{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:F7QLPKOV2UVUZF6GQBT7XPJWD6","short_pith_number":"pith:F7QLPKOV","canonical_record":{"source":{"id":"1412.6448","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-19T17:22:03Z","cross_cats_sorted":[],"title_canon_sha256":"68e37da39c62214adaa0ea869ca04a8e5342ca8c3e5a061c0f0839ca1f4417ae","abstract_canon_sha256":"6c24f97d404820cbcad3b665794b4cef57806d0074bad27839723a5bba258893"},"schema_version":"1.0"},"canonical_sha256":"2fe0b7a9d5d52b4c97c68067fbbd361f9ff771eac8dcd755dca073396d2ea42b","source":{"kind":"arxiv","id":"1412.6448","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6448","created_at":"2026-05-18T02:19:42Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6448v4","created_at":"2026-05-18T02:19:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6448","created_at":"2026-05-18T02:19:42Z"},{"alias_kind":"pith_short_12","alias_value":"F7QLPKOV2UVU","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"F7QLPKOV2UVUZF6G","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"F7QLPKOV","created_at":"2026-05-18T12:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:F7QLPKOV2UVUZF6GQBT7XPJWD6","target":"record","payload":{"canonical_record":{"source":{"id":"1412.6448","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-19T17:22:03Z","cross_cats_sorted":[],"title_canon_sha256":"68e37da39c62214adaa0ea869ca04a8e5342ca8c3e5a061c0f0839ca1f4417ae","abstract_canon_sha256":"6c24f97d404820cbcad3b665794b4cef57806d0074bad27839723a5bba258893"},"schema_version":"1.0"},"canonical_sha256":"2fe0b7a9d5d52b4c97c68067fbbd361f9ff771eac8dcd755dca073396d2ea42b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:42.411949Z","signature_b64":"wSPoIpFHZY64MStl/KpGJUhYsAFz4c/zCFC6H0w323W8W/SOPbmLLIeKADyTMkniDyrazI+3l7sfmQ7zAx34Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe0b7a9d5d52b4c97c68067fbbd361f9ff771eac8dcd755dca073396d2ea42b","last_reissued_at":"2026-05-18T02:19:42.411389Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:42.411389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.6448","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":"2026-05-18T02:19:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hG84U0pED3bcObj8kQP5/KuUZGdbX0KuXVpV9oWeLb+jVDWHTtZk76H8mzp70UGKc2S0h9UY25Lcz11WPPfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:29:38.499571Z"},"content_sha256":"055da7a4b859af4a30c662fe9b18b4b005523730b5b961ceef2a996abe93b6f3","schema_version":"1.0","event_id":"sha256:055da7a4b859af4a30c662fe9b18b4b005523730b5b961ceef2a996abe93b6f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:F7QLPKOV2UVUZF6GQBT7XPJWD6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Embedding Word Similarity with Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Coline Devin, Felix Hill, Kyunghyun Cho, Sebastien Jean, Yoshua Bengio","submitted_at":"2014-12-19T17:22:03Z","abstract_excerpt":"Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural language model. We show that embeddings from translation models outperform those learned by monolingual models at tasks that require knowledge of both conceptual similarity and lexical-syntactic role. We further show that these effects hold when translating from both English to French and English to German, and argue that the desirable properties of transla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6448","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":"2026-05-18T02:19:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRM4ndqIlWmWLT0KTSm6GFTddaDJvhMF0RixW2zpJ7UPa6OTeh9N8vjQyMXJZ/UjJovksBm73JI+lQ3p2Rx7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:29:38.500233Z"},"content_sha256":"c4a158f024f0ec3a6fa2531131cceb6c8c44c24d9cf3a6d4f8870a484efcefef","schema_version":"1.0","event_id":"sha256:c4a158f024f0ec3a6fa2531131cceb6c8c44c24d9cf3a6d4f8870a484efcefef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7QLPKOV2UVUZF6GQBT7XPJWD6/bundle.json","state_url":"https://pith.science/pith/F7QLPKOV2UVUZF6GQBT7XPJWD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7QLPKOV2UVUZF6GQBT7XPJWD6/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":"2026-06-07T17:29:38Z","links":{"resolver":"https://pith.science/pith/F7QLPKOV2UVUZF6GQBT7XPJWD6","bundle":"https://pith.science/pith/F7QLPKOV2UVUZF6GQBT7XPJWD6/bundle.json","state":"https://pith.science/pith/F7QLPKOV2UVUZF6GQBT7XPJWD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7QLPKOV2UVUZF6GQBT7XPJWD6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:F7QLPKOV2UVUZF6GQBT7XPJWD6","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":"6c24f97d404820cbcad3b665794b4cef57806d0074bad27839723a5bba258893","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-19T17:22:03Z","title_canon_sha256":"68e37da39c62214adaa0ea869ca04a8e5342ca8c3e5a061c0f0839ca1f4417ae"},"schema_version":"1.0","source":{"id":"1412.6448","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6448","created_at":"2026-05-18T02:19:42Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6448v4","created_at":"2026-05-18T02:19:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6448","created_at":"2026-05-18T02:19:42Z"},{"alias_kind":"pith_short_12","alias_value":"F7QLPKOV2UVU","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"F7QLPKOV2UVUZF6G","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"F7QLPKOV","created_at":"2026-05-18T12:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:c4a158f024f0ec3a6fa2531131cceb6c8c44c24d9cf3a6d4f8870a484efcefef","target":"graph","created_at":"2026-05-18T02:19:42Z","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":"Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural language model. We show that embeddings from translation models outperform those learned by monolingual models at tasks that require knowledge of both conceptual similarity and lexical-syntactic role. We further show that these effects hold when translating from both English to French and English to German, and argue that the desirable properties of transla","authors_text":"Coline Devin, Felix Hill, Kyunghyun Cho, Sebastien Jean, Yoshua Bengio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-19T17:22:03Z","title":"Embedding Word Similarity with Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6448","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":"sha256:055da7a4b859af4a30c662fe9b18b4b005523730b5b961ceef2a996abe93b6f3","target":"record","created_at":"2026-05-18T02:19:42Z","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":"6c24f97d404820cbcad3b665794b4cef57806d0074bad27839723a5bba258893","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-19T17:22:03Z","title_canon_sha256":"68e37da39c62214adaa0ea869ca04a8e5342ca8c3e5a061c0f0839ca1f4417ae"},"schema_version":"1.0","source":{"id":"1412.6448","kind":"arxiv","version":4}},"canonical_sha256":"2fe0b7a9d5d52b4c97c68067fbbd361f9ff771eac8dcd755dca073396d2ea42b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fe0b7a9d5d52b4c97c68067fbbd361f9ff771eac8dcd755dca073396d2ea42b","first_computed_at":"2026-05-18T02:19:42.411389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:19:42.411389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wSPoIpFHZY64MStl/KpGJUhYsAFz4c/zCFC6H0w323W8W/SOPbmLLIeKADyTMkniDyrazI+3l7sfmQ7zAx34Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:19:42.411949Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.6448","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:055da7a4b859af4a30c662fe9b18b4b005523730b5b961ceef2a996abe93b6f3","sha256:c4a158f024f0ec3a6fa2531131cceb6c8c44c24d9cf3a6d4f8870a484efcefef"],"state_sha256":"4e9c998a56aa3f72538d5b2a8e2934c0458de8ae1d9e15eae89b4be022bcd2a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cR9CCV8q7FxLkKyfzZAnRGNxNFiKWkmGJD9P2QQjQDZ2c3IAu/SD3SnTDRUSYVLFIBoiXqVFSWAEdUEm2VsxAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T17:29:38.503522Z","bundle_sha256":"b390ace7d80c0940b7e4cdf8c6848f46a9f13b194553c83eab1de9fff1b889b0"}}