou0KeLACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:11:22.619071Z"},"content_sha256":"4d74ebc57735a4e5a060038dfe44c2f37bbf33768e4cd4d13f5313e4bd015548","schema_version":"1.0","event_id":"sha256:4d74ebc57735a4e5a060038dfe44c2f37bbf33768e4cd4d13f5313e4bd015548"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYEYPULIQXMOQVD52BW4UGY7GZ/bundle.json","state_url":"https://pith.science/pith/ZYEYPULIQXMOQVD52BW4UGY7GZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYEYPULIQXMOQVD52BW4UGY7GZ/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":"2026-06-02T22:11:22Z","links":{"resolver":"https://pith.science/pith/ZYEYPULIQXMOQVD52BW4UGY7GZ","bundle":"https://pith.science/pith/ZYEYPULIQXMOQVD52BW4UGY7GZ/bundle.json","state":"https://pith.science/pith/ZYEYPULIQXMOQVD52BW4UGY7GZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYEYPULIQXMOQVD52BW4UGY7GZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZYEYPULIQXMOQVD52BW4UGY7GZ","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":"b219a0a9166795a5b1ea2d6b869c7f9f38cba078a4f31e675e9b1cdb7614d154","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-12T12:46:08Z","title_canon_sha256":"f7a0f6d22c047a1af67c5103dd260dc83de7844e1643c0fff4e4bf6abce3b94a"},"schema_version":"1.0","source":{"id":"1804.04475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04475","created_at":"2026-05-18T00:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04475v1","created_at":"2026-05-18T00:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04475","created_at":"2026-05-18T00:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZYEYPULIQXMO","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZYEYPULIQXMOQVD5","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZYEYPULI","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:4d74ebc57735a4e5a060038dfe44c2f37bbf33768e4cd4d13f5313e4bd015548","target":"graph","created_at":"2026-05-18T00:18:37Z","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":"Cross-lingual information retrieval is a challenging task in the absence of aligned parallel corpora. In this paper, we address this problem by considering topically aligned corpora designed for evaluating an IR setup. To emphasize, we neither use any sentence-aligned corpora or document-aligned corpora, nor do we use any language specific resources such as dictionary, thesaurus, or grammar rules. Instead, we use an embedding into a common space and learn word correspondences directly from there. We test our proposed approach for bilingual IR on standard FIRE datasets for Bangla, Hindi and Eng","authors_text":"Arnab Bhattacharya, Kripabandhu Ghosh, Mitodru Niyogi","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-12T12:46:08Z","title":"Learning Multilingual Embeddings for Cross-Lingual Information Retrieval in the Presence of Topically Aligned Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04475","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":"sha256:1208c9c882add16751d083dad40ae9583763e8f4ecdca7f366d41f2b76f48202","target":"record","created_at":"2026-05-18T00:18:37Z","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":"b219a0a9166795a5b1ea2d6b869c7f9f38cba078a4f31e675e9b1cdb7614d154","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-12T12:46:08Z","title_canon_sha256":"f7a0f6d22c047a1af67c5103dd260dc83de7844e1643c0fff4e4bf6abce3b94a"},"schema_version":"1.0","source":{"id":"1804.04475","kind":"arxiv","version":1}},"canonical_sha256":"ce0987d16885d8e8547dd06dca1b1f3660a0c7f91369e7b94b9e11008e9ba3fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce0987d16885d8e8547dd06dca1b1f3660a0c7f91369e7b94b9e11008e9ba3fd","first_computed_at":"2026-05-18T00:18:37.429786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:37.429786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QIgzxRCjyLhxYWfD3Q2sFFEJD3q6+qSPBv7MWUM49VTjViAx66pM4djv8khJrpTFBDhVsHsBjE39ScNk5KvDDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:37.430305Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.04475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1208c9c882add16751d083dad40ae9583763e8f4ecdca7f366d41f2b76f48202","sha256:4d74ebc57735a4e5a060038dfe44c2f37bbf33768e4cd4d13f5313e4bd015548"],"state_sha256":"89c38febfc491472d58d7c045f1a931172be4cafed0375e5226eb561431c0023"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDZgTKBZFE0TIodwJlGmvsIR1geRf94HaqUtUtOASsZzPxCqCvYQmmY5FhLfd10Zjhpj4J0ICWmUJgoOyBBLCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T22:11:22.621064Z","bundle_sha256":"c7d3e576f347b10efb952945e9e9fedfe0012a7f60db5cb20440388e821ed700"}}