{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:PPTW3WG2G3DWTO4KIU7T7CLAUS","short_pith_number":"pith:PPTW3WG2","canonical_record":{"source":{"id":"1312.5542","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-12-19T13:31:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8ce1634be542fdf1f2ab299af98dc31ca43b3d326267f96766f1bf03c222e47","abstract_canon_sha256":"ef25371674f49d687560ec161ca18d85f308ce97ef034b42288d099557375281"},"schema_version":"1.0"},"canonical_sha256":"7be76dd8da36c769bb8a453f3f8960a49607280a00edbe48421c96de8f9ade44","source":{"kind":"arxiv","id":"1312.5542","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1312.5542","created_at":"2026-05-18T00:53:24Z"},{"alias_kind":"arxiv_version","alias_value":"1312.5542v3","created_at":"2026-05-18T00:53:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.5542","created_at":"2026-05-18T00:53:24Z"},{"alias_kind":"pith_short_12","alias_value":"PPTW3WG2G3DW","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"PPTW3WG2G3DWTO4K","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"PPTW3WG2","created_at":"2026-05-18T12:27:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:PPTW3WG2G3DWTO4KIU7T7CLAUS","target":"record","payload":{"canonical_record":{"source":{"id":"1312.5542","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-12-19T13:31:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8ce1634be542fdf1f2ab299af98dc31ca43b3d326267f96766f1bf03c222e47","abstract_canon_sha256":"ef25371674f49d687560ec161ca18d85f308ce97ef034b42288d099557375281"},"schema_version":"1.0"},"canonical_sha256":"7be76dd8da36c769bb8a453f3f8960a49607280a00edbe48421c96de8f9ade44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:24.852606Z","signature_b64":"QMdAUsJp9NavwYpY8RDQO81ciDnzXzS0p953odh9BJa+4HNrjvkg+Ka3PI1osQuWWDBlp4VAxcM+qPBn5CNOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be76dd8da36c769bb8a453f3f8960a49607280a00edbe48421c96de8f9ade44","last_reissued_at":"2026-05-18T00:53:24.852007Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:24.852007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1312.5542","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:53:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"//38Pp82Vwg3wcOFcwOg9QQM724C8w65t0yW61BCCYRwbTrSh3oV1SXMsmkgnbHGoDFfomcLdyk6TT86CHO1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T09:13:50.859465Z"},"content_sha256":"0db994e4656531a9c05d7c0c5b029c480d1ac217bc914091b7d52538e13a8074","schema_version":"1.0","event_id":"sha256:0db994e4656531a9c05d7c0c5b029c480d1ac217bc914091b7d52538e13a8074"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:PPTW3WG2G3DWTO4KIU7T7CLAUS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word Emdeddings through Hellinger PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"R\\'emi Lebret, Ronan Collobert","submitted_at":"2013-12-19T13:31:11Z","abstract_excerpt":"Word embeddings resulting from neural language models have been shown to be successful for a large variety of NLP tasks. However, such architecture might be difficult to train and time-consuming. Instead, we propose to drastically simplify the word embeddings computation through a Hellinger PCA of the word co-occurence matrix. We compare those new word embeddings with some well-known embeddings on NER and movie review tasks and show that we can reach similar or even better performance. Although deep learning is not really necessary for generating good word embeddings, we show that it can provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.5542","kind":"arxiv","version":3},"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":"2026-05-18T00:53:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JqAuJT4ynGwuXn17DIY8eYCG1mw+H1bDIQEDezBc/h9tr8B69mV73eaWhthdolYlQ19hY3BzQVQftyfrX/cmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T09:13:50.859987Z"},"content_sha256":"23466d853292c51f59021714434a34bf75a0c515768fb6ca00d6f4ba279c3032","schema_version":"1.0","event_id":"sha256:23466d853292c51f59021714434a34bf75a0c515768fb6ca00d6f4ba279c3032"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPTW3WG2G3DWTO4KIU7T7CLAUS/bundle.json","state_url":"https://pith.science/pith/PPTW3WG2G3DWTO4KIU7T7CLAUS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPTW3WG2G3DWTO4KIU7T7CLAUS/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":"2026-08-12T09:13:50Z","links":{"resolver":"https://pith.science/pith/PPTW3WG2G3DWTO4KIU7T7CLAUS","bundle":"https://pith.science/pith/PPTW3WG2G3DWTO4KIU7T7CLAUS/bundle.json","state":"https://pith.science/pith/PPTW3WG2G3DWTO4KIU7T7CLAUS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPTW3WG2G3DWTO4KIU7T7CLAUS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:PPTW3WG2G3DWTO4KIU7T7CLAUS","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":"ef25371674f49d687560ec161ca18d85f308ce97ef034b42288d099557375281","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-12-19T13:31:11Z","title_canon_sha256":"d8ce1634be542fdf1f2ab299af98dc31ca43b3d326267f96766f1bf03c222e47"},"schema_version":"1.0","source":{"id":"1312.5542","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1312.5542","created_at":"2026-05-18T00:53:24Z"},{"alias_kind":"arxiv_version","alias_value":"1312.5542v3","created_at":"2026-05-18T00:53:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.5542","created_at":"2026-05-18T00:53:24Z"},{"alias_kind":"pith_short_12","alias_value":"PPTW3WG2G3DW","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"PPTW3WG2G3DWTO4K","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"PPTW3WG2","created_at":"2026-05-18T12:27:54Z"}],"graph_snapshots":[{"event_id":"sha256:23466d853292c51f59021714434a34bf75a0c515768fb6ca00d6f4ba279c3032","target":"graph","created_at":"2026-05-18T00:53:24Z","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":"Word embeddings resulting from neural language models have been shown to be successful for a large variety of NLP tasks. However, such architecture might be difficult to train and time-consuming. Instead, we propose to drastically simplify the word embeddings computation through a Hellinger PCA of the word co-occurence matrix. We compare those new word embeddings with some well-known embeddings on NER and movie review tasks and show that we can reach similar or even better performance. Although deep learning is not really necessary for generating good word embeddings, we show that it can provi","authors_text":"R\\'emi Lebret, Ronan Collobert","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-12-19T13:31:11Z","title":"Word Emdeddings through Hellinger PCA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.5542","kind":"arxiv","version":3},"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":"sha256:0db994e4656531a9c05d7c0c5b029c480d1ac217bc914091b7d52538e13a8074","target":"record","created_at":"2026-05-18T00:53:24Z","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":"ef25371674f49d687560ec161ca18d85f308ce97ef034b42288d099557375281","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-12-19T13:31:11Z","title_canon_sha256":"d8ce1634be542fdf1f2ab299af98dc31ca43b3d326267f96766f1bf03c222e47"},"schema_version":"1.0","source":{"id":"1312.5542","kind":"arxiv","version":3}},"canonical_sha256":"7be76dd8da36c769bb8a453f3f8960a49607280a00edbe48421c96de8f9ade44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7be76dd8da36c769bb8a453f3f8960a49607280a00edbe48421c96de8f9ade44","first_computed_at":"2026-05-18T00:53:24.852007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:24.852007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QMdAUsJp9NavwYpY8RDQO81ciDnzXzS0p953odh9BJa+4HNrjvkg+Ka3PI1osQuWWDBlp4VAxcM+qPBn5CNOCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:24.852606Z","signed_message":"canonical_sha256_bytes"},"source_id":"1312.5542","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0db994e4656531a9c05d7c0c5b029c480d1ac217bc914091b7d52538e13a8074","sha256:23466d853292c51f59021714434a34bf75a0c515768fb6ca00d6f4ba279c3032"],"state_sha256":"26a185f40419ca9cc0f1f3d9a7553e547b4a95276b9f5f2b5245818ed2beb9f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SC4F3v/YypFPUPYusr+NLEHkEE/5ZweSKpwrhzB9BQX+r/4XX9AfqA7XjOrIr5NcWz7Y97e8SRN7QEWYh+jcCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T09:13:50.863498Z","bundle_sha256":"dd76a2ddc2092fc3bef711421f2b5485d980c9b908065144e22ce31e581fe0dd"}}