{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LFV6PW75LRHHPIP6MCMPCDKQED","short_pith_number":"pith:LFV6PW75","canonical_record":{"source":{"id":"1710.09805","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T16:54:13Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"12f03c24e5030c79ff58bb328bad6c32f0950f304e2449d968d0649d1545e1c7","abstract_canon_sha256":"719897645fba0f78fec5854d232e4c5314d68d4f5afaaa494b3e21fe3bf65a63"},"schema_version":"1.0"},"canonical_sha256":"596be7dbfd5c4e77a1fe6098f10d5020e0c4512803fd8d09a212c905dc7bc81e","source":{"kind":"arxiv","id":"1710.09805","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.09805","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"1710.09805v3","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.09805","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"LFV6PW75LRHH","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LFV6PW75LRHHPIP6","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LFV6PW75","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LFV6PW75LRHHPIP6MCMPCDKQED","target":"record","payload":{"canonical_record":{"source":{"id":"1710.09805","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T16:54:13Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"12f03c24e5030c79ff58bb328bad6c32f0950f304e2449d968d0649d1545e1c7","abstract_canon_sha256":"719897645fba0f78fec5854d232e4c5314d68d4f5afaaa494b3e21fe3bf65a63"},"schema_version":"1.0"},"canonical_sha256":"596be7dbfd5c4e77a1fe6098f10d5020e0c4512803fd8d09a212c905dc7bc81e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:24.800855Z","signature_b64":"biCLGty3ruD81HpLzHK2gBco8o4rrgNKSgdcL2ciM3JqFuFA88sgpH2EUYaK76huhqV4BPg4dfX0SHUvPNh/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"596be7dbfd5c4e77a1fe6098f10d5020e0c4512803fd8d09a212c905dc7bc81e","last_reissued_at":"2026-05-18T00:12:24.800195Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:24.800195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.09805","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":"2026-05-18T00:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzEHxP2lZSeHOH8szyIKD6bEcB/2+YqbQCcYBb5DIeSS/9TDRQbZKZ4r6TCyJkyQM4c14sy361hwPlRxu3h6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:02:31.271512Z"},"content_sha256":"20353f333f83ca7ec666884884ba07ec0780d0af3b1c175dd84776718bd05947","schema_version":"1.0","event_id":"sha256:20353f333f83ca7ec666884884ba07ec0780d0af3b1c175dd84776718bd05947"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LFV6PW75LRHHPIP6MCMPCDKQED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Negative Sampling for Word Representation using Self-embedded Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fajie Yuan, Joemon M. Jose, Long Chen, Weinan Zhang","submitted_at":"2017-10-26T16:54:13Z","abstract_excerpt":"Although the word-popularity based negative sampler has shown superb performance in the skip-gram model, the theoretical motivation behind oversampling popular (non-observed) words as negative samples is still not well understood. In this paper, we start from an investigation of the gradient vanishing issue in the skipgram model without a proper negative sampler. By performing an insightful analysis from the stochastic gradient descent (SGD) learning perspective, we demonstrate that, both theoretically and intuitively, negative samples with larger inner product scores are more informative than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.09805","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":"2026-05-18T00:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QoiLqKxruxBcsITrvrxEH302Vahd4nfph8PEkSiV3m4Be/ws8nkhzwCS42txi/m6A9ByVXwlUAOvYsO1Rv9QDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:02:31.272288Z"},"content_sha256":"7694f7bd8358bb4a4516bdf02b91c8344fcaded9fd8e75d14a831550bee8444b","schema_version":"1.0","event_id":"sha256:7694f7bd8358bb4a4516bdf02b91c8344fcaded9fd8e75d14a831550bee8444b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LFV6PW75LRHHPIP6MCMPCDKQED/bundle.json","state_url":"https://pith.science/pith/LFV6PW75LRHHPIP6MCMPCDKQED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LFV6PW75LRHHPIP6MCMPCDKQED/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":"2026-05-30T00:02:31Z","links":{"resolver":"https://pith.science/pith/LFV6PW75LRHHPIP6MCMPCDKQED","bundle":"https://pith.science/pith/LFV6PW75LRHHPIP6MCMPCDKQED/bundle.json","state":"https://pith.science/pith/LFV6PW75LRHHPIP6MCMPCDKQED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LFV6PW75LRHHPIP6MCMPCDKQED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LFV6PW75LRHHPIP6MCMPCDKQED","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":"719897645fba0f78fec5854d232e4c5314d68d4f5afaaa494b3e21fe3bf65a63","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T16:54:13Z","title_canon_sha256":"12f03c24e5030c79ff58bb328bad6c32f0950f304e2449d968d0649d1545e1c7"},"schema_version":"1.0","source":{"id":"1710.09805","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.09805","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"1710.09805v3","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.09805","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"LFV6PW75LRHH","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LFV6PW75LRHHPIP6","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LFV6PW75","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:7694f7bd8358bb4a4516bdf02b91c8344fcaded9fd8e75d14a831550bee8444b","target":"graph","created_at":"2026-05-18T00:12:24Z","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":"Although the word-popularity based negative sampler has shown superb performance in the skip-gram model, the theoretical motivation behind oversampling popular (non-observed) words as negative samples is still not well understood. In this paper, we start from an investigation of the gradient vanishing issue in the skipgram model without a proper negative sampler. By performing an insightful analysis from the stochastic gradient descent (SGD) learning perspective, we demonstrate that, both theoretically and intuitively, negative samples with larger inner product scores are more informative than","authors_text":"Fajie Yuan, Joemon M. Jose, Long Chen, Weinan Zhang","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T16:54:13Z","title":"Improving Negative Sampling for Word Representation using Self-embedded Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.09805","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":"sha256:20353f333f83ca7ec666884884ba07ec0780d0af3b1c175dd84776718bd05947","target":"record","created_at":"2026-05-18T00:12:24Z","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":"719897645fba0f78fec5854d232e4c5314d68d4f5afaaa494b3e21fe3bf65a63","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T16:54:13Z","title_canon_sha256":"12f03c24e5030c79ff58bb328bad6c32f0950f304e2449d968d0649d1545e1c7"},"schema_version":"1.0","source":{"id":"1710.09805","kind":"arxiv","version":3}},"canonical_sha256":"596be7dbfd5c4e77a1fe6098f10d5020e0c4512803fd8d09a212c905dc7bc81e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"596be7dbfd5c4e77a1fe6098f10d5020e0c4512803fd8d09a212c905dc7bc81e","first_computed_at":"2026-05-18T00:12:24.800195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:24.800195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"biCLGty3ruD81HpLzHK2gBco8o4rrgNKSgdcL2ciM3JqFuFA88sgpH2EUYaK76huhqV4BPg4dfX0SHUvPNh/DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:24.800855Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.09805","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20353f333f83ca7ec666884884ba07ec0780d0af3b1c175dd84776718bd05947","sha256:7694f7bd8358bb4a4516bdf02b91c8344fcaded9fd8e75d14a831550bee8444b"],"state_sha256":"ede6cfeabc1374af4f3bbf664077349ce8884ca7384aa2b944d278fa217cb3bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AxONORu78lNWQ6XgwiJNieeU78+XSxbcDvmSlDfZTutgXYGMjrYchfrk2ra9kYlMAA02O5QCfyvA81c8ldSKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T00:02:31.276325Z","bundle_sha256":"6b7b334fbd2b51cf5ee7854255638b6ef5f8c4e0f36108c54e4d72ed67578953"}}