{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PD54YWJHANYYJAAADDRIQQDYXT","short_pith_number":"pith:PD54YWJH","canonical_record":{"source":{"id":"1807.00930","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T23:54:48Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"7bf9ac7a02cb91bf1eede64e09b1b998e88ca8a6ac628c937efe0155605cb765","abstract_canon_sha256":"5c63ab1fb0d8776122670ba278909f82eb7960284f7d7f3fab0186d61cf5c516"},"schema_version":"1.0"},"canonical_sha256":"78fbcc5927037184800018e2884078bcc0e43a7f6bdb37ed80a254137aca8777","source":{"kind":"arxiv","id":"1807.00930","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.00930","created_at":"2026-05-18T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"1807.00930v4","created_at":"2026-05-18T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00930","created_at":"2026-05-18T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"PD54YWJHANYY","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PD54YWJHANYYJAAA","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PD54YWJH","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PD54YWJHANYYJAAADDRIQQDYXT","target":"record","payload":{"canonical_record":{"source":{"id":"1807.00930","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T23:54:48Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"7bf9ac7a02cb91bf1eede64e09b1b998e88ca8a6ac628c937efe0155605cb765","abstract_canon_sha256":"5c63ab1fb0d8776122670ba278909f82eb7960284f7d7f3fab0186d61cf5c516"},"schema_version":"1.0"},"canonical_sha256":"78fbcc5927037184800018e2884078bcc0e43a7f6bdb37ed80a254137aca8777","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:44.612459Z","signature_b64":"qBDR4uG1uZGjgHKnug1qOqW1aIMzhRP9bQrrhDddqeUh/eEaXpa+99vpvPyW8bhFOfkW+3bjGRSeMfuWwjtvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78fbcc5927037184800018e2884078bcc0e43a7f6bdb37ed80a254137aca8777","last_reissued_at":"2026-05-18T00:04:44.611744Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:44.611744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.00930","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PP/aW8HAM2bdDgK36mJmtsPyIiYicTypaL5tIt1cbOYlzSDsHh9KIQ5t2d4My9IlD0D35evejpjEVY7SmLxFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T03:55:34.714483Z"},"content_sha256":"cc7e6e4e56878fd89cccefebdf47416e8c72ba7a8da54152351afd29f0cc6b25","schema_version":"1.0","event_id":"sha256:cc7e6e4e56878fd89cccefebdf47416e8c72ba7a8da54152351afd29f0cc6b25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PD54YWJHANYYJAAADDRIQQDYXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Random Projections for Language Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Davide Nunes, Luis Antunes","submitted_at":"2018-07-02T23:54:48Z","abstract_excerpt":"Neural network-based language models deal with data sparsity problems by mapping the large discrete space of words into a smaller continuous space of real-valued vectors. By learning distributed vector representations for words, each training sample informs the neural network model about a combinatorial number of other patterns. In this paper, we exploit the sparsity in natural language even further by encoding each unique input word using a fixed sparse random representation. These sparse codes are then projected onto a smaller embedding space which allows for the encoding of word occurrences"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00930","kind":"arxiv","version":4},"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":"2026-05-18T00:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3JyEzn9/yvIWOBVNIMehl6XFht/nHXNTkabe39Pump2ubZOKqQQcbZS3ONoAWOl9zsx2nEOI9Kld732kI1vHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T03:55:34.714825Z"},"content_sha256":"813961cfee800d984a83279ba99f681fd6ea88af5420743ae0a03a0d8d5239f4","schema_version":"1.0","event_id":"sha256:813961cfee800d984a83279ba99f681fd6ea88af5420743ae0a03a0d8d5239f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PD54YWJHANYYJAAADDRIQQDYXT/bundle.json","state_url":"https://pith.science/pith/PD54YWJHANYYJAAADDRIQQDYXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PD54YWJHANYYJAAADDRIQQDYXT/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":"2026-06-24T03:55:34Z","links":{"resolver":"https://pith.science/pith/PD54YWJHANYYJAAADDRIQQDYXT","bundle":"https://pith.science/pith/PD54YWJHANYYJAAADDRIQQDYXT/bundle.json","state":"https://pith.science/pith/PD54YWJHANYYJAAADDRIQQDYXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PD54YWJHANYYJAAADDRIQQDYXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PD54YWJHANYYJAAADDRIQQDYXT","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":"5c63ab1fb0d8776122670ba278909f82eb7960284f7d7f3fab0186d61cf5c516","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T23:54:48Z","title_canon_sha256":"7bf9ac7a02cb91bf1eede64e09b1b998e88ca8a6ac628c937efe0155605cb765"},"schema_version":"1.0","source":{"id":"1807.00930","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.00930","created_at":"2026-05-18T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"1807.00930v4","created_at":"2026-05-18T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00930","created_at":"2026-05-18T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"PD54YWJHANYY","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PD54YWJHANYYJAAA","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PD54YWJH","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:813961cfee800d984a83279ba99f681fd6ea88af5420743ae0a03a0d8d5239f4","target":"graph","created_at":"2026-05-18T00:04:44Z","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":"Neural network-based language models deal with data sparsity problems by mapping the large discrete space of words into a smaller continuous space of real-valued vectors. By learning distributed vector representations for words, each training sample informs the neural network model about a combinatorial number of other patterns. In this paper, we exploit the sparsity in natural language even further by encoding each unique input word using a fixed sparse random representation. These sparse codes are then projected onto a smaller embedding space which allows for the encoding of word occurrences","authors_text":"Davide Nunes, Luis Antunes","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T23:54:48Z","title":"Neural Random Projections for Language Modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00930","kind":"arxiv","version":4},"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:cc7e6e4e56878fd89cccefebdf47416e8c72ba7a8da54152351afd29f0cc6b25","target":"record","created_at":"2026-05-18T00:04:44Z","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":"5c63ab1fb0d8776122670ba278909f82eb7960284f7d7f3fab0186d61cf5c516","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T23:54:48Z","title_canon_sha256":"7bf9ac7a02cb91bf1eede64e09b1b998e88ca8a6ac628c937efe0155605cb765"},"schema_version":"1.0","source":{"id":"1807.00930","kind":"arxiv","version":4}},"canonical_sha256":"78fbcc5927037184800018e2884078bcc0e43a7f6bdb37ed80a254137aca8777","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78fbcc5927037184800018e2884078bcc0e43a7f6bdb37ed80a254137aca8777","first_computed_at":"2026-05-18T00:04:44.611744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:44.611744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qBDR4uG1uZGjgHKnug1qOqW1aIMzhRP9bQrrhDddqeUh/eEaXpa+99vpvPyW8bhFOfkW+3bjGRSeMfuWwjtvAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:44.612459Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.00930","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc7e6e4e56878fd89cccefebdf47416e8c72ba7a8da54152351afd29f0cc6b25","sha256:813961cfee800d984a83279ba99f681fd6ea88af5420743ae0a03a0d8d5239f4"],"state_sha256":"e5a5cd5398dab67cc82682fd73e95513c42413c7fecd6b86a02159d93f31cf15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7nRiNFBmJLdVNrH/CCSFBI7OXm/s/kBN7EQLtjp6CVKU13qC1Qe752GqdcTY2mVSkAB0piTcy3CB+9bBnDYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T03:55:34.716692Z","bundle_sha256":"f0eca12455dff7fda11f29600e78b2b8b5c1b715faa45b8104b5eec198309c3e"}}