{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:E3TCIMSQUOVSMVMZYCDARZFHY2","short_pith_number":"pith:E3TCIMSQ","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"},"canonical_sha256":"26e6243250a3ab265599c08608e4a7c6b3b95ab976e108cadd03fca25eecb067","source":{"kind":"arxiv","id":"1206.4958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.4958","created_at":"2026-05-18T03:52:53Z"},{"alias_kind":"arxiv_version","alias_value":"1206.4958v1","created_at":"2026-05-18T03:52:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.4958","created_at":"2026-05-18T03:52:53Z"},{"alias_kind":"pith_short_12","alias_value":"E3TCIMSQUOVS","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"E3TCIMSQUOVSMVMZ","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"E3TCIMSQ","created_at":"2026-05-18T12:27:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:E3TCIMSQUOVSMVMZYCDARZFHY2","target":"record","payload":{"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"},"canonical_sha256":"26e6243250a3ab265599c08608e4a7c6b3b95ab976e108cadd03fca25eecb067","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"},"source_kind":"arxiv","source_id":"1206.4958","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":"2026-05-18T03:52:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6A9kYrtt6LnsKfL0tBzTr5NrvPryIESjgTFpjUes4+TIUc5ybOZafYOQX8sgNfV+fsS4F6QI7iRsdKQtrtC2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T14:20:40.456232Z"},"content_sha256":"fe24413165a011fb36cb5a64741ecab2d3d003e833da4d7be746db0daaf18ff6","schema_version":"1.0","event_id":"sha256:fe24413165a011fb36cb5a64741ecab2d3d003e833da4d7be746db0daaf18ff6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:E3TCIMSQUOVSMVMZYCDARZFHY2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:52:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wawhB3k5UfQ6Y3ncNI27V13gUEGtiOC+xKOaGr6BErSUKlTmdJ2x9N+26g4pNUfWtDJGIwLBFlBOGsvnAi4+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T14:20:40.456590Z"},"content_sha256":"8fcca68fbadfadb4e16d371848ff7e8e7b4846799e1d3dfbaad42fd20e43ea62","schema_version":"1.0","event_id":"sha256:8fcca68fbadfadb4e16d371848ff7e8e7b4846799e1d3dfbaad42fd20e43ea62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/bundle.json","state_url":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/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":"2026-06-03T14:20:40Z","links":{"resolver":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2","bundle":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/bundle.json","state":"https://pith.science/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3TCIMSQUOVSMVMZYCDARZFHY2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:E3TCIMSQUOVSMVMZYCDARZFHY2","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":"deeae29687eecbdfb1844da5262ef1b3c0d645bfbe71ad2f27ff656972b6a290","cross_cats_sorted":["cs.CL","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-06-21T18:17:50Z","title_canon_sha256":"7db788f68c477b094ae6267d0fcd11e99d8844ef0c8ef7df785bea99b2030425"},"schema_version":"1.0","source":{"id":"1206.4958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.4958","created_at":"2026-05-18T03:52:53Z"},{"alias_kind":"arxiv_version","alias_value":"1206.4958v1","created_at":"2026-05-18T03:52:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.4958","created_at":"2026-05-18T03:52:53Z"},{"alias_kind":"pith_short_12","alias_value":"E3TCIMSQUOVS","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"E3TCIMSQUOVSMVMZ","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"E3TCIMSQ","created_at":"2026-05-18T12:27:04Z"}],"graph_snapshots":[{"event_id":"sha256:8fcca68fbadfadb4e16d371848ff7e8e7b4846799e1d3dfbaad42fd20e43ea62","target":"graph","created_at":"2026-05-18T03:52:53Z","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":"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","authors_text":"Anhei Shu, Anyu Zhou, Dan Wallach, Jedidiah R. Crandall, Peiyou Song","cross_cats":["cs.CL","cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-06-21T18:17:50Z","title":"A Pointillism Approach for Natural Language Processing of Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.4958","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:fe24413165a011fb36cb5a64741ecab2d3d003e833da4d7be746db0daaf18ff6","target":"record","created_at":"2026-05-18T03:52:53Z","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":"deeae29687eecbdfb1844da5262ef1b3c0d645bfbe71ad2f27ff656972b6a290","cross_cats_sorted":["cs.CL","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-06-21T18:17:50Z","title_canon_sha256":"7db788f68c477b094ae6267d0fcd11e99d8844ef0c8ef7df785bea99b2030425"},"schema_version":"1.0","source":{"id":"1206.4958","kind":"arxiv","version":1}},"canonical_sha256":"26e6243250a3ab265599c08608e4a7c6b3b95ab976e108cadd03fca25eecb067","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26e6243250a3ab265599c08608e4a7c6b3b95ab976e108cadd03fca25eecb067","first_computed_at":"2026-05-18T03:52:53.791431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:53.791431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YdYbc40RjC1uuUb8vzahyOMiAi4JC36oPb4uyOqVnWY0lcVbz5M4WNykg6SzYGR6Gm0qpho2RJF36qSqrOxqBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:53.792276Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.4958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe24413165a011fb36cb5a64741ecab2d3d003e833da4d7be746db0daaf18ff6","sha256:8fcca68fbadfadb4e16d371848ff7e8e7b4846799e1d3dfbaad42fd20e43ea62"],"state_sha256":"ab0e11999a1aa6ce1ad4c797056b5f4a7ce4f95af950ccf6289ad8d87c797ce8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vy/UX7xNkCl8cJv/+CT1wGXdu/EQzeORL6T33Rz9WQGyTcxiYI4/uZx99FnvKkehJqVaay+Zk5RrelKhBEb/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T14:20:40.459113Z","bundle_sha256":"f6ea6841793769389a1c6500773ba13219098988537588bb908f744edc7cc753"}}