{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RXQ65Q3E7EUW2GT7RX7EORVHPA","short_pith_number":"pith:RXQ65Q3E","canonical_record":{"source":{"id":"1603.04747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-15T16:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"04dd7f152ee2520123660869c80272db22ce91881020f831f47ee483836a5ade","abstract_canon_sha256":"1c51e120b6fb9532bea2ced4458a5c02a9384c086da401836cb6ca04f92516e1"},"schema_version":"1.0"},"canonical_sha256":"8de1eec364f9296d1a7f8dfe4746a7782e03463f66a2458d98d2a80e411236b6","source":{"kind":"arxiv","id":"1603.04747","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.04747","created_at":"2026-05-18T01:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"1603.04747v1","created_at":"2026-05-18T01:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.04747","created_at":"2026-05-18T01:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"RXQ65Q3E7EUW","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RXQ65Q3E7EUW2GT7","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RXQ65Q3E","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RXQ65Q3E7EUW2GT7RX7EORVHPA","target":"record","payload":{"canonical_record":{"source":{"id":"1603.04747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-15T16:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"04dd7f152ee2520123660869c80272db22ce91881020f831f47ee483836a5ade","abstract_canon_sha256":"1c51e120b6fb9532bea2ced4458a5c02a9384c086da401836cb6ca04f92516e1"},"schema_version":"1.0"},"canonical_sha256":"8de1eec364f9296d1a7f8dfe4746a7782e03463f66a2458d98d2a80e411236b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:04.056723Z","signature_b64":"UqGvrS5PL2tyquKXC0QTkO+BuMByFjSXV7d5f3G3dcymJiiQ+d/dV0uz6orGXeje4FN2mS5QDhXZlJ5VjmWbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8de1eec364f9296d1a7f8dfe4746a7782e03463f66a2458d98d2a80e411236b6","last_reissued_at":"2026-05-18T01:19:04.056127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:04.056127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.04747","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":"2026-05-18T01:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IcCl0Ulnd6KnmBUUF30VhR/Yr0vU004oedCGyorQuDIP1S3jrPrnHJDTEDzJ89jYN4bZJXy4dwz4pyJ1ZNalBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:56:25.219425Z"},"content_sha256":"5dc7d825556e69e7a895546d5c29e14d37eaae5a69217fbf4c50aea5f30177dd","schema_version":"1.0","event_id":"sha256:5dc7d825556e69e7a895546d5c29e14d37eaae5a69217fbf4c50aea5f30177dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RXQ65Q3E7EUW2GT7RX7EORVHPA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic Modeling Using Distributed Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gagan Madan, Parag Jain, Ramandeep S Randhawa","submitted_at":"2016-03-15T16:21:58Z","abstract_excerpt":"We propose a new algorithm for topic modeling, Vec2Topic, that identifies the main topics in a corpus using semantic information captured via high-dimensional distributed word embeddings. Our technique is unsupervised and generates a list of topics ranked with respect to importance. We find that it works better than existing topic modeling techniques such as Latent Dirichlet Allocation for identifying key topics in user-generated content, such as emails, chats, etc., where topics are diffused across the corpus. We also find that Vec2Topic works equally well for non-user generated content, such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.04747","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":"2026-05-18T01:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rT63Hhtb2+Z+o3Qf2JUTBwMwRy1iqK81tdW+GECAuUBgFgt5/UQgoYqYSoWGEYrV4DTuKPOuFZY8wO2iKpGdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:56:25.220053Z"},"content_sha256":"9486f90de9d7b5c2cabeb34c2366a2431c5c534ed55035af47b881a161f57d40","schema_version":"1.0","event_id":"sha256:9486f90de9d7b5c2cabeb34c2366a2431c5c534ed55035af47b881a161f57d40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/bundle.json","state_url":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/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":"2026-05-27T01:56:25Z","links":{"resolver":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA","bundle":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/bundle.json","state":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RXQ65Q3E7EUW2GT7RX7EORVHPA","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":"1c51e120b6fb9532bea2ced4458a5c02a9384c086da401836cb6ca04f92516e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-15T16:21:58Z","title_canon_sha256":"04dd7f152ee2520123660869c80272db22ce91881020f831f47ee483836a5ade"},"schema_version":"1.0","source":{"id":"1603.04747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.04747","created_at":"2026-05-18T01:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"1603.04747v1","created_at":"2026-05-18T01:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.04747","created_at":"2026-05-18T01:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"RXQ65Q3E7EUW","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RXQ65Q3E7EUW2GT7","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RXQ65Q3E","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:9486f90de9d7b5c2cabeb34c2366a2431c5c534ed55035af47b881a161f57d40","target":"graph","created_at":"2026-05-18T01:19:04Z","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":"We propose a new algorithm for topic modeling, Vec2Topic, that identifies the main topics in a corpus using semantic information captured via high-dimensional distributed word embeddings. Our technique is unsupervised and generates a list of topics ranked with respect to importance. We find that it works better than existing topic modeling techniques such as Latent Dirichlet Allocation for identifying key topics in user-generated content, such as emails, chats, etc., where topics are diffused across the corpus. We also find that Vec2Topic works equally well for non-user generated content, such","authors_text":"Gagan Madan, Parag Jain, Ramandeep S Randhawa","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-15T16:21:58Z","title":"Topic Modeling Using Distributed Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.04747","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":"sha256:5dc7d825556e69e7a895546d5c29e14d37eaae5a69217fbf4c50aea5f30177dd","target":"record","created_at":"2026-05-18T01:19:04Z","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":"1c51e120b6fb9532bea2ced4458a5c02a9384c086da401836cb6ca04f92516e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-15T16:21:58Z","title_canon_sha256":"04dd7f152ee2520123660869c80272db22ce91881020f831f47ee483836a5ade"},"schema_version":"1.0","source":{"id":"1603.04747","kind":"arxiv","version":1}},"canonical_sha256":"8de1eec364f9296d1a7f8dfe4746a7782e03463f66a2458d98d2a80e411236b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8de1eec364f9296d1a7f8dfe4746a7782e03463f66a2458d98d2a80e411236b6","first_computed_at":"2026-05-18T01:19:04.056127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:19:04.056127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UqGvrS5PL2tyquKXC0QTkO+BuMByFjSXV7d5f3G3dcymJiiQ+d/dV0uz6orGXeje4FN2mS5QDhXZlJ5VjmWbBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:19:04.056723Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.04747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dc7d825556e69e7a895546d5c29e14d37eaae5a69217fbf4c50aea5f30177dd","sha256:9486f90de9d7b5c2cabeb34c2366a2431c5c534ed55035af47b881a161f57d40"],"state_sha256":"f18db3a0b0fe641a73c981140bcfbd44fac6b4189e9bd1531a7ed21df9d2ac43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eiK4+BWFFMf/zbQDaRYcx/Fzj0RNReLGVb5QdKPjedebmLTxz+4F0KSWehim8CmSy9gSRqJ7qm4hdyNQfB+2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:56:25.223257Z","bundle_sha256":"2dfb47b0530620dccc558176131d13a231c7726a687b7e5e1d6f34bc6aee1ecd"}}