{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:MUD3CD2WAM46WA5YJBW4T4ALJN","short_pith_number":"pith:MUD3CD2W","canonical_record":{"source":{"id":"1605.03481","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-11T15:30:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"68d8b475edb61bfa637d0f8a6e7493c4a948c5604986471f35f35a01e5575897","abstract_canon_sha256":"6af562250e3a5cad24af27a326e269fd1c8646a623f5d9c37396203c49695f68"},"schema_version":"1.0"},"canonical_sha256":"6507b10f560339eb03b8486dc9f00b4b7c014ab6bfb76435f8312dfe6924db79","source":{"kind":"arxiv","id":"1605.03481","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.03481","created_at":"2026-05-18T01:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"1605.03481v2","created_at":"2026-05-18T01:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.03481","created_at":"2026-05-18T01:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"MUD3CD2WAM46","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MUD3CD2WAM46WA5Y","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MUD3CD2W","created_at":"2026-05-18T12:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:MUD3CD2WAM46WA5YJBW4T4ALJN","target":"record","payload":{"canonical_record":{"source":{"id":"1605.03481","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-11T15:30:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"68d8b475edb61bfa637d0f8a6e7493c4a948c5604986471f35f35a01e5575897","abstract_canon_sha256":"6af562250e3a5cad24af27a326e269fd1c8646a623f5d9c37396203c49695f68"},"schema_version":"1.0"},"canonical_sha256":"6507b10f560339eb03b8486dc9f00b4b7c014ab6bfb76435f8312dfe6924db79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:38.176015Z","signature_b64":"oB3iyncMDokzC6YOs5y/Fjn2Wt2SfMFR51RPzLow6XynWlCIxpvkQajuXMPo8ZDLE78VREZv1twmXqp16mhZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6507b10f560339eb03b8486dc9f00b4b7c014ab6bfb76435f8312dfe6924db79","last_reissued_at":"2026-05-18T01:14:38.175183Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:38.175183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.03481","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":"2026-05-18T01:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ksY114h3ZmuQDCm/1FQGvZcK7xKb69U6xwMPffso8GSwy5jo+Y53b6dV2DRxIhnQPYHtq/KPs+0BjEDEajyRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:25:44.495110Z"},"content_sha256":"5a008c63698269f011a98f5b41fb0456839a48685fdc842eb6b0c1a23bcf7810","schema_version":"1.0","event_id":"sha256:5a008c63698269f011a98f5b41fb0456839a48685fdc842eb6b0c1a23bcf7810"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:MUD3CD2WAM46WA5YJBW4T4ALJN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tweet2Vec: Character-Based Distributed Representations for Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bhuwan Dhingra, Dylan Fitzpatrick, Michael Muehl, William W. Cohen, Zhong Zhou","submitted_at":"2016-05-11T15:30:09Z","abstract_excerpt":"Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively large vocabulary size for word-level approaches. We propose a character composition model, tweet2vec, which finds vector-space representations of whole tweets by learning complex, non-local dependencies in character sequences. The proposed model outperforms a word-level baseline at predicting user-annotated hashtags associated with the posts, doing significa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.03481","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":"2026-05-18T01:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GW6GzQuQ8I4v9ob+0RzghGtBCDYLKyT+BrUpI6WI137oqVA0OSKdIIest9/V8CjJGgNF3syQc4kY1o63IhaHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:25:44.495546Z"},"content_sha256":"cd9a62262a64ea8bd0bb168a9fb8c575f6b80511605426059c7dbacabc14deb8","schema_version":"1.0","event_id":"sha256:cd9a62262a64ea8bd0bb168a9fb8c575f6b80511605426059c7dbacabc14deb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/bundle.json","state_url":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/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":"2026-05-18T20:25:44Z","links":{"resolver":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN","bundle":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/bundle.json","state":"https://pith.science/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MUD3CD2WAM46WA5YJBW4T4ALJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:MUD3CD2WAM46WA5YJBW4T4ALJN","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":"6af562250e3a5cad24af27a326e269fd1c8646a623f5d9c37396203c49695f68","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-11T15:30:09Z","title_canon_sha256":"68d8b475edb61bfa637d0f8a6e7493c4a948c5604986471f35f35a01e5575897"},"schema_version":"1.0","source":{"id":"1605.03481","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.03481","created_at":"2026-05-18T01:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"1605.03481v2","created_at":"2026-05-18T01:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.03481","created_at":"2026-05-18T01:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"MUD3CD2WAM46","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MUD3CD2WAM46WA5Y","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MUD3CD2W","created_at":"2026-05-18T12:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:cd9a62262a64ea8bd0bb168a9fb8c575f6b80511605426059c7dbacabc14deb8","target":"graph","created_at":"2026-05-18T01:14:38Z","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":"Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively large vocabulary size for word-level approaches. We propose a character composition model, tweet2vec, which finds vector-space representations of whole tweets by learning complex, non-local dependencies in character sequences. The proposed model outperforms a word-level baseline at predicting user-annotated hashtags associated with the posts, doing significa","authors_text":"Bhuwan Dhingra, Dylan Fitzpatrick, Michael Muehl, William W. Cohen, Zhong Zhou","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-11T15:30:09Z","title":"Tweet2Vec: Character-Based Distributed Representations for Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.03481","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":"sha256:5a008c63698269f011a98f5b41fb0456839a48685fdc842eb6b0c1a23bcf7810","target":"record","created_at":"2026-05-18T01:14:38Z","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":"6af562250e3a5cad24af27a326e269fd1c8646a623f5d9c37396203c49695f68","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-11T15:30:09Z","title_canon_sha256":"68d8b475edb61bfa637d0f8a6e7493c4a948c5604986471f35f35a01e5575897"},"schema_version":"1.0","source":{"id":"1605.03481","kind":"arxiv","version":2}},"canonical_sha256":"6507b10f560339eb03b8486dc9f00b4b7c014ab6bfb76435f8312dfe6924db79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6507b10f560339eb03b8486dc9f00b4b7c014ab6bfb76435f8312dfe6924db79","first_computed_at":"2026-05-18T01:14:38.175183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:14:38.175183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oB3iyncMDokzC6YOs5y/Fjn2Wt2SfMFR51RPzLow6XynWlCIxpvkQajuXMPo8ZDLE78VREZv1twmXqp16mhZDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:14:38.176015Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.03481","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a008c63698269f011a98f5b41fb0456839a48685fdc842eb6b0c1a23bcf7810","sha256:cd9a62262a64ea8bd0bb168a9fb8c575f6b80511605426059c7dbacabc14deb8"],"state_sha256":"54ff76fbc3853b63ed4352f6475d1b8878fe534ffee38659ca7967f698ee1c99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXqne9jYVG6pQYApZJGtWQZ2pUE/9cW2sp6W3QjMJBX4tS7H1CUggYf1kTFL4kcia3sX/LwrHl0qcDXr+jajBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T20:25:44.497571Z","bundle_sha256":"5cebe3a32a4e970d8b7ede12a2aa25f1cbcc1c4977303d92b59905a8007b219c"}}