{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:R7SUGJJDB2NEDU7PPOTIMDWTMZ","short_pith_number":"pith:R7SUGJJD","canonical_record":{"source":{"id":"1710.02650","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-07T08:18:12Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c33ae2d7401af3335e156b5de98ecfe8d00cb905268d7454fea03d2577b9a29f","abstract_canon_sha256":"d80df4705c1312a8fc7447aa518d568a9a2289611dc29491d1c6c9323677a617"},"schema_version":"1.0"},"canonical_sha256":"8fe54325230e9a41d3ef7ba6860ed3664de793cbb7ff484727fa82df2e993865","source":{"kind":"arxiv","id":"1710.02650","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.02650","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"arxiv_version","alias_value":"1710.02650v2","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.02650","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"pith_short_12","alias_value":"R7SUGJJDB2NE","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R7SUGJJDB2NEDU7P","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R7SUGJJD","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:R7SUGJJDB2NEDU7PPOTIMDWTMZ","target":"record","payload":{"canonical_record":{"source":{"id":"1710.02650","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-07T08:18:12Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c33ae2d7401af3335e156b5de98ecfe8d00cb905268d7454fea03d2577b9a29f","abstract_canon_sha256":"d80df4705c1312a8fc7447aa518d568a9a2289611dc29491d1c6c9323677a617"},"schema_version":"1.0"},"canonical_sha256":"8fe54325230e9a41d3ef7ba6860ed3664de793cbb7ff484727fa82df2e993865","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:30.624434Z","signature_b64":"h6obYX8AJf2Z42cw6ypOvmkZGlIMne8aESv7nRQIDrXgrkgFIRZSvA6+lur+T9gLkzHNROEcBwGiZ8A594n9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fe54325230e9a41d3ef7ba6860ed3664de793cbb7ff484727fa82df2e993865","last_reissued_at":"2026-05-18T00:24:30.623962Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:30.623962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.02650","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":"2026-05-18T00:24:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JGw17zfFBcPJZDH0jfxfGc7Glt4rdgFpE7KXbfg0MdWo1rud1GJp/30uFR28k9bF55p1IqiEvb/7gtFUkYt+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:02:33.103072Z"},"content_sha256":"2bfadec1d2dd1a2a92ef9c79272855534d19f7c3cc23f1affffccabbb20e42e1","schema_version":"1.0","event_id":"sha256:2bfadec1d2dd1a2a92ef9c79272855534d19f7c3cc23f1affffccabbb20e42e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:R7SUGJJDB2NEDU7PPOTIMDWTMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic Modeling based on Keywords and Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Johannes Schneider","submitted_at":"2017-10-07T08:18:12Z","abstract_excerpt":"Current topic models often suffer from discovering topics not matching human intuition, unnatural switching of topics within documents and high computational demands. We address these concerns by proposing a topic model and an inference algorithm based on automatically identifying characteristic keywords for topics. Keywords influence topic-assignments of nearby words. Our algorithm learns (key)word-topic scores and it self-regulates the number of topics. Inference is simple and easily parallelizable. Qualitative analysis yields comparable results to state-of-the-art models (eg. LDA), but with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.02650","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":"2026-05-18T00:24:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"phVQYs498Km6WyEXJreJyUFQl+3RK6lKUs89rE+38ldWZz/uTMgQN0by2DwRIpbvFyHXOM9loXcBaPb+LyzKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:02:33.103439Z"},"content_sha256":"27864aa0d2ab58b8ddb9f288bc15a07a023c759f094acc3b691da388af5ce1d7","schema_version":"1.0","event_id":"sha256:27864aa0d2ab58b8ddb9f288bc15a07a023c759f094acc3b691da388af5ce1d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/bundle.json","state_url":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/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":"2026-06-04T05:02:33Z","links":{"resolver":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ","bundle":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/bundle.json","state":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:R7SUGJJDB2NEDU7PPOTIMDWTMZ","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":"d80df4705c1312a8fc7447aa518d568a9a2289611dc29491d1c6c9323677a617","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-07T08:18:12Z","title_canon_sha256":"c33ae2d7401af3335e156b5de98ecfe8d00cb905268d7454fea03d2577b9a29f"},"schema_version":"1.0","source":{"id":"1710.02650","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.02650","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"arxiv_version","alias_value":"1710.02650v2","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.02650","created_at":"2026-05-18T00:24:30Z"},{"alias_kind":"pith_short_12","alias_value":"R7SUGJJDB2NE","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R7SUGJJDB2NEDU7P","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R7SUGJJD","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:27864aa0d2ab58b8ddb9f288bc15a07a023c759f094acc3b691da388af5ce1d7","target":"graph","created_at":"2026-05-18T00:24:30Z","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":"Current topic models often suffer from discovering topics not matching human intuition, unnatural switching of topics within documents and high computational demands. We address these concerns by proposing a topic model and an inference algorithm based on automatically identifying characteristic keywords for topics. Keywords influence topic-assignments of nearby words. Our algorithm learns (key)word-topic scores and it self-regulates the number of topics. Inference is simple and easily parallelizable. Qualitative analysis yields comparable results to state-of-the-art models (eg. LDA), but with","authors_text":"Johannes Schneider","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-07T08:18:12Z","title":"Topic Modeling based on Keywords and Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.02650","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":"sha256:2bfadec1d2dd1a2a92ef9c79272855534d19f7c3cc23f1affffccabbb20e42e1","target":"record","created_at":"2026-05-18T00:24:30Z","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":"d80df4705c1312a8fc7447aa518d568a9a2289611dc29491d1c6c9323677a617","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-07T08:18:12Z","title_canon_sha256":"c33ae2d7401af3335e156b5de98ecfe8d00cb905268d7454fea03d2577b9a29f"},"schema_version":"1.0","source":{"id":"1710.02650","kind":"arxiv","version":2}},"canonical_sha256":"8fe54325230e9a41d3ef7ba6860ed3664de793cbb7ff484727fa82df2e993865","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fe54325230e9a41d3ef7ba6860ed3664de793cbb7ff484727fa82df2e993865","first_computed_at":"2026-05-18T00:24:30.623962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:30.623962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h6obYX8AJf2Z42cw6ypOvmkZGlIMne8aESv7nRQIDrXgrkgFIRZSvA6+lur+T9gLkzHNROEcBwGiZ8A594n9CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:30.624434Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.02650","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bfadec1d2dd1a2a92ef9c79272855534d19f7c3cc23f1affffccabbb20e42e1","sha256:27864aa0d2ab58b8ddb9f288bc15a07a023c759f094acc3b691da388af5ce1d7"],"state_sha256":"2051515b6ea15c1d43db67e2e3d46352b5c48442c51a3030d24abaa4641b481d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RJazb0V/FZsEtjY0AfHUAK4kGeh+GrMqVgQcgfx6AmbescfYulojg7WtYWoRaHC4sZYLenogkZp/mjzUuo6aDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T05:02:33.105424Z","bundle_sha256":"c93f4161c8a68af85613d7b954a1aa119d1c3abe204b1ff5b351069cd01080f7"}}