{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MCFNSB6FIOL65MRRRXHDMOLAYB","short_pith_number":"pith:MCFNSB6F","canonical_record":{"source":{"id":"1712.00527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T00:39:49Z","cross_cats_sorted":[],"title_canon_sha256":"8bb2fcc93f1ce34d7238ad3f7d3b051d3ab6f341192f65e0c451cbae1666a37e","abstract_canon_sha256":"455a72536d5a70cb57fbdc0142a218170bc0fcf39727384d72a2c3eef8511ad4"},"schema_version":"1.0"},"canonical_sha256":"608ad907c54397eeb2318dce363960c050e4f70edff44ca198172f5cbe91eecf","source":{"kind":"arxiv","id":"1712.00527","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00527","created_at":"2026-05-18T00:09:05Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00527v2","created_at":"2026-05-18T00:09:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00527","created_at":"2026-05-18T00:09:05Z"},{"alias_kind":"pith_short_12","alias_value":"MCFNSB6FIOL6","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MCFNSB6FIOL65MRR","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MCFNSB6F","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MCFNSB6FIOL65MRRRXHDMOLAYB","target":"record","payload":{"canonical_record":{"source":{"id":"1712.00527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T00:39:49Z","cross_cats_sorted":[],"title_canon_sha256":"8bb2fcc93f1ce34d7238ad3f7d3b051d3ab6f341192f65e0c451cbae1666a37e","abstract_canon_sha256":"455a72536d5a70cb57fbdc0142a218170bc0fcf39727384d72a2c3eef8511ad4"},"schema_version":"1.0"},"canonical_sha256":"608ad907c54397eeb2318dce363960c050e4f70edff44ca198172f5cbe91eecf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:05.666929Z","signature_b64":"34EbFujtFrZvDuefxIyZ7dtgzOsJLVua+ym3jK6EvFzaJumatU5YMTaqNRW9BW4ZA+Uvusu0WT3lZzuoQHbABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"608ad907c54397eeb2318dce363960c050e4f70edff44ca198172f5cbe91eecf","last_reissued_at":"2026-05-18T00:09:05.666213Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:05.666213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.00527","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":"2026-05-18T00:09:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pN/yz4rB18qEZA/qMyDHuBPrm5H+lICzAqEBGfcfgxwszeJmjPA7enIyGDS+k0t7+lCPHZ5QgPdcYEYrgdOgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:29:12.431000Z"},"content_sha256":"f7e8a33c5dcdb01cb68f23d09f102c4e783d947c50c34d97ac202d90a0498485","schema_version":"1.0","event_id":"sha256:f7e8a33c5dcdb01cb68f23d09f102c4e783d947c50c34d97ac202d90a0498485"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MCFNSB6FIOL65MRRRXHDMOLAYB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Sampled Softmax with Kernel Based Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guy Blanc, Steffen Rendle","submitted_at":"2017-12-02T00:39:49Z","abstract_excerpt":"Softmax is the most commonly used output function for multiclass problems and is widely used in areas such as vision, natural language processing, and recommendation. A softmax model has linear costs in the number of classes which makes it too expensive for many real-world problems. A common approach to speed up training involves sampling only some of the classes at each training step. It is known that this method is biased and that the bias increases the more the sampling distribution deviates from the output distribution. Nevertheless, almost any recent work uses simple sampling distribution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00527","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":"2026-05-18T00:09:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hAnuQs4VIDJfVXN/OBkHoE52AYvUUaHpfOsjd1SRdv4kI16WTvGbBfvi8KcLqA0FWOqC5vj6LMe/fQXixaqeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:29:12.431344Z"},"content_sha256":"744348f25bd80093c0f86d3a85b17fa32919ff503652411d537554a574b34163","schema_version":"1.0","event_id":"sha256:744348f25bd80093c0f86d3a85b17fa32919ff503652411d537554a574b34163"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCFNSB6FIOL65MRRRXHDMOLAYB/bundle.json","state_url":"https://pith.science/pith/MCFNSB6FIOL65MRRRXHDMOLAYB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCFNSB6FIOL65MRRRXHDMOLAYB/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":"2026-07-07T10:29:12Z","links":{"resolver":"https://pith.science/pith/MCFNSB6FIOL65MRRRXHDMOLAYB","bundle":"https://pith.science/pith/MCFNSB6FIOL65MRRRXHDMOLAYB/bundle.json","state":"https://pith.science/pith/MCFNSB6FIOL65MRRRXHDMOLAYB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCFNSB6FIOL65MRRRXHDMOLAYB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MCFNSB6FIOL65MRRRXHDMOLAYB","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":"455a72536d5a70cb57fbdc0142a218170bc0fcf39727384d72a2c3eef8511ad4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T00:39:49Z","title_canon_sha256":"8bb2fcc93f1ce34d7238ad3f7d3b051d3ab6f341192f65e0c451cbae1666a37e"},"schema_version":"1.0","source":{"id":"1712.00527","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00527","created_at":"2026-05-18T00:09:05Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00527v2","created_at":"2026-05-18T00:09:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00527","created_at":"2026-05-18T00:09:05Z"},{"alias_kind":"pith_short_12","alias_value":"MCFNSB6FIOL6","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MCFNSB6FIOL65MRR","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MCFNSB6F","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:744348f25bd80093c0f86d3a85b17fa32919ff503652411d537554a574b34163","target":"graph","created_at":"2026-05-18T00:09:05Z","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":"Softmax is the most commonly used output function for multiclass problems and is widely used in areas such as vision, natural language processing, and recommendation. A softmax model has linear costs in the number of classes which makes it too expensive for many real-world problems. A common approach to speed up training involves sampling only some of the classes at each training step. It is known that this method is biased and that the bias increases the more the sampling distribution deviates from the output distribution. Nevertheless, almost any recent work uses simple sampling distribution","authors_text":"Guy Blanc, Steffen Rendle","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T00:39:49Z","title":"Adaptive Sampled Softmax with Kernel Based Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00527","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:f7e8a33c5dcdb01cb68f23d09f102c4e783d947c50c34d97ac202d90a0498485","target":"record","created_at":"2026-05-18T00:09:05Z","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":"455a72536d5a70cb57fbdc0142a218170bc0fcf39727384d72a2c3eef8511ad4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T00:39:49Z","title_canon_sha256":"8bb2fcc93f1ce34d7238ad3f7d3b051d3ab6f341192f65e0c451cbae1666a37e"},"schema_version":"1.0","source":{"id":"1712.00527","kind":"arxiv","version":2}},"canonical_sha256":"608ad907c54397eeb2318dce363960c050e4f70edff44ca198172f5cbe91eecf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"608ad907c54397eeb2318dce363960c050e4f70edff44ca198172f5cbe91eecf","first_computed_at":"2026-05-18T00:09:05.666213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:05.666213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"34EbFujtFrZvDuefxIyZ7dtgzOsJLVua+ym3jK6EvFzaJumatU5YMTaqNRW9BW4ZA+Uvusu0WT3lZzuoQHbABA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:05.666929Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.00527","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7e8a33c5dcdb01cb68f23d09f102c4e783d947c50c34d97ac202d90a0498485","sha256:744348f25bd80093c0f86d3a85b17fa32919ff503652411d537554a574b34163"],"state_sha256":"2ee11985c0d150ee9be51cc5bdc74cee464fc3691094f756d5891abaeed1469e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b/kQtnf+f4WB2RY3JGtNMYDDsPUqOnASuzbsGWBe2W7wRLcIsujRmCIMySH+zpGA07WAnVQgwXgL/v3EwEhHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:29:12.433311Z","bundle_sha256":"377ae55ba566e5110acbdf98ff836a7d4b0304788470b1534be1e4ac30993d0c"}}