{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:BF7TNGCYU4AI3YOUFD35SNLVGK","short_pith_number":"pith:BF7TNGCY","canonical_record":{"source":{"id":"1606.00819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T19:35:46Z","cross_cats_sorted":[],"title_canon_sha256":"150f664c8d4685a78069834a71e8ec2531eed738b5e8430b11872710a96003ca","abstract_canon_sha256":"52154b0f1ed34a2f06165535a3b00efdd38377a8a223e2e9cfcc7813b2f7dfc2"},"schema_version":"1.0"},"canonical_sha256":"097f369858a7008de1d428f7d9357532b085bc7b1ca3102ca82a055eca18f353","source":{"kind":"arxiv","id":"1606.00819","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.00819","created_at":"2026-05-18T01:12:45Z"},{"alias_kind":"arxiv_version","alias_value":"1606.00819v2","created_at":"2026-05-18T01:12:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00819","created_at":"2026-05-18T01:12:45Z"},{"alias_kind":"pith_short_12","alias_value":"BF7TNGCYU4AI","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BF7TNGCYU4AI3YOU","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BF7TNGCY","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:BF7TNGCYU4AI3YOUFD35SNLVGK","target":"record","payload":{"canonical_record":{"source":{"id":"1606.00819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T19:35:46Z","cross_cats_sorted":[],"title_canon_sha256":"150f664c8d4685a78069834a71e8ec2531eed738b5e8430b11872710a96003ca","abstract_canon_sha256":"52154b0f1ed34a2f06165535a3b00efdd38377a8a223e2e9cfcc7813b2f7dfc2"},"schema_version":"1.0"},"canonical_sha256":"097f369858a7008de1d428f7d9357532b085bc7b1ca3102ca82a055eca18f353","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:45.040253Z","signature_b64":"g7fhBb3Jfl7VEWvAkPa2cdO2A6rctD1oy1nnlZ7o7MQKLT0icERA7E3z/zeet34F4x718l9vKgDP/JPh+kGgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"097f369858a7008de1d428f7d9357532b085bc7b1ca3102ca82a055eca18f353","last_reissued_at":"2026-05-18T01:12:45.039866Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:45.039866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.00819","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q2YZ2TrBXLnJukS3aKUvO3pxySFmwkSKf55XppPy3B8W56vbsVrR7xstxYhKDDEHbSwm5n0a6QAYm7z6YmmYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:35:21.313866Z"},"content_sha256":"189315384d0b1fa4c5b5f8479504d216ef6e85bb0b8bf3a04da58e3eda3e5a78","schema_version":"1.0","event_id":"sha256:189315384d0b1fa4c5b5f8479504d216ef6e85bb0b8bf3a04da58e3eda3e5a78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:BF7TNGCYU4AI3YOUFD35SNLVGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Matrix Factorization using Window Sampling and Negative Sampling for Improved Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Salle, Aline Villavicencio, Marco Idiart","submitted_at":"2016-06-02T19:35:46Z","abstract_excerpt":"In this paper, we propose LexVec, a new method for generating distributed word representations that uses low-rank, weighted factorization of the Positive Point-wise Mutual Information matrix via stochastic gradient descent, employing a weighting scheme that assigns heavier penalties for errors on frequent co-occurrences while still accounting for negative co-occurrence. Evaluation on word similarity and analogy tasks shows that LexVec matches and often outperforms state-of-the-art methods on many of these tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00819","kind":"arxiv","version":2},"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":"2026-05-18T01:12:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"adE5vpAlkktNXYXBhxq6h0Ga0Y3d8b+Y6AQsCKM+EJjihq1mvJ7lOnkyM90ERUGGFPzfqNZXGMlwiYGU3lrEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:35:21.314553Z"},"content_sha256":"9f2c642957da4bd07fd8c7dcedeece0a180ffa709c05ec4edbbaefa2a0e0736b","schema_version":"1.0","event_id":"sha256:9f2c642957da4bd07fd8c7dcedeece0a180ffa709c05ec4edbbaefa2a0e0736b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/bundle.json","state_url":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/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":"2026-05-26T10:35:21Z","links":{"resolver":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK","bundle":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/bundle.json","state":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BF7TNGCYU4AI3YOUFD35SNLVGK","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":"52154b0f1ed34a2f06165535a3b00efdd38377a8a223e2e9cfcc7813b2f7dfc2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T19:35:46Z","title_canon_sha256":"150f664c8d4685a78069834a71e8ec2531eed738b5e8430b11872710a96003ca"},"schema_version":"1.0","source":{"id":"1606.00819","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.00819","created_at":"2026-05-18T01:12:45Z"},{"alias_kind":"arxiv_version","alias_value":"1606.00819v2","created_at":"2026-05-18T01:12:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00819","created_at":"2026-05-18T01:12:45Z"},{"alias_kind":"pith_short_12","alias_value":"BF7TNGCYU4AI","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BF7TNGCYU4AI3YOU","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BF7TNGCY","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:9f2c642957da4bd07fd8c7dcedeece0a180ffa709c05ec4edbbaefa2a0e0736b","target":"graph","created_at":"2026-05-18T01:12:45Z","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":"In this paper, we propose LexVec, a new method for generating distributed word representations that uses low-rank, weighted factorization of the Positive Point-wise Mutual Information matrix via stochastic gradient descent, employing a weighting scheme that assigns heavier penalties for errors on frequent co-occurrences while still accounting for negative co-occurrence. Evaluation on word similarity and analogy tasks shows that LexVec matches and often outperforms state-of-the-art methods on many of these tasks.","authors_text":"Alexandre Salle, Aline Villavicencio, Marco Idiart","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T19:35:46Z","title":"Matrix Factorization using Window Sampling and Negative Sampling for Improved Word Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00819","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":"sha256:189315384d0b1fa4c5b5f8479504d216ef6e85bb0b8bf3a04da58e3eda3e5a78","target":"record","created_at":"2026-05-18T01:12:45Z","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":"52154b0f1ed34a2f06165535a3b00efdd38377a8a223e2e9cfcc7813b2f7dfc2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T19:35:46Z","title_canon_sha256":"150f664c8d4685a78069834a71e8ec2531eed738b5e8430b11872710a96003ca"},"schema_version":"1.0","source":{"id":"1606.00819","kind":"arxiv","version":2}},"canonical_sha256":"097f369858a7008de1d428f7d9357532b085bc7b1ca3102ca82a055eca18f353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"097f369858a7008de1d428f7d9357532b085bc7b1ca3102ca82a055eca18f353","first_computed_at":"2026-05-18T01:12:45.039866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:45.039866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g7fhBb3Jfl7VEWvAkPa2cdO2A6rctD1oy1nnlZ7o7MQKLT0icERA7E3z/zeet34F4x718l9vKgDP/JPh+kGgCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:45.040253Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.00819","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:189315384d0b1fa4c5b5f8479504d216ef6e85bb0b8bf3a04da58e3eda3e5a78","sha256:9f2c642957da4bd07fd8c7dcedeece0a180ffa709c05ec4edbbaefa2a0e0736b"],"state_sha256":"b0532fe81968688ce58aa1ec714be642dbcf8a78106286ed6c4c2a4f03e71c5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sXnXPyEFfnfouYGPUmaecFFFwZw/B9TAG8jskLyquEg73jY/3URxNllSkcuX/rawDNeLxwJcE77f/GBoFw+lBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:35:21.317638Z","bundle_sha256":"f566555d1a72fb34bdef5b90b3b78e2d48d805f702dd1acbcfcce48f62762dc5"}}