{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:H5QNKJ7KEHDWWBTY3I4P6EJN7L","short_pith_number":"pith:H5QNKJ7K","canonical_record":{"source":{"id":"1707.09823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-31T12:48:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c2528b510f62026d3ba060c3ac344af6408630c91ff53b2c1a15d62c111244c0","abstract_canon_sha256":"67aae37620583155048b927435505965e20e683c620746d907983ffc86154ba5"},"schema_version":"1.0"},"canonical_sha256":"3f60d527ea21c76b0678da38ff112dfaf0fc4bf53cf38e92619062f5bf3a5d33","source":{"kind":"arxiv","id":"1707.09823","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09823","created_at":"2026-05-18T00:39:08Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09823v1","created_at":"2026-05-18T00:39:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09823","created_at":"2026-05-18T00:39:08Z"},{"alias_kind":"pith_short_12","alias_value":"H5QNKJ7KEHDW","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"H5QNKJ7KEHDWWBTY","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"H5QNKJ7K","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:H5QNKJ7KEHDWWBTY3I4P6EJN7L","target":"record","payload":{"canonical_record":{"source":{"id":"1707.09823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-31T12:48:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c2528b510f62026d3ba060c3ac344af6408630c91ff53b2c1a15d62c111244c0","abstract_canon_sha256":"67aae37620583155048b927435505965e20e683c620746d907983ffc86154ba5"},"schema_version":"1.0"},"canonical_sha256":"3f60d527ea21c76b0678da38ff112dfaf0fc4bf53cf38e92619062f5bf3a5d33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:08.121890Z","signature_b64":"04/CEJIc75Rlv/aHC7oDKB9pcrqY+m41sZR6DrbNnk9vrlTjk4GCLLAaIyWxOXzuhm73qSjKIIqvAfRQy+rwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f60d527ea21c76b0678da38ff112dfaf0fc4bf53cf38e92619062f5bf3a5d33","last_reissued_at":"2026-05-18T00:39:08.121167Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:08.121167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.09823","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":"2026-05-18T00:39:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0S0gsLlMJaNOlT4ACKdsFxgOKmZYNuqJ3o8ocDJrwRZDx3izPDsHcEJMcwhgv3LtELfl6Mj2QxIL7z7q1IQsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:20:55.543564Z"},"content_sha256":"be50c24c72d333be59a3c75f8f12cf6a68202c66da46c4099aaabd06de086627","schema_version":"1.0","event_id":"sha256:be50c24c72d333be59a3c75f8f12cf6a68202c66da46c4099aaabd06de086627"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:H5QNKJ7KEHDWWBTY3I4P6EJN7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Familia: An Open-Source Toolkit for Industrial Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chen Li, Di Jiang, Rongzhong Lian, Siqi Bao, Zeyu Chen","submitted_at":"2017-07-31T12:48:45Z","abstract_excerpt":"Familia is an open-source toolkit for pragmatic topic modeling in industry. Familia abstracts the utilities of topic modeling in industry as two paradigms: semantic representation and semantic matching. Efficient implementations of the two paradigms are made publicly available for the first time. Furthermore, we provide off-the-shelf topic models trained on large-scale industrial corpora, including Latent Dirichlet Allocation (LDA), SentenceLDA and Topical Word Embedding (TWE). We further describe typical applications which are successfully powered by topic modeling, in order to ease the confu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09823","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":"2026-05-18T00:39:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QJXk5xQHvIsiQYT/ex1HXg23dJglbi2D3JnEeoiuz5ODK4VV6EaVLc9UdWDh/vO28GC1ZYW+T9rm/FYPry4kAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:20:55.544134Z"},"content_sha256":"28a82053b1b1c514ca3be64026fa33af15d2fe30954046e601413ca3f4bf44be","schema_version":"1.0","event_id":"sha256:28a82053b1b1c514ca3be64026fa33af15d2fe30954046e601413ca3f4bf44be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5QNKJ7KEHDWWBTY3I4P6EJN7L/bundle.json","state_url":"https://pith.science/pith/H5QNKJ7KEHDWWBTY3I4P6EJN7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5QNKJ7KEHDWWBTY3I4P6EJN7L/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":"2026-05-26T23:20:55Z","links":{"resolver":"https://pith.science/pith/H5QNKJ7KEHDWWBTY3I4P6EJN7L","bundle":"https://pith.science/pith/H5QNKJ7KEHDWWBTY3I4P6EJN7L/bundle.json","state":"https://pith.science/pith/H5QNKJ7KEHDWWBTY3I4P6EJN7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5QNKJ7KEHDWWBTY3I4P6EJN7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:H5QNKJ7KEHDWWBTY3I4P6EJN7L","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":"67aae37620583155048b927435505965e20e683c620746d907983ffc86154ba5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-31T12:48:45Z","title_canon_sha256":"c2528b510f62026d3ba060c3ac344af6408630c91ff53b2c1a15d62c111244c0"},"schema_version":"1.0","source":{"id":"1707.09823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09823","created_at":"2026-05-18T00:39:08Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09823v1","created_at":"2026-05-18T00:39:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09823","created_at":"2026-05-18T00:39:08Z"},{"alias_kind":"pith_short_12","alias_value":"H5QNKJ7KEHDW","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"H5QNKJ7KEHDWWBTY","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"H5QNKJ7K","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:28a82053b1b1c514ca3be64026fa33af15d2fe30954046e601413ca3f4bf44be","target":"graph","created_at":"2026-05-18T00:39:08Z","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":"Familia is an open-source toolkit for pragmatic topic modeling in industry. Familia abstracts the utilities of topic modeling in industry as two paradigms: semantic representation and semantic matching. Efficient implementations of the two paradigms are made publicly available for the first time. Furthermore, we provide off-the-shelf topic models trained on large-scale industrial corpora, including Latent Dirichlet Allocation (LDA), SentenceLDA and Topical Word Embedding (TWE). We further describe typical applications which are successfully powered by topic modeling, in order to ease the confu","authors_text":"Chen Li, Di Jiang, Rongzhong Lian, Siqi Bao, Zeyu Chen","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-31T12:48:45Z","title":"Familia: An Open-Source Toolkit for Industrial Topic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09823","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:be50c24c72d333be59a3c75f8f12cf6a68202c66da46c4099aaabd06de086627","target":"record","created_at":"2026-05-18T00:39:08Z","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":"67aae37620583155048b927435505965e20e683c620746d907983ffc86154ba5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-31T12:48:45Z","title_canon_sha256":"c2528b510f62026d3ba060c3ac344af6408630c91ff53b2c1a15d62c111244c0"},"schema_version":"1.0","source":{"id":"1707.09823","kind":"arxiv","version":1}},"canonical_sha256":"3f60d527ea21c76b0678da38ff112dfaf0fc4bf53cf38e92619062f5bf3a5d33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f60d527ea21c76b0678da38ff112dfaf0fc4bf53cf38e92619062f5bf3a5d33","first_computed_at":"2026-05-18T00:39:08.121167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:08.121167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"04/CEJIc75Rlv/aHC7oDKB9pcrqY+m41sZR6DrbNnk9vrlTjk4GCLLAaIyWxOXzuhm73qSjKIIqvAfRQy+rwBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:08.121890Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.09823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be50c24c72d333be59a3c75f8f12cf6a68202c66da46c4099aaabd06de086627","sha256:28a82053b1b1c514ca3be64026fa33af15d2fe30954046e601413ca3f4bf44be"],"state_sha256":"61809813c18e07e8ccb8d94315c36132ce1d29d4582f75724c2f98e1f65cd6e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sarddWS8J4SZyGIMwJdMQ3X5+NZGcM8NvsYrtwXk83Hxta/z5sjblXkOD4F3q2d4AnZoytfwmw2zaWMXj0B+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T23:20:55.547450Z","bundle_sha256":"dbd03318d13b852db1dd87f4cc6c51ab4ce2cbbf98ce31325bcbcc13c6494989"}}