{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:EPSYCJ4WE4COUKVKQRRRFKAOMZ","short_pith_number":"pith:EPSYCJ4W","canonical_record":{"source":{"id":"1606.00577","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T08:15:15Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"18ec980bd3b2504abb91689435aac76926c31b062f0470b6bab0732c64b75dbb","abstract_canon_sha256":"c2c26468a6a57671edb7ae4b2815b1765e2e371c5e2ea3e6151e319f7939819b"},"schema_version":"1.0"},"canonical_sha256":"23e58127962704ea2aaa846312a80e666cc30330b823a0521f144934122e237d","source":{"kind":"arxiv","id":"1606.00577","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.00577","created_at":"2026-05-18T00:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"1606.00577v3","created_at":"2026-05-18T00:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00577","created_at":"2026-05-18T00:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"EPSYCJ4WE4CO","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EPSYCJ4WE4COUKVK","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EPSYCJ4W","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:EPSYCJ4WE4COUKVKQRRRFKAOMZ","target":"record","payload":{"canonical_record":{"source":{"id":"1606.00577","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T08:15:15Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"18ec980bd3b2504abb91689435aac76926c31b062f0470b6bab0732c64b75dbb","abstract_canon_sha256":"c2c26468a6a57671edb7ae4b2815b1765e2e371c5e2ea3e6151e319f7939819b"},"schema_version":"1.0"},"canonical_sha256":"23e58127962704ea2aaa846312a80e666cc30330b823a0521f144934122e237d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:16.109283Z","signature_b64":"jRA778Fvg1/nmEu6LJjbioa8qkumaq34mY8frKZbbVUReuPJxsiWI1xAtQkiLPSnLxWh1EsGf3Es52VcKIm5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23e58127962704ea2aaa846312a80e666cc30330b823a0521f144934122e237d","last_reissued_at":"2026-05-18T00:44:16.108808Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:16.108808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.00577","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pX5ycBnpVNZngj1bEkAWP6ilT25yr3qAE4MY0GRFVSeCqKxorjrSwLx3XCwpy8bJdyBHELaGjc9YaJX6pG+IAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:54:41.619653Z"},"content_sha256":"bfe803a24ecdac9b77ced0fd5badd9f214b8e61e3264d091fe93f3b3ea62fa24","schema_version":"1.0","event_id":"sha256:bfe803a24ecdac9b77ced0fd5badd9f214b8e61e3264d091fe93f3b3ea62fa24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:EPSYCJ4WE4COUKVKQRRRFKAOMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Source-LDA: Enhancing probabilistic topic models using prior knowledge sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Corey Arnold, Justin Wood, Patrick Tan, Wei Wang","submitted_at":"2016-06-02T08:15:15Z","abstract_excerpt":"A popular approach to topic modeling involves extracting co-occurring n-grams of a corpus into semantic themes. The set of n-grams in a theme represents an underlying topic, but most topic modeling approaches are not able to label these sets of words with a single n-gram. Such labels are useful for topic identification in summarization systems. This paper introduces a novel approach to labeling a group of n-grams comprising an individual topic. The approach taken is to complement the existing topic distributions over words with a known distribution based on a predefined set of topics. This is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00577","kind":"arxiv","version":3},"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":"2026-05-18T00:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JZfUIfxg2mJG70wkNwzycFYnGcdbqH/ScZabH1M+FKiteBiEJui1Hxd1rUFy5aaWz0TvjduselnFghqt535SCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:54:41.620011Z"},"content_sha256":"7b75a4832993767018f45db834a8b30052305a06cbe76953f797106e09ec588e","schema_version":"1.0","event_id":"sha256:7b75a4832993767018f45db834a8b30052305a06cbe76953f797106e09ec588e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPSYCJ4WE4COUKVKQRRRFKAOMZ/bundle.json","state_url":"https://pith.science/pith/EPSYCJ4WE4COUKVKQRRRFKAOMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPSYCJ4WE4COUKVKQRRRFKAOMZ/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":"2026-05-28T01:54:41Z","links":{"resolver":"https://pith.science/pith/EPSYCJ4WE4COUKVKQRRRFKAOMZ","bundle":"https://pith.science/pith/EPSYCJ4WE4COUKVKQRRRFKAOMZ/bundle.json","state":"https://pith.science/pith/EPSYCJ4WE4COUKVKQRRRFKAOMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPSYCJ4WE4COUKVKQRRRFKAOMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:EPSYCJ4WE4COUKVKQRRRFKAOMZ","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":"c2c26468a6a57671edb7ae4b2815b1765e2e371c5e2ea3e6151e319f7939819b","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T08:15:15Z","title_canon_sha256":"18ec980bd3b2504abb91689435aac76926c31b062f0470b6bab0732c64b75dbb"},"schema_version":"1.0","source":{"id":"1606.00577","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.00577","created_at":"2026-05-18T00:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"1606.00577v3","created_at":"2026-05-18T00:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00577","created_at":"2026-05-18T00:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"EPSYCJ4WE4CO","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EPSYCJ4WE4COUKVK","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EPSYCJ4W","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:7b75a4832993767018f45db834a8b30052305a06cbe76953f797106e09ec588e","target":"graph","created_at":"2026-05-18T00:44:16Z","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":"A popular approach to topic modeling involves extracting co-occurring n-grams of a corpus into semantic themes. The set of n-grams in a theme represents an underlying topic, but most topic modeling approaches are not able to label these sets of words with a single n-gram. Such labels are useful for topic identification in summarization systems. This paper introduces a novel approach to labeling a group of n-grams comprising an individual topic. The approach taken is to complement the existing topic distributions over words with a known distribution based on a predefined set of topics. This is ","authors_text":"Corey Arnold, Justin Wood, Patrick Tan, Wei Wang","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T08:15:15Z","title":"Source-LDA: Enhancing probabilistic topic models using prior knowledge sources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00577","kind":"arxiv","version":3},"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:bfe803a24ecdac9b77ced0fd5badd9f214b8e61e3264d091fe93f3b3ea62fa24","target":"record","created_at":"2026-05-18T00:44:16Z","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":"c2c26468a6a57671edb7ae4b2815b1765e2e371c5e2ea3e6151e319f7939819b","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T08:15:15Z","title_canon_sha256":"18ec980bd3b2504abb91689435aac76926c31b062f0470b6bab0732c64b75dbb"},"schema_version":"1.0","source":{"id":"1606.00577","kind":"arxiv","version":3}},"canonical_sha256":"23e58127962704ea2aaa846312a80e666cc30330b823a0521f144934122e237d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23e58127962704ea2aaa846312a80e666cc30330b823a0521f144934122e237d","first_computed_at":"2026-05-18T00:44:16.108808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:16.108808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jRA778Fvg1/nmEu6LJjbioa8qkumaq34mY8frKZbbVUReuPJxsiWI1xAtQkiLPSnLxWh1EsGf3Es52VcKIm5Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:16.109283Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.00577","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfe803a24ecdac9b77ced0fd5badd9f214b8e61e3264d091fe93f3b3ea62fa24","sha256:7b75a4832993767018f45db834a8b30052305a06cbe76953f797106e09ec588e"],"state_sha256":"28ad8b4d1e7f81d5ae248a4de27e401768bc6850fbaada20343f932b1b7973dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y20658aSRgJW2dxmkWD8CuIVXpzArNcetnugrNzPhtkOHPjkceY01rBnwNvfIl3BcBc9I+Q6gIh/o13Bc/IJBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:54:41.622119Z","bundle_sha256":"b072254073f328fda63d46a5e448c5ccefca897f765b3486aab61d6881c936fe"}}