{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:YEHSMOXW3UUWSBA7N2F76T3ZER","short_pith_number":"pith:YEHSMOXW","canonical_record":{"source":{"id":"1504.06654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T22:12:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"46fc3c2e380a60eb97cdc383d25b07f330c298af729a55e00a7b8a17e414a726","abstract_canon_sha256":"74b13b6d155aed0a403d4fdb7215db60e0318c5354061b8e49b5540e0c90449d"},"schema_version":"1.0"},"canonical_sha256":"c10f263af6dd2969041f6e8bff4f792451ab3ebe5fc49419a32af54de9f61e06","source":{"kind":"arxiv","id":"1504.06654","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.06654","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1504.06654v1","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.06654","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"YEHSMOXW3UUW","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"YEHSMOXW3UUWSBA7","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"YEHSMOXW","created_at":"2026-05-18T12:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:YEHSMOXW3UUWSBA7N2F76T3ZER","target":"record","payload":{"canonical_record":{"source":{"id":"1504.06654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T22:12:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"46fc3c2e380a60eb97cdc383d25b07f330c298af729a55e00a7b8a17e414a726","abstract_canon_sha256":"74b13b6d155aed0a403d4fdb7215db60e0318c5354061b8e49b5540e0c90449d"},"schema_version":"1.0"},"canonical_sha256":"c10f263af6dd2969041f6e8bff4f792451ab3ebe5fc49419a32af54de9f61e06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:17:52.861329Z","signature_b64":"k3R0nWQe9rwhR7pRmXWLpVj4YWXQGOpnBeh10yt5/H+l4UNzZL0ynOdF86eI7FaOK4RvAP74TCdwA8bq+PtoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c10f263af6dd2969041f6e8bff4f792451ab3ebe5fc49419a32af54de9f61e06","last_reissued_at":"2026-05-18T02:17:52.860771Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:17:52.860771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1504.06654","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":"2026-05-18T02:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t7b2+Fzn3cCMAoOcBY4Pve1OBtPZVij4pFF/DI4s/1XFaMDQTQH2Xxjjc91Ked/uJ1KFJ0/DSOAa4k8ZoXFCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:53:09.916901Z"},"content_sha256":"556b8224e985f1dce023b5f21d12cb9b256583832d79f6de465e800bb2b3c70e","schema_version":"1.0","event_id":"sha256:556b8224e985f1dce023b5f21d12cb9b256583832d79f6de465e800bb2b3c70e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:YEHSMOXW3UUWSBA7N2F76T3ZER","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Alexandre Passos, Andrew McCallum, Arvind Neelakantan, Jeevan Shankar","submitted_at":"2015-04-24T22:12:14Z","abstract_excerpt":"There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type ignoring polysemy and thus jeopardizing their usefulness for downstream tasks. We present an extension to the Skip-gram model that efficiently learns multiple embeddings per word type. It differs from recent related work by jointly performing word sense discrimination and embedding learning, by non-parametrically estimating the number of senses per word type, and by its "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.06654","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":"2026-05-18T02:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uXzXihARGExPBQ1iqpSeY5+NkWBPlOcHDLG4auWA1zvlMVaI/1iSvxSRJ+HTjNbzIWPZWNeQ4lBRM8jrk2TuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:53:09.917263Z"},"content_sha256":"a721fe1b2d5d119e4047c8fa432b0dec8cc4aa78d02100d0defb2b2f3ccac8be","schema_version":"1.0","event_id":"sha256:a721fe1b2d5d119e4047c8fa432b0dec8cc4aa78d02100d0defb2b2f3ccac8be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/bundle.json","state_url":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/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":"2026-05-26T02:53:09Z","links":{"resolver":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER","bundle":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/bundle.json","state":"https://pith.science/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEHSMOXW3UUWSBA7N2F76T3ZER/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:YEHSMOXW3UUWSBA7N2F76T3ZER","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":"74b13b6d155aed0a403d4fdb7215db60e0318c5354061b8e49b5540e0c90449d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T22:12:14Z","title_canon_sha256":"46fc3c2e380a60eb97cdc383d25b07f330c298af729a55e00a7b8a17e414a726"},"schema_version":"1.0","source":{"id":"1504.06654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.06654","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1504.06654v1","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.06654","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"YEHSMOXW3UUW","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"YEHSMOXW3UUWSBA7","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"YEHSMOXW","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:a721fe1b2d5d119e4047c8fa432b0dec8cc4aa78d02100d0defb2b2f3ccac8be","target":"graph","created_at":"2026-05-18T02:17:52Z","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":"There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type ignoring polysemy and thus jeopardizing their usefulness for downstream tasks. We present an extension to the Skip-gram model that efficiently learns multiple embeddings per word type. It differs from recent related work by jointly performing word sense discrimination and embedding learning, by non-parametrically estimating the number of senses per word type, and by its ","authors_text":"Alexandre Passos, Andrew McCallum, Arvind Neelakantan, Jeevan Shankar","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T22:12:14Z","title":"Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.06654","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":"sha256:556b8224e985f1dce023b5f21d12cb9b256583832d79f6de465e800bb2b3c70e","target":"record","created_at":"2026-05-18T02:17:52Z","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":"74b13b6d155aed0a403d4fdb7215db60e0318c5354061b8e49b5540e0c90449d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T22:12:14Z","title_canon_sha256":"46fc3c2e380a60eb97cdc383d25b07f330c298af729a55e00a7b8a17e414a726"},"schema_version":"1.0","source":{"id":"1504.06654","kind":"arxiv","version":1}},"canonical_sha256":"c10f263af6dd2969041f6e8bff4f792451ab3ebe5fc49419a32af54de9f61e06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c10f263af6dd2969041f6e8bff4f792451ab3ebe5fc49419a32af54de9f61e06","first_computed_at":"2026-05-18T02:17:52.860771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:17:52.860771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k3R0nWQe9rwhR7pRmXWLpVj4YWXQGOpnBeh10yt5/H+l4UNzZL0ynOdF86eI7FaOK4RvAP74TCdwA8bq+PtoCA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:17:52.861329Z","signed_message":"canonical_sha256_bytes"},"source_id":"1504.06654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:556b8224e985f1dce023b5f21d12cb9b256583832d79f6de465e800bb2b3c70e","sha256:a721fe1b2d5d119e4047c8fa432b0dec8cc4aa78d02100d0defb2b2f3ccac8be"],"state_sha256":"efb28acecd8d12aeb62194241b0b744fbae2fa789c00a9db14b5e3219e344c29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c8KBcFYDfunDwVWY6wGVRzY4JgVjenVLuP1xs/TTs8cSjue0yAScZHZeDF6UWX0VNX/xEf8a8ieKJFbQnjWUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:53:09.919383Z","bundle_sha256":"1bbd8485d5d91d21209ae198d40ffe64be5f811ace422e309bcaa1c1fb4ee77d"}}