{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4EYEFFE7GZAFS55NUXI33BGSCK","short_pith_number":"pith:4EYEFFE7","canonical_record":{"source":{"id":"1810.00664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-24T10:54:52Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"375b0d33ef5ee7b1e12943226c65f65192189d1e361a0eb23a350d4168feaabd","abstract_canon_sha256":"57ade3e1654e44174cf7fbbe8a3b1f5f63a1474ee0be929183f44ba37760d9aa"},"schema_version":"1.0"},"canonical_sha256":"e13042949f36405977ada5d1bd84d2129ed4d50ace2d3b4c02ab76af4748ce4c","source":{"kind":"arxiv","id":"1810.00664","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00664","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00664v1","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00664","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"4EYEFFE7GZAF","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4EYEFFE7GZAFS55N","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4EYEFFE7","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4EYEFFE7GZAFS55NUXI33BGSCK","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-24T10:54:52Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"375b0d33ef5ee7b1e12943226c65f65192189d1e361a0eb23a350d4168feaabd","abstract_canon_sha256":"57ade3e1654e44174cf7fbbe8a3b1f5f63a1474ee0be929183f44ba37760d9aa"},"schema_version":"1.0"},"canonical_sha256":"e13042949f36405977ada5d1bd84d2129ed4d50ace2d3b4c02ab76af4748ce4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:25.169548Z","signature_b64":"HgbOGa8wy28oiaAuvNGIWkRy0ZV9G3+1LIoTWI2V+1hbq7y8CzoZwPQoDw8aj3yWVlnMkKbGrsbey2G+N913Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e13042949f36405977ada5d1bd84d2129ed4d50ace2d3b4c02ab76af4748ce4c","last_reissued_at":"2026-05-18T00:04:25.169027Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:25.169027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00664","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":"2026-05-18T00:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mT8lD56xhYPtQcGse3ehjschw4bqlVdtbuMF+PX4JJSu/+1m9/om3FYZjANZgdnjeQOsTRghH2fRDmMfuzoOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:10:36.374565Z"},"content_sha256":"93d660391c74416fe994e3388e92f774ecd8e6796b0c82b2d88001b4ba832b29","schema_version":"1.0","event_id":"sha256:93d660391c74416fe994e3388e92f774ecd8e6796b0c82b2d88001b4ba832b29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4EYEFFE7GZAFS55NUXI33BGSCK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Similarity in Vector Space Models: A Comparative Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Adam Lugowski, Kenneth Younge, Omid Shahmirzadi","submitted_at":"2018-09-24T10:54:52Z","abstract_excerpt":"Automatic measurement of semantic text similarity is an important task in natural language processing. In this paper, we evaluate the performance of different vector space models to perform this task. We address the real-world problem of modeling patent-to-patent similarity and compare TFIDF (and related extensions), topic models (e.g., latent semantic indexing), and neural models (e.g., paragraph vectors). Contrary to expectations, the added computational cost of text embedding methods is justified only when: 1) the target text is condensed; and 2) the similarity comparison is trivial. Otherw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00664","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":"2026-05-18T00:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uK7yBiwCqBXTx6dqtTMEhacwEwdVDVuWnDmi4AoLScUE8bVBemiQx5pAPkmPAggTYDW1MFahsx5njQkbqalHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:10:36.375153Z"},"content_sha256":"68833117b3eec5951520bdab06da786c47f93d9e5b555873c5988b629f696674","schema_version":"1.0","event_id":"sha256:68833117b3eec5951520bdab06da786c47f93d9e5b555873c5988b629f696674"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4EYEFFE7GZAFS55NUXI33BGSCK/bundle.json","state_url":"https://pith.science/pith/4EYEFFE7GZAFS55NUXI33BGSCK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4EYEFFE7GZAFS55NUXI33BGSCK/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":"2026-08-07T22:10:36Z","links":{"resolver":"https://pith.science/pith/4EYEFFE7GZAFS55NUXI33BGSCK","bundle":"https://pith.science/pith/4EYEFFE7GZAFS55NUXI33BGSCK/bundle.json","state":"https://pith.science/pith/4EYEFFE7GZAFS55NUXI33BGSCK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4EYEFFE7GZAFS55NUXI33BGSCK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4EYEFFE7GZAFS55NUXI33BGSCK","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":"57ade3e1654e44174cf7fbbe8a3b1f5f63a1474ee0be929183f44ba37760d9aa","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-24T10:54:52Z","title_canon_sha256":"375b0d33ef5ee7b1e12943226c65f65192189d1e361a0eb23a350d4168feaabd"},"schema_version":"1.0","source":{"id":"1810.00664","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00664","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00664v1","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00664","created_at":"2026-05-18T00:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"4EYEFFE7GZAF","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4EYEFFE7GZAFS55N","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4EYEFFE7","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:68833117b3eec5951520bdab06da786c47f93d9e5b555873c5988b629f696674","target":"graph","created_at":"2026-05-18T00:04:25Z","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":"Automatic measurement of semantic text similarity is an important task in natural language processing. In this paper, we evaluate the performance of different vector space models to perform this task. We address the real-world problem of modeling patent-to-patent similarity and compare TFIDF (and related extensions), topic models (e.g., latent semantic indexing), and neural models (e.g., paragraph vectors). Contrary to expectations, the added computational cost of text embedding methods is justified only when: 1) the target text is condensed; and 2) the similarity comparison is trivial. Otherw","authors_text":"Adam Lugowski, Kenneth Younge, Omid Shahmirzadi","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-24T10:54:52Z","title":"Text Similarity in Vector Space Models: A Comparative Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00664","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":"sha256:93d660391c74416fe994e3388e92f774ecd8e6796b0c82b2d88001b4ba832b29","target":"record","created_at":"2026-05-18T00:04:25Z","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":"57ade3e1654e44174cf7fbbe8a3b1f5f63a1474ee0be929183f44ba37760d9aa","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-24T10:54:52Z","title_canon_sha256":"375b0d33ef5ee7b1e12943226c65f65192189d1e361a0eb23a350d4168feaabd"},"schema_version":"1.0","source":{"id":"1810.00664","kind":"arxiv","version":1}},"canonical_sha256":"e13042949f36405977ada5d1bd84d2129ed4d50ace2d3b4c02ab76af4748ce4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e13042949f36405977ada5d1bd84d2129ed4d50ace2d3b4c02ab76af4748ce4c","first_computed_at":"2026-05-18T00:04:25.169027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:25.169027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HgbOGa8wy28oiaAuvNGIWkRy0ZV9G3+1LIoTWI2V+1hbq7y8CzoZwPQoDw8aj3yWVlnMkKbGrsbey2G+N913Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:25.169548Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00664","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93d660391c74416fe994e3388e92f774ecd8e6796b0c82b2d88001b4ba832b29","sha256:68833117b3eec5951520bdab06da786c47f93d9e5b555873c5988b629f696674"],"state_sha256":"b6bc1f0096829af59ef37c9fb06800bfebd8f8a6a20436b4f1d785d8c3ed15e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ZwWVPu+4sh8XnXJKI3Gbu4pJ0CjcTdSpz3ZFjisO+AYiDFq5uUclLrCy08nS3qRn1gSnJQVXelbzIOLTzBcBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:10:36.379034Z","bundle_sha256":"9fedf781e347675f2faf1047a6fd054f759e4fcb8e458c3aee6591354e320a68"}}