{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IVCXN2JM2A6V4MD2Z5ER3KPOMO","short_pith_number":"pith:IVCXN2JM","canonical_record":{"source":{"id":"1712.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-26T21:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"071efe1dedb149703f684174e2d7152a14724420f69c6f565b66cc73eda9f05a","abstract_canon_sha256":"944c094bc874ee9899349be68632e8228e6b39d71ac9e5fe6d9eb59bd11a2f22"},"schema_version":"1.0"},"canonical_sha256":"454576e92cd03d5e307acf491da9ee63976a5c88f81b88893bfcedf8b86351c6","source":{"kind":"arxiv","id":"1712.09405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.09405","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"1712.09405v1","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09405","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"IVCXN2JM2A6V","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IVCXN2JM2A6V4MD2","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IVCXN2JM","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IVCXN2JM2A6V4MD2Z5ER3KPOMO","target":"record","payload":{"canonical_record":{"source":{"id":"1712.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-26T21:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"071efe1dedb149703f684174e2d7152a14724420f69c6f565b66cc73eda9f05a","abstract_canon_sha256":"944c094bc874ee9899349be68632e8228e6b39d71ac9e5fe6d9eb59bd11a2f22"},"schema_version":"1.0"},"canonical_sha256":"454576e92cd03d5e307acf491da9ee63976a5c88f81b88893bfcedf8b86351c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:08.535366Z","signature_b64":"G7HBrTjsSQuJjWbuzDqsNRndMTJ55nPzazrZYnQuxMS4Hlv6HC7selbd+0eM+igvKNQ9aFOS+QWI6hV5mraLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"454576e92cd03d5e307acf491da9ee63976a5c88f81b88893bfcedf8b86351c6","last_reissued_at":"2026-05-18T00:27:08.534682Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:08.534682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.09405","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":"2026-05-18T00:27:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5zQEu+NIDOKjEbJtwciP1+O7ypMrY2oTmMV2IwTVJo4vRUujtSbTMQHQsc/fEBzj5mGGHPNIzsbwUQZzLQ95Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:39:05.981511Z"},"content_sha256":"692b33ace13cd41c335cabe37807a83d3241ad5c07023aabf6ab41a20502904e","schema_version":"1.0","event_id":"sha256:692b33ace13cd41c335cabe37807a83d3241ad5c07023aabf6ab41a20502904e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IVCXN2JM2A6V4MD2Z5ER3KPOMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advances in Pre-Training Distributed Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armand Joulin, Christian Puhrsch, Edouard Grave, Piotr Bojanowski, Tomas Mikolov","submitted_at":"2017-12-26T21:00:04Z","abstract_excerpt":"Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word vector representations by using a combination of known tricks that are however rarely used together. The main result of our work is the new set of publicly available pre-trained models that outperform the current state of the art by a large margin on a number of tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09405","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":"2026-05-18T00:27:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3OO1O/J/GFrTJ04j2udX8PZu5o2BmTgfLiA2RHccqBxz8IHlDTz9oxRww9ueZ89srkcMBQ0pnOrq7toS758cDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:39:05.981858Z"},"content_sha256":"621f1d8f7cf03da386fbde4c4f0ed1cd05cac78754373674cdef71d83fadbb4a","schema_version":"1.0","event_id":"sha256:621f1d8f7cf03da386fbde4c4f0ed1cd05cac78754373674cdef71d83fadbb4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/bundle.json","state_url":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/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":"2026-06-05T09:39:05Z","links":{"resolver":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO","bundle":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/bundle.json","state":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IVCXN2JM2A6V4MD2Z5ER3KPOMO","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":"944c094bc874ee9899349be68632e8228e6b39d71ac9e5fe6d9eb59bd11a2f22","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-26T21:00:04Z","title_canon_sha256":"071efe1dedb149703f684174e2d7152a14724420f69c6f565b66cc73eda9f05a"},"schema_version":"1.0","source":{"id":"1712.09405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.09405","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"1712.09405v1","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09405","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"IVCXN2JM2A6V","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IVCXN2JM2A6V4MD2","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IVCXN2JM","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:621f1d8f7cf03da386fbde4c4f0ed1cd05cac78754373674cdef71d83fadbb4a","target":"graph","created_at":"2026-05-18T00:27:08Z","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 Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word vector representations by using a combination of known tricks that are however rarely used together. The main result of our work is the new set of publicly available pre-trained models that outperform the current state of the art by a large margin on a number of tasks.","authors_text":"Armand Joulin, Christian Puhrsch, Edouard Grave, Piotr Bojanowski, Tomas Mikolov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-26T21:00:04Z","title":"Advances in Pre-Training Distributed Word Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09405","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":"sha256:692b33ace13cd41c335cabe37807a83d3241ad5c07023aabf6ab41a20502904e","target":"record","created_at":"2026-05-18T00:27:08Z","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":"944c094bc874ee9899349be68632e8228e6b39d71ac9e5fe6d9eb59bd11a2f22","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-26T21:00:04Z","title_canon_sha256":"071efe1dedb149703f684174e2d7152a14724420f69c6f565b66cc73eda9f05a"},"schema_version":"1.0","source":{"id":"1712.09405","kind":"arxiv","version":1}},"canonical_sha256":"454576e92cd03d5e307acf491da9ee63976a5c88f81b88893bfcedf8b86351c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"454576e92cd03d5e307acf491da9ee63976a5c88f81b88893bfcedf8b86351c6","first_computed_at":"2026-05-18T00:27:08.534682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:08.534682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G7HBrTjsSQuJjWbuzDqsNRndMTJ55nPzazrZYnQuxMS4Hlv6HC7selbd+0eM+igvKNQ9aFOS+QWI6hV5mraLDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:08.535366Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.09405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:692b33ace13cd41c335cabe37807a83d3241ad5c07023aabf6ab41a20502904e","sha256:621f1d8f7cf03da386fbde4c4f0ed1cd05cac78754373674cdef71d83fadbb4a"],"state_sha256":"a232d986bf6dacb819d4d04219c8c74ada8e99fde49e8ad02ef275076c0a86a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jihWR36tH//Aq9WEI5Vkrri7fLC2rINzNgwGhVX/gn7TFO5nuhw2x60or9ZUv+dmWOlSiz1/Ivfs+ezZBJ1jDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T09:39:05.984171Z","bundle_sha256":"97f10d31529bb1345f7ebd2d7f8bd38e71579d4eb757182df47cc93629c78863"}}