{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:IWJUMC5G3XJQQISH3YWWZFSLCD","short_pith_number":"pith:IWJUMC5G","canonical_record":{"source":{"id":"1607.05818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-20T04:22:50Z","cross_cats_sorted":[],"title_canon_sha256":"377706338815432fbbb7e1846cca492ee59f87e4b8493d8a9e70b95d6d107bed","abstract_canon_sha256":"1f8a11880d74c1a9fc84b5175849f22ee3906306d04cf99736a55765ae3a1159"},"schema_version":"1.0"},"canonical_sha256":"4593460ba6ddd3082247de2d6c964b10c983a4508165dd138ce20c8866795331","source":{"kind":"arxiv","id":"1607.05818","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.05818","created_at":"2026-05-18T01:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"1607.05818v1","created_at":"2026-05-18T01:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05818","created_at":"2026-05-18T01:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"IWJUMC5G3XJQ","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IWJUMC5G3XJQQISH","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IWJUMC5G","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:IWJUMC5G3XJQQISH3YWWZFSLCD","target":"record","payload":{"canonical_record":{"source":{"id":"1607.05818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-20T04:22:50Z","cross_cats_sorted":[],"title_canon_sha256":"377706338815432fbbb7e1846cca492ee59f87e4b8493d8a9e70b95d6d107bed","abstract_canon_sha256":"1f8a11880d74c1a9fc84b5175849f22ee3906306d04cf99736a55765ae3a1159"},"schema_version":"1.0"},"canonical_sha256":"4593460ba6ddd3082247de2d6c964b10c983a4508165dd138ce20c8866795331","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:45.205069Z","signature_b64":"TvLzHQRD00a2tr7szAaALhQsKpGNdmXDU8NRYNodf4JWKLT5CcuZ/WUHH17jbM60RfZx/saatYbBZiDyDaGLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4593460ba6ddd3082247de2d6c964b10c983a4508165dd138ce20c8866795331","last_reissued_at":"2026-05-18T01:10:45.204723Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:45.204723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.05818","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":"2026-05-18T01:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P6S6N+jSRzDopcygoT1ls0DNTddvKJ0W4jAnWYzSG7JB4i0QTF6+Sz+yOtahagIoZRe1VDW+sJTCzCmf5X/zCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:44:05.080588Z"},"content_sha256":"176b1b482999404e74c84b52f45442249d793fe8e1ed5c1380984d48ca50385a","schema_version":"1.0","event_id":"sha256:176b1b482999404e74c84b52f45442249d793fe8e1ed5c1380984d48ca50385a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:IWJUMC5G3XJQQISH3YWWZFSLCD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Adaptation of Topic Modeling to Sentences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew S. Gordon, Reid Swanson, Ruey-Cheng Chen","submitted_at":"2016-07-20T04:22:50Z","abstract_excerpt":"Advances in topic modeling have yielded effective methods for characterizing the latent semantics of textual data. However, applying standard topic modeling approaches to sentence-level tasks introduces a number of challenges. In this paper, we adapt the approach of latent-Dirichlet allocation to include an additional layer for incorporating information about the sentence boundaries in documents. We show that the addition of this minimal information of document structure improves the perplexity results of a trained model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05818","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":"2026-05-18T01:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sfSgZpzBEZMHx++9aX6cE87HFCg+WtZRuAvm++geaQGHGTi1O0WRDT/+HXGNwkV2x5eeUVRNyH/GHFQ6qqNyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:44:05.080919Z"},"content_sha256":"3fc2ba0418891068ecd0e853fefb9d6ec8d6e0530170455c6a9b31589a5f13d6","schema_version":"1.0","event_id":"sha256:3fc2ba0418891068ecd0e853fefb9d6ec8d6e0530170455c6a9b31589a5f13d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWJUMC5G3XJQQISH3YWWZFSLCD/bundle.json","state_url":"https://pith.science/pith/IWJUMC5G3XJQQISH3YWWZFSLCD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWJUMC5G3XJQQISH3YWWZFSLCD/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":"2026-06-29T18:44:05Z","links":{"resolver":"https://pith.science/pith/IWJUMC5G3XJQQISH3YWWZFSLCD","bundle":"https://pith.science/pith/IWJUMC5G3XJQQISH3YWWZFSLCD/bundle.json","state":"https://pith.science/pith/IWJUMC5G3XJQQISH3YWWZFSLCD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWJUMC5G3XJQQISH3YWWZFSLCD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:IWJUMC5G3XJQQISH3YWWZFSLCD","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":"1f8a11880d74c1a9fc84b5175849f22ee3906306d04cf99736a55765ae3a1159","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-20T04:22:50Z","title_canon_sha256":"377706338815432fbbb7e1846cca492ee59f87e4b8493d8a9e70b95d6d107bed"},"schema_version":"1.0","source":{"id":"1607.05818","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.05818","created_at":"2026-05-18T01:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"1607.05818v1","created_at":"2026-05-18T01:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05818","created_at":"2026-05-18T01:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"IWJUMC5G3XJQ","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IWJUMC5G3XJQQISH","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IWJUMC5G","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:3fc2ba0418891068ecd0e853fefb9d6ec8d6e0530170455c6a9b31589a5f13d6","target":"graph","created_at":"2026-05-18T01:10:45Z","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":"Advances in topic modeling have yielded effective methods for characterizing the latent semantics of textual data. However, applying standard topic modeling approaches to sentence-level tasks introduces a number of challenges. In this paper, we adapt the approach of latent-Dirichlet allocation to include an additional layer for incorporating information about the sentence boundaries in documents. We show that the addition of this minimal information of document structure improves the perplexity results of a trained model.","authors_text":"Andrew S. Gordon, Reid Swanson, Ruey-Cheng Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-20T04:22:50Z","title":"An Adaptation of Topic Modeling to Sentences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05818","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":"sha256:176b1b482999404e74c84b52f45442249d793fe8e1ed5c1380984d48ca50385a","target":"record","created_at":"2026-05-18T01:10:45Z","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":"1f8a11880d74c1a9fc84b5175849f22ee3906306d04cf99736a55765ae3a1159","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-20T04:22:50Z","title_canon_sha256":"377706338815432fbbb7e1846cca492ee59f87e4b8493d8a9e70b95d6d107bed"},"schema_version":"1.0","source":{"id":"1607.05818","kind":"arxiv","version":1}},"canonical_sha256":"4593460ba6ddd3082247de2d6c964b10c983a4508165dd138ce20c8866795331","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4593460ba6ddd3082247de2d6c964b10c983a4508165dd138ce20c8866795331","first_computed_at":"2026-05-18T01:10:45.204723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:45.204723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TvLzHQRD00a2tr7szAaALhQsKpGNdmXDU8NRYNodf4JWKLT5CcuZ/WUHH17jbM60RfZx/saatYbBZiDyDaGLBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:45.205069Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.05818","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:176b1b482999404e74c84b52f45442249d793fe8e1ed5c1380984d48ca50385a","sha256:3fc2ba0418891068ecd0e853fefb9d6ec8d6e0530170455c6a9b31589a5f13d6"],"state_sha256":"47e72a11bffd760e452780e97254b94774d5febc8bbb69568d12159caa4c168a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zh3HGGJnykw6/SLnOHAE2oT/QFu2osfLMQ16ftvHUrFCaF9Bw0zm3WdUvM4vnT+R/jYq1ALReQfwM/MLCx8GBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T18:44:05.082686Z","bundle_sha256":"9a39d12d5a15a439c6970551bb6ad49cb26617331a97766f6a08d19c66cec5d9"}}