{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:JTOYWOVNPUVD2Q6FQD2TOYNOIJ","short_pith_number":"pith:JTOYWOVN","canonical_record":{"source":{"id":"1705.10586","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-05-29T15:53:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"62256dfdc7572b47a4b4abb6231eee4ef7f176c42c57f6861d7b45ae848bfe72","abstract_canon_sha256":"e90000fc7b28d5279375f00ae4a1c2284166d28bbf88f672de1a0f0ac02c93c9"},"schema_version":"1.0"},"canonical_sha256":"4cdd8b3aad7d2a3d43c580f53761ae42799103c0902fbbd11a1eab94be2cd272","source":{"kind":"arxiv","id":"1705.10586","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10586","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10586v1","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10586","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"JTOYWOVNPUVD","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JTOYWOVNPUVD2Q6F","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JTOYWOVN","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:JTOYWOVNPUVD2Q6FQD2TOYNOIJ","target":"record","payload":{"canonical_record":{"source":{"id":"1705.10586","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-05-29T15:53:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"62256dfdc7572b47a4b4abb6231eee4ef7f176c42c57f6861d7b45ae848bfe72","abstract_canon_sha256":"e90000fc7b28d5279375f00ae4a1c2284166d28bbf88f672de1a0f0ac02c93c9"},"schema_version":"1.0"},"canonical_sha256":"4cdd8b3aad7d2a3d43c580f53761ae42799103c0902fbbd11a1eab94be2cd272","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:24.135665Z","signature_b64":"qNvSFJuGFq9i96x+b5goatZRIRDJGtE6TgcUpRU7lv9whdZGiJAnaum2I3MjbZJoaQ8OhhjK17FnrlEwwFDTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cdd8b3aad7d2a3d43c580f53761ae42799103c0902fbbd11a1eab94be2cd272","last_reissued_at":"2026-05-18T00:43:24.135001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:24.135001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.10586","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":"2026-05-18T00:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vE0+1A1vvr1DJN/JJWtQ3LAgRABxG3S3iHGHt8nV1RDhl/WjjB2jluWWJ8DhfH5FkQ0POAq6J+6WEN0+XbPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:24:13.667411Z"},"content_sha256":"78b2dcdefbffd6bc8f0a448a02be4205b2b5b36b642c0430e784da2d87ee315e","schema_version":"1.0","event_id":"sha256:78b2dcdefbffd6bc8f0a448a02be4205b2b5b36b642c0430e784da2d87ee315e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:JTOYWOVNPUVD2Q6FQD2TOYNOIJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Character-Based Text Classification using Top Down Semantic Model for Sentence Representation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Dahlmeier, Xin Zheng, Zhenzhou Wu","submitted_at":"2017-05-29T15:53:00Z","abstract_excerpt":"Despite the success of deep learning on many fronts especially image and speech, its application in text classification often is still not as good as a simple linear SVM on n-gram TF-IDF representation especially for smaller datasets. Deep learning tends to emphasize on sentence level semantics when learning a representation with models like recurrent neural network or recursive neural network, however from the success of TF-IDF representation, it seems a bag-of-words type of representation has its strength. Taking advantage of both representions, we present a model known as TDSM (Top Down Sem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10586","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":"2026-05-18T00:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nEv7YB6jZjNJCb01Pvfy1ZHb3goNoBjqWRppmpNgHZd40wl4zTw2Ypws+DrfDyPL0LIDrYIi3NSjN+TmEG4KBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:24:13.667774Z"},"content_sha256":"dc0d19925fd7a90965f4235e101d31d01f6c031e925f37f3e13b7e5f3886e4ad","schema_version":"1.0","event_id":"sha256:dc0d19925fd7a90965f4235e101d31d01f6c031e925f37f3e13b7e5f3886e4ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTOYWOVNPUVD2Q6FQD2TOYNOIJ/bundle.json","state_url":"https://pith.science/pith/JTOYWOVNPUVD2Q6FQD2TOYNOIJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTOYWOVNPUVD2Q6FQD2TOYNOIJ/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":"2026-06-01T06:24:13Z","links":{"resolver":"https://pith.science/pith/JTOYWOVNPUVD2Q6FQD2TOYNOIJ","bundle":"https://pith.science/pith/JTOYWOVNPUVD2Q6FQD2TOYNOIJ/bundle.json","state":"https://pith.science/pith/JTOYWOVNPUVD2Q6FQD2TOYNOIJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTOYWOVNPUVD2Q6FQD2TOYNOIJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:JTOYWOVNPUVD2Q6FQD2TOYNOIJ","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":"e90000fc7b28d5279375f00ae4a1c2284166d28bbf88f672de1a0f0ac02c93c9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-05-29T15:53:00Z","title_canon_sha256":"62256dfdc7572b47a4b4abb6231eee4ef7f176c42c57f6861d7b45ae848bfe72"},"schema_version":"1.0","source":{"id":"1705.10586","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10586","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10586v1","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10586","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"JTOYWOVNPUVD","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JTOYWOVNPUVD2Q6F","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JTOYWOVN","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:dc0d19925fd7a90965f4235e101d31d01f6c031e925f37f3e13b7e5f3886e4ad","target":"graph","created_at":"2026-05-18T00:43:24Z","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":"Despite the success of deep learning on many fronts especially image and speech, its application in text classification often is still not as good as a simple linear SVM on n-gram TF-IDF representation especially for smaller datasets. Deep learning tends to emphasize on sentence level semantics when learning a representation with models like recurrent neural network or recursive neural network, however from the success of TF-IDF representation, it seems a bag-of-words type of representation has its strength. Taking advantage of both representions, we present a model known as TDSM (Top Down Sem","authors_text":"Daniel Dahlmeier, Xin Zheng, Zhenzhou Wu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-05-29T15:53:00Z","title":"Character-Based Text Classification using Top Down Semantic Model for Sentence Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10586","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":"sha256:78b2dcdefbffd6bc8f0a448a02be4205b2b5b36b642c0430e784da2d87ee315e","target":"record","created_at":"2026-05-18T00:43:24Z","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":"e90000fc7b28d5279375f00ae4a1c2284166d28bbf88f672de1a0f0ac02c93c9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-05-29T15:53:00Z","title_canon_sha256":"62256dfdc7572b47a4b4abb6231eee4ef7f176c42c57f6861d7b45ae848bfe72"},"schema_version":"1.0","source":{"id":"1705.10586","kind":"arxiv","version":1}},"canonical_sha256":"4cdd8b3aad7d2a3d43c580f53761ae42799103c0902fbbd11a1eab94be2cd272","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cdd8b3aad7d2a3d43c580f53761ae42799103c0902fbbd11a1eab94be2cd272","first_computed_at":"2026-05-18T00:43:24.135001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:24.135001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qNvSFJuGFq9i96x+b5goatZRIRDJGtE6TgcUpRU7lv9whdZGiJAnaum2I3MjbZJoaQ8OhhjK17FnrlEwwFDTAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:24.135665Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.10586","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78b2dcdefbffd6bc8f0a448a02be4205b2b5b36b642c0430e784da2d87ee315e","sha256:dc0d19925fd7a90965f4235e101d31d01f6c031e925f37f3e13b7e5f3886e4ad"],"state_sha256":"d20bf2e84fc42142a786f561140902dbd275c97d4a4bb32a899d82ca1295ba70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u1+hKEX2AnAx+DHutuX2VGYAdgNNsCZDteycCSiK77GAFxDT1HajA3cEwwHR0U4V7dsYoo5qxkds5YgSZD+ADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T06:24:13.670086Z","bundle_sha256":"2410144901559566aacce2be8a92fdc1591bec7cb8da413def42d02d9b7e70c2"}}