{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OPGITI7GAGBIQOQLKQMQCUAFNV","short_pith_number":"pith:OPGITI7G","canonical_record":{"source":{"id":"1606.08061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-26T17:57:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5ed0667d037ccb356ab0b310e47ca63c8a1936e4ef4cbea812b00c4c49155b01","abstract_canon_sha256":"fed1d4f4cf55e5f1d1931dc6cc2737dc91a3bdded2f0deed6f9332a49ede9529"},"schema_version":"1.0"},"canonical_sha256":"73cc89a3e60182883a0b54190150056d4494899183538caab0349b41cb0f1cfa","source":{"kind":"arxiv","id":"1606.08061","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.08061","created_at":"2026-05-18T01:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"1606.08061v1","created_at":"2026-05-18T01:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.08061","created_at":"2026-05-18T01:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"OPGITI7GAGBI","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OPGITI7GAGBIQOQL","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OPGITI7G","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OPGITI7GAGBIQOQLKQMQCUAFNV","target":"record","payload":{"canonical_record":{"source":{"id":"1606.08061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-26T17:57:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5ed0667d037ccb356ab0b310e47ca63c8a1936e4ef4cbea812b00c4c49155b01","abstract_canon_sha256":"fed1d4f4cf55e5f1d1931dc6cc2737dc91a3bdded2f0deed6f9332a49ede9529"},"schema_version":"1.0"},"canonical_sha256":"73cc89a3e60182883a0b54190150056d4494899183538caab0349b41cb0f1cfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:53.927871Z","signature_b64":"cfbyGCxa7Lr24xTtC5s6pjlDN4Ry+5Urvj1at4QHvZb/xgmcNCKDaCazX4TXuWRJ6TkG0SMXdBOD2RCRqEiaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73cc89a3e60182883a0b54190150056d4494899183538caab0349b41cb0f1cfa","last_reissued_at":"2026-05-18T01:11:53.927513Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:53.927513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.08061","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":"2026-05-18T01:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DrXeJx7ZdhAP0aRPzIwrSgIhT8ltzG6k3KZImmymdTEnO4NNiKwrDYyssULSanIxmE/TC/SGb1UKPdJujfmaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:08:54.901282Z"},"content_sha256":"20fe2b3cb07220fdce78e7677316a1b5133f5e5dc0e0498549af4ba84bbbb15e","schema_version":"1.0","event_id":"sha256:20fe2b3cb07220fdce78e7677316a1b5133f5e5dc0e0498549af4ba84bbbb15e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OPGITI7GAGBIQOQLKQMQCUAFNV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exact gradient updates in time independent of output size for the spherical loss family","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Alexandre de Br\\'ebisson, Pascal Vincent, Xavier Bouthillier","submitted_at":"2016-06-26T17:57:36Z","abstract_excerpt":"An important class of problems involves training deep neural networks with sparse prediction targets of very high dimension D. These occur naturally in e.g. neural language models or the learning of word-embeddings, often posed as predicting the probability of next words among a vocabulary of size D (e.g. 200,000). Computing the equally large, but typically non-sparse D-dimensional output vector from a last hidden layer of reasonable dimension d (e.g. 500) incurs a prohibitive O(Dd) computational cost for each example, as does updating the $D \\times d$ output weight matrix and computing the gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.08061","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":"2026-05-18T01:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QstbNBeJnfaJPpEAdt3FFBTqKijsBWmPXYr5nI2afME+mlGg5w5rt3Xobp2UqiOPqO8oRCCznBgrvaOLqU7TAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:08:54.901904Z"},"content_sha256":"dbc955f9c8507dfbeee28cd251d95ccbd4e6c28f8806f1e912d48bfb5310d44d","schema_version":"1.0","event_id":"sha256:dbc955f9c8507dfbeee28cd251d95ccbd4e6c28f8806f1e912d48bfb5310d44d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPGITI7GAGBIQOQLKQMQCUAFNV/bundle.json","state_url":"https://pith.science/pith/OPGITI7GAGBIQOQLKQMQCUAFNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPGITI7GAGBIQOQLKQMQCUAFNV/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":"2026-05-25T20:08:54Z","links":{"resolver":"https://pith.science/pith/OPGITI7GAGBIQOQLKQMQCUAFNV","bundle":"https://pith.science/pith/OPGITI7GAGBIQOQLKQMQCUAFNV/bundle.json","state":"https://pith.science/pith/OPGITI7GAGBIQOQLKQMQCUAFNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPGITI7GAGBIQOQLKQMQCUAFNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OPGITI7GAGBIQOQLKQMQCUAFNV","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":"fed1d4f4cf55e5f1d1931dc6cc2737dc91a3bdded2f0deed6f9332a49ede9529","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-26T17:57:36Z","title_canon_sha256":"5ed0667d037ccb356ab0b310e47ca63c8a1936e4ef4cbea812b00c4c49155b01"},"schema_version":"1.0","source":{"id":"1606.08061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.08061","created_at":"2026-05-18T01:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"1606.08061v1","created_at":"2026-05-18T01:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.08061","created_at":"2026-05-18T01:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"OPGITI7GAGBI","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OPGITI7GAGBIQOQL","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OPGITI7G","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:dbc955f9c8507dfbeee28cd251d95ccbd4e6c28f8806f1e912d48bfb5310d44d","target":"graph","created_at":"2026-05-18T01:11:53Z","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":"An important class of problems involves training deep neural networks with sparse prediction targets of very high dimension D. These occur naturally in e.g. neural language models or the learning of word-embeddings, often posed as predicting the probability of next words among a vocabulary of size D (e.g. 200,000). Computing the equally large, but typically non-sparse D-dimensional output vector from a last hidden layer of reasonable dimension d (e.g. 500) incurs a prohibitive O(Dd) computational cost for each example, as does updating the $D \\times d$ output weight matrix and computing the gr","authors_text":"Alexandre de Br\\'ebisson, Pascal Vincent, Xavier Bouthillier","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-26T17:57:36Z","title":"Exact gradient updates in time independent of output size for the spherical loss family"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.08061","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":"sha256:20fe2b3cb07220fdce78e7677316a1b5133f5e5dc0e0498549af4ba84bbbb15e","target":"record","created_at":"2026-05-18T01:11:53Z","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":"fed1d4f4cf55e5f1d1931dc6cc2737dc91a3bdded2f0deed6f9332a49ede9529","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-26T17:57:36Z","title_canon_sha256":"5ed0667d037ccb356ab0b310e47ca63c8a1936e4ef4cbea812b00c4c49155b01"},"schema_version":"1.0","source":{"id":"1606.08061","kind":"arxiv","version":1}},"canonical_sha256":"73cc89a3e60182883a0b54190150056d4494899183538caab0349b41cb0f1cfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73cc89a3e60182883a0b54190150056d4494899183538caab0349b41cb0f1cfa","first_computed_at":"2026-05-18T01:11:53.927513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:11:53.927513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cfbyGCxa7Lr24xTtC5s6pjlDN4Ry+5Urvj1at4QHvZb/xgmcNCKDaCazX4TXuWRJ6TkG0SMXdBOD2RCRqEiaDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:11:53.927871Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.08061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20fe2b3cb07220fdce78e7677316a1b5133f5e5dc0e0498549af4ba84bbbb15e","sha256:dbc955f9c8507dfbeee28cd251d95ccbd4e6c28f8806f1e912d48bfb5310d44d"],"state_sha256":"9849bb60b7f21e987a25d589d6622cfa847ba58f6b9a7cddfdfe04fe7008c0d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjPgKgNCpSTb0LRcgSI5ZiWPZv4UQL1AjIfk9X692terhdN1UAO923QbQjNgnghnRK5T4XOIkG/E4fY0kZSfCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:08:54.905470Z","bundle_sha256":"d8391d72af6cdf810e0f7de92fe1f34fab7c6ee6dd34513592f3f007497dabff"}}