{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JSBVYG5GYX2VTXPF2IHX4ZOZOS","short_pith_number":"pith:JSBVYG5G","canonical_record":{"source":{"id":"1809.00918","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-04T12:32:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe1a1596c71774413b284f849522e87531023dea765f1645f1494d0f52d64151","abstract_canon_sha256":"2f9a318076168c14efa5b70e3c0350160e7dd172f331d56365e3d446a949692c"},"schema_version":"1.0"},"canonical_sha256":"4c835c1ba6c5f559dde5d20f7e65d9749bb5fd2ed0d4bf565b6be6b7641ae0ab","source":{"kind":"arxiv","id":"1809.00918","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.00918","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"1809.00918v2","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00918","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"JSBVYG5GYX2V","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JSBVYG5GYX2VTXPF","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JSBVYG5G","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JSBVYG5GYX2VTXPF2IHX4ZOZOS","target":"record","payload":{"canonical_record":{"source":{"id":"1809.00918","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-04T12:32:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe1a1596c71774413b284f849522e87531023dea765f1645f1494d0f52d64151","abstract_canon_sha256":"2f9a318076168c14efa5b70e3c0350160e7dd172f331d56365e3d446a949692c"},"schema_version":"1.0"},"canonical_sha256":"4c835c1ba6c5f559dde5d20f7e65d9749bb5fd2ed0d4bf565b6be6b7641ae0ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:48.131222Z","signature_b64":"m7NS+EZIK238N3oBZrZsMdMiIEikrltBkmD0scnqccC4k8rpnC8nY1uTYyv4LaR8oLTfuzHh0S0/54BbUMNzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c835c1ba6c5f559dde5d20f7e65d9749bb5fd2ed0d4bf565b6be6b7641ae0ab","last_reissued_at":"2026-05-17T23:44:48.130604Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:48.130604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.00918","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":"2026-05-17T23:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x1Zx/NXOji4h1q39hHo8AMzs+sfWdgMT5z1bPsyMc7HVsXFQGMrhntzTLEbmE+wJ/KiPBLU8HKvHAv7Wfj3jAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T03:11:14.183499Z"},"content_sha256":"08e32f6fb9fa89f4978cf781c14cbd17c1f8f94bfeb78a0f96172c235e4aed32","schema_version":"1.0","event_id":"sha256:08e32f6fb9fa89f4978cf781c14cbd17c1f8f94bfeb78a0f96172c235e4aed32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JSBVYG5GYX2VTXPF2IHX4ZOZOS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Segmentation-free Compositional $n$-gram Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Geewook Kim, Hidetoshi Shimodaira, Kazuki Fukui","submitted_at":"2018-09-04T12:32:54Z","abstract_excerpt":"We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word dictionaries), yet it is very effective for noisy corpora written in unsegmented languages such as Chinese and Japanese. The main idea of our method is to ignore word boundaries completely (i.e., segmentation-free), and construct representations for all character $n$-grams in a raw corpus with embeddings of compositional sub-$n$-grams. Although the idea is simple, our experiments on various ben"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00918","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":"2026-05-17T23:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vIufEmQ5waDVdPgT16XwEf6olwzhwENtTockmFkfWhKuk/tqdX/HMJ9jA+CqYd0WL3kecf13Lu0rQysbBAhPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T03:11:14.184287Z"},"content_sha256":"ffa70ce13d1971d302c3c182f6686ffbf7992a824d2246ed23c72319fb6e1f9a","schema_version":"1.0","event_id":"sha256:ffa70ce13d1971d302c3c182f6686ffbf7992a824d2246ed23c72319fb6e1f9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JSBVYG5GYX2VTXPF2IHX4ZOZOS/bundle.json","state_url":"https://pith.science/pith/JSBVYG5GYX2VTXPF2IHX4ZOZOS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JSBVYG5GYX2VTXPF2IHX4ZOZOS/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":"2026-06-10T03:11:14Z","links":{"resolver":"https://pith.science/pith/JSBVYG5GYX2VTXPF2IHX4ZOZOS","bundle":"https://pith.science/pith/JSBVYG5GYX2VTXPF2IHX4ZOZOS/bundle.json","state":"https://pith.science/pith/JSBVYG5GYX2VTXPF2IHX4ZOZOS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JSBVYG5GYX2VTXPF2IHX4ZOZOS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JSBVYG5GYX2VTXPF2IHX4ZOZOS","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":"2f9a318076168c14efa5b70e3c0350160e7dd172f331d56365e3d446a949692c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-04T12:32:54Z","title_canon_sha256":"fe1a1596c71774413b284f849522e87531023dea765f1645f1494d0f52d64151"},"schema_version":"1.0","source":{"id":"1809.00918","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.00918","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"1809.00918v2","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00918","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"JSBVYG5GYX2V","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JSBVYG5GYX2VTXPF","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JSBVYG5G","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:ffa70ce13d1971d302c3c182f6686ffbf7992a824d2246ed23c72319fb6e1f9a","target":"graph","created_at":"2026-05-17T23:44:48Z","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":"We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word dictionaries), yet it is very effective for noisy corpora written in unsegmented languages such as Chinese and Japanese. The main idea of our method is to ignore word boundaries completely (i.e., segmentation-free), and construct representations for all character $n$-grams in a raw corpus with embeddings of compositional sub-$n$-grams. Although the idea is simple, our experiments on various ben","authors_text":"Geewook Kim, Hidetoshi Shimodaira, Kazuki Fukui","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-04T12:32:54Z","title":"Segmentation-free Compositional $n$-gram Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00918","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":"sha256:08e32f6fb9fa89f4978cf781c14cbd17c1f8f94bfeb78a0f96172c235e4aed32","target":"record","created_at":"2026-05-17T23:44:48Z","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":"2f9a318076168c14efa5b70e3c0350160e7dd172f331d56365e3d446a949692c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-04T12:32:54Z","title_canon_sha256":"fe1a1596c71774413b284f849522e87531023dea765f1645f1494d0f52d64151"},"schema_version":"1.0","source":{"id":"1809.00918","kind":"arxiv","version":2}},"canonical_sha256":"4c835c1ba6c5f559dde5d20f7e65d9749bb5fd2ed0d4bf565b6be6b7641ae0ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c835c1ba6c5f559dde5d20f7e65d9749bb5fd2ed0d4bf565b6be6b7641ae0ab","first_computed_at":"2026-05-17T23:44:48.130604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:48.130604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m7NS+EZIK238N3oBZrZsMdMiIEikrltBkmD0scnqccC4k8rpnC8nY1uTYyv4LaR8oLTfuzHh0S0/54BbUMNzAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:48.131222Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.00918","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08e32f6fb9fa89f4978cf781c14cbd17c1f8f94bfeb78a0f96172c235e4aed32","sha256:ffa70ce13d1971d302c3c182f6686ffbf7992a824d2246ed23c72319fb6e1f9a"],"state_sha256":"9ef23b5afb6d2ccdfdceef8298deb053441536eb45b606c53de370887b7c7365"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YMfr9+lQXYoV7E/f52ZivBemSPkCdNigft0ERHgvwM8tKETrsFgIlOGcknbAXqu5IhhV92eH6MvITMadXsZPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T03:11:14.188998Z","bundle_sha256":"13be9b48399cd3b557e47f67aace155a5e26cef3001a95a5e722ecab4a70d53a"}}