{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:E3TCIMSQUOVSMVMZYCDARZFHY2","short_pith_number":"pith:E3TCIMSQ","schema_version":"1.0","canonical_sha256":"26e6243250a3ab265599c08608e4a7c6b3b95ab976e108cadd03fca25eecb067","source":{"kind":"arxiv","id":"1206.4958","version":1},"attestation_state":"computed","paper":{"title":"A Pointillism Approach for Natural Language Processing of Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SI"],"primary_cat":"cs.IR","authors_text":"Anhei Shu, Anyu Zhou, Dan Wallach, Jedidiah R. Crandall, Peiyou Song","submitted_at":"2012-06-21T18:17:50Z","abstract_excerpt":"The Chinese language poses challenges for natural language processing based on the unit of a word even for formal uses of the Chinese language, social media only makes word segmentation in Chinese even more difficult. In this document we propose a pointillism approach to natural language processing. Rather than words that have individual meanings, the basic unit of a pointillism approach is trigrams of characters. These grams take on meaning in aggregate when they appear together in a way that is correlated over time.\n  Our results from three kinds of experiments show that when words and topic"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1206.4958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-06-21T18:17:50Z","cross_cats_sorted":["cs.CL","cs.SI"],"title_canon_sha256":"7db788f68c477b094ae6267d0fcd11e99d8844ef0c8ef7df785bea99b2030425","abstract_canon_sha256":"deeae29687eecbdfb1844da5262ef1b3c0d645bfbe71ad2f27ff656972b6a290"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:53.792276Z","signature_b64":"YdYbc40RjC1uuUb8vzahyOMiAi4JC36oPb4uyOqVnWY0lcVbz5M4WNykg6SzYGR6Gm0qpho2RJF36qSqrOxqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26e6243250a3ab265599c08608e4a7c6b3b95ab976e108cadd03fca25eecb067","last_reissued_at":"2026-05-18T03:52:53.791431Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:53.791431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Pointillism Approach for Natural Language Processing of Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SI"],"primary_cat":"cs.IR","authors_text":"Anhei Shu, Anyu Zhou, Dan Wallach, Jedidiah R. Crandall, Peiyou Song","submitted_at":"2012-06-21T18:17:50Z","abstract_excerpt":"The Chinese language poses challenges for natural language processing based on the unit of a word even for formal uses of the Chinese language, social media only makes word segmentation in Chinese even more difficult. In this document we propose a pointillism approach to natural language processing. Rather than words that have individual meanings, the basic unit of a pointillism approach is trigrams of characters. These grams take on meaning in aggregate when they appear together in a way that is correlated over time.\n  Our results from three kinds of experiments show that when words and topic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.4958","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1206.4958","created_at":"2026-05-18T03:52:53.791573+00:00"},{"alias_kind":"arxiv_version","alias_value":"1206.4958v1","created_at":"2026-05-18T03:52:53.791573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.4958","created_at":"2026-05-18T03:52:53.791573+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3TCIMSQUOVS","created_at":"2026-05-18T12:27:04.183437+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3TCIMSQUOVSMVMZ","created_at":"2026-05-18T12:27:04.183437+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3TCIMSQ","created_at":"2026-05-18T12:27:04.183437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2","json":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2.json","graph_json":"https://pith.science/api/pith-number/E3TCIMSQUOVSMVMZYCDARZFHY2/graph.json","events_json":"https://pith.science/api/pith-number/E3TCIMSQUOVSMVMZYCDARZFHY2/events.json","paper":"https://pith.science/paper/E3TCIMSQ"},"agent_actions":{"view_html":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2","download_json":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2.json","view_paper":"https://pith.science/paper/E3TCIMSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1206.4958&json=true","fetch_graph":"https://pith.science/api/pith-number/E3TCIMSQUOVSMVMZYCDARZFHY2/graph.json","fetch_events":"https://pith.science/api/pith-number/E3TCIMSQUOVSMVMZYCDARZFHY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/action/storage_attestation","attest_author":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/action/author_attestation","sign_citation":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/action/citation_signature","submit_replication":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/action/replication_record"}},"created_at":"2026-05-18T03:52:53.791573+00:00","updated_at":"2026-05-18T03:52:53.791573+00:00"}