{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PUBFWJRC557CIMR33EATNWLH4J","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":"8cd5a41e83b040368e72739892b6530af986d111a0498d3af363ebc8428987cb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T18:38:21Z","title_canon_sha256":"2d992147bae6d523543659e67b0418b3e56a5138d990acc22b387649fcde1b85"},"schema_version":"1.0","source":{"id":"2002.12317","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12317","created_at":"2026-07-05T01:49:50Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12317v2","created_at":"2026-07-05T01:49:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12317","created_at":"2026-07-05T01:49:50Z"},{"alias_kind":"pith_short_12","alias_value":"PUBFWJRC557C","created_at":"2026-07-05T01:49:50Z"},{"alias_kind":"pith_short_16","alias_value":"PUBFWJRC557CIMR3","created_at":"2026-07-05T01:49:50Z"},{"alias_kind":"pith_short_8","alias_value":"PUBFWJRC","created_at":"2026-07-05T01:49:50Z"}],"graph_snapshots":[{"event_id":"sha256:790d5ab8f46dff807127d02144f0608652ad10c91766961bcc17ceb3c24136a6","target":"graph","created_at":"2026-07-05T01:49:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.12317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"word2vec due to Mikolov \\textit{et al.} (2013) is a word embedding method that is widely used in natural language processing. Despite its great success and frequent use, theoretical justification is still lacking. The main contribution of our paper is to propose a rigorous analysis of the highly nonlinear functional of word2vec. Our results suggest that word2vec may be primarily driven by an underlying spectral method. This insight may open the door to obtaining provable guarantees for word2vec. We support these findings by numerical simulations. One fascinating open question is whether the no","authors_text":"Ariel Jaffe, Erez Peterfreund, Jonathan Patsenker, Ofir Lindenbaum, Stefan Steinerberger, Yuval Kluger","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T18:38:21Z","title":"The Spectral Underpinning of word2vec"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12317","kind":"arxiv","version":2},"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:c4df688f9037f4b0d9626d63cbfebd6fae9d4f8f2c219bd53d7d41f628efe08d","target":"record","created_at":"2026-07-05T01:49:50Z","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":"8cd5a41e83b040368e72739892b6530af986d111a0498d3af363ebc8428987cb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T18:38:21Z","title_canon_sha256":"2d992147bae6d523543659e67b0418b3e56a5138d990acc22b387649fcde1b85"},"schema_version":"1.0","source":{"id":"2002.12317","kind":"arxiv","version":2}},"canonical_sha256":"7d025b2622ef7e24323bd90136d967e25d9d3c162efbbe635e59cb2c2da35b31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d025b2622ef7e24323bd90136d967e25d9d3c162efbbe635e59cb2c2da35b31","first_computed_at":"2026-07-05T01:49:50.009397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:50.009397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+VI7FDH0/fBU+TJVzCF7abtmITiupiycCA7JbtXKnP66WNt29On0atPz3BZQUI5RlrR3ax/Zz5tKTt9O3q1uBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:50.009782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.12317","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4df688f9037f4b0d9626d63cbfebd6fae9d4f8f2c219bd53d7d41f628efe08d","sha256:790d5ab8f46dff807127d02144f0608652ad10c91766961bcc17ceb3c24136a6"],"state_sha256":"630d30451212d6abba447173afd8cca6366ebd98e83a3c6297fbc7043d5d77ec"}