{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:36HKB5TB7FPZ3WAEHA42U5JPJD","short_pith_number":"pith:36HKB5TB","canonical_record":{"source":{"id":"1810.12387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-29T20:13:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"205555172e6cd2823fcac0be4d77edfd7e366cd6cccdb5eb6a18feef58f74dac","abstract_canon_sha256":"1359469af7c67636f637f1b023ab83c94e83f4a97a90cf46065557be2cfa0250"},"schema_version":"1.0"},"canonical_sha256":"df8ea0f661f95f9dd8043839aa752f48e9eaf53fe93d136c38d4f728cd6d7ee2","source":{"kind":"arxiv","id":"1810.12387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12387","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12387v1","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12387","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"pith_short_12","alias_value":"36HKB5TB7FPZ","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"36HKB5TB7FPZ3WAE","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"36HKB5TB","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:36HKB5TB7FPZ3WAEHA42U5JPJD","target":"record","payload":{"canonical_record":{"source":{"id":"1810.12387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-29T20:13:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"205555172e6cd2823fcac0be4d77edfd7e366cd6cccdb5eb6a18feef58f74dac","abstract_canon_sha256":"1359469af7c67636f637f1b023ab83c94e83f4a97a90cf46065557be2cfa0250"},"schema_version":"1.0"},"canonical_sha256":"df8ea0f661f95f9dd8043839aa752f48e9eaf53fe93d136c38d4f728cd6d7ee2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:02.840043Z","signature_b64":"MrV46CBc+u+akDxrYlhl4iLYmDrA/LsnUWj/1T5txCPEeztTqBidgQt3CIE7nta0T28A5yv79aJ5hA61swLhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df8ea0f661f95f9dd8043839aa752f48e9eaf53fe93d136c38d4f728cd6d7ee2","last_reissued_at":"2026-05-18T00:02:02.839530Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:02.839530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.12387","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":"2026-05-18T00:02:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UVo4ZTTZ/ruOxR4oZmum0kCnHDSTeud6EmO9vEqNhTDxug7IJtM98cnTa9E7OYI9Nw1e4PT53hNoOcxfddumAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T16:32:21.649049Z"},"content_sha256":"e830163f5015bf06858a92d3ce350d686073587a6388626a38cad11c8f423c82","schema_version":"1.0","event_id":"sha256:e830163f5015bf06858a92d3ce350d686073587a6388626a38cad11c8f423c82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:36HKB5TB7FPZ3WAEHA42U5JPJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Modeling with Sparse Product of Sememe Experts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Fen Lin, Hao Zhu, Jun Yan, Leyu Lin, Maosong Sun, Ruobing Xie, Yihong Gu, Zhiyuan Liu","submitted_at":"2018-10-29T20:13:05Z","abstract_excerpt":"Most language modeling methods rely on large-scale data to statistically learn the sequential patterns of words. In this paper, we argue that words are atomic language units but not necessarily atomic semantic units. Inspired by HowNet, we use sememes, the minimum semantic units in human languages, to represent the implicit semantics behind words for language modeling, named Sememe-Driven Language Model (SDLM). More specifically, to predict the next word, SDLM first estimates the sememe distribution gave textual context. Afterward, it regards each sememe as a distinct semantic expert, and thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12387","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":"2026-05-18T00:02:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JzwhQBaWTbyTfUuGozRTaqb7UXlU0z8oTDMp9F8tMcs8rVSA6/UcbOYY9xqPvaUxYg8ywHG3v4hXS6WIbXMmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T16:32:21.649446Z"},"content_sha256":"42d711bfeac771f8bb8dd457a50fee02977a24f299be9517f3f674e68e7ef522","schema_version":"1.0","event_id":"sha256:42d711bfeac771f8bb8dd457a50fee02977a24f299be9517f3f674e68e7ef522"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36HKB5TB7FPZ3WAEHA42U5JPJD/bundle.json","state_url":"https://pith.science/pith/36HKB5TB7FPZ3WAEHA42U5JPJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36HKB5TB7FPZ3WAEHA42U5JPJD/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":"2026-05-21T16:32:21Z","links":{"resolver":"https://pith.science/pith/36HKB5TB7FPZ3WAEHA42U5JPJD","bundle":"https://pith.science/pith/36HKB5TB7FPZ3WAEHA42U5JPJD/bundle.json","state":"https://pith.science/pith/36HKB5TB7FPZ3WAEHA42U5JPJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36HKB5TB7FPZ3WAEHA42U5JPJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:36HKB5TB7FPZ3WAEHA42U5JPJD","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":"1359469af7c67636f637f1b023ab83c94e83f4a97a90cf46065557be2cfa0250","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-29T20:13:05Z","title_canon_sha256":"205555172e6cd2823fcac0be4d77edfd7e366cd6cccdb5eb6a18feef58f74dac"},"schema_version":"1.0","source":{"id":"1810.12387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12387","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12387v1","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12387","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"pith_short_12","alias_value":"36HKB5TB7FPZ","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"36HKB5TB7FPZ3WAE","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"36HKB5TB","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:42d711bfeac771f8bb8dd457a50fee02977a24f299be9517f3f674e68e7ef522","target":"graph","created_at":"2026-05-18T00:02:02Z","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":"Most language modeling methods rely on large-scale data to statistically learn the sequential patterns of words. In this paper, we argue that words are atomic language units but not necessarily atomic semantic units. Inspired by HowNet, we use sememes, the minimum semantic units in human languages, to represent the implicit semantics behind words for language modeling, named Sememe-Driven Language Model (SDLM). More specifically, to predict the next word, SDLM first estimates the sememe distribution gave textual context. Afterward, it regards each sememe as a distinct semantic expert, and thes","authors_text":"Fen Lin, Hao Zhu, Jun Yan, Leyu Lin, Maosong Sun, Ruobing Xie, Yihong Gu, Zhiyuan Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-29T20:13:05Z","title":"Language Modeling with Sparse Product of Sememe Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12387","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:e830163f5015bf06858a92d3ce350d686073587a6388626a38cad11c8f423c82","target":"record","created_at":"2026-05-18T00:02:02Z","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":"1359469af7c67636f637f1b023ab83c94e83f4a97a90cf46065557be2cfa0250","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-29T20:13:05Z","title_canon_sha256":"205555172e6cd2823fcac0be4d77edfd7e366cd6cccdb5eb6a18feef58f74dac"},"schema_version":"1.0","source":{"id":"1810.12387","kind":"arxiv","version":1}},"canonical_sha256":"df8ea0f661f95f9dd8043839aa752f48e9eaf53fe93d136c38d4f728cd6d7ee2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df8ea0f661f95f9dd8043839aa752f48e9eaf53fe93d136c38d4f728cd6d7ee2","first_computed_at":"2026-05-18T00:02:02.839530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:02.839530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MrV46CBc+u+akDxrYlhl4iLYmDrA/LsnUWj/1T5txCPEeztTqBidgQt3CIE7nta0T28A5yv79aJ5hA61swLhAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:02.840043Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e830163f5015bf06858a92d3ce350d686073587a6388626a38cad11c8f423c82","sha256:42d711bfeac771f8bb8dd457a50fee02977a24f299be9517f3f674e68e7ef522"],"state_sha256":"a6f2fc67d37fc1cc58dfe1bb44ba3d3e55aaab9ad55c5fe8cdf53a3a0bf017b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8J8iwZqttCPZfboVa3aAVEmkEcqdILgh5MbhCoGcZZMoLIELsL9qViurot+jlACYM1hQpfymk96SonVw0H0TAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T16:32:21.651555Z","bundle_sha256":"797e825b782566b9c5d6378b43fbde9d8a591214226425c7c9bae735d35662e5"}}