{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:DO4EK7DVOMSHKDLLNLHLBJMREP","short_pith_number":"pith:DO4EK7DV","canonical_record":{"source":{"id":"1404.4606","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-04-16T12:59:29Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"80f4f72e61a255320f81802ff8a7bdab61ac5b05de4c33ad3ba0a98bafb15703","abstract_canon_sha256":"c605aa8c7ca23df6a770baef482ef71674a6b3bbaa5d7d65af2e9d0fadfb168d"},"schema_version":"1.0"},"canonical_sha256":"1bb8457c757324750d6b6aceb0a59123fa52ae77d235c44ad18aa1b6b99e4956","source":{"kind":"arxiv","id":"1404.4606","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1404.4606","created_at":"2026-05-18T02:49:28Z"},{"alias_kind":"arxiv_version","alias_value":"1404.4606v3","created_at":"2026-05-18T02:49:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.4606","created_at":"2026-05-18T02:49:28Z"},{"alias_kind":"pith_short_12","alias_value":"DO4EK7DVOMSH","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DO4EK7DVOMSHKDLL","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DO4EK7DV","created_at":"2026-05-18T12:28:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:DO4EK7DVOMSHKDLLNLHLBJMREP","target":"record","payload":{"canonical_record":{"source":{"id":"1404.4606","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-04-16T12:59:29Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"80f4f72e61a255320f81802ff8a7bdab61ac5b05de4c33ad3ba0a98bafb15703","abstract_canon_sha256":"c605aa8c7ca23df6a770baef482ef71674a6b3bbaa5d7d65af2e9d0fadfb168d"},"schema_version":"1.0"},"canonical_sha256":"1bb8457c757324750d6b6aceb0a59123fa52ae77d235c44ad18aa1b6b99e4956","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:49:28.401278Z","signature_b64":"kGeBjL9NgC5fBnNa774VRz1Zq14BrpONA2H9wRYphpeAvHcXpwzinIoZkHmcmR56yjaKy6m0iX7uyT2xiFyYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bb8457c757324750d6b6aceb0a59123fa52ae77d235c44ad18aa1b6b99e4956","last_reissued_at":"2026-05-18T02:49:28.400640Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:49:28.400640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1404.4606","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":"2026-05-18T02:49:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8j1NOOaZbpZvqgzUznLBPKFXFQybUm6kNavPLCm+7RsMYlkT9K6vO1RppsZBsQBcH6t5LeGazhcAxhuwBSPICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T03:12:13.772186Z"},"content_sha256":"19558aed25e7e862103ad14d6d2b60afb6826589050e88c2feada695ea7c98f3","schema_version":"1.0","event_id":"sha256:19558aed25e7e862103ad14d6d2b60afb6826589050e88c2feada695ea7c98f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:DO4EK7DVOMSHKDLLNLHLBJMREP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Many Topics? Stability Analysis for Topic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Derek Greene, Derek O'Callaghan, P\\'adraig Cunningham","submitted_at":"2014-04-16T12:59:29Z","abstract_excerpt":"Topic modeling refers to the task of discovering the underlying thematic structure in a text corpus, where the output is commonly presented as a report of the top terms appearing in each topic. Despite the diversity of topic modeling algorithms that have been proposed, a common challenge in successfully applying these techniques is the selection of an appropriate number of topics for a given corpus. Choosing too few topics will produce results that are overly broad, while choosing too many will result in the \"over-clustering\" of a corpus into many small, highly-similar topics. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.4606","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":"2026-05-18T02:49:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Hs/Q3Ad6kk/K0APuuc+JoGOWORDusng3Ip3mioBGZHmWcnhNveBRWHSHSphtKNeQ61D0Z4k+X/+lYUPrEqcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T03:12:13.772549Z"},"content_sha256":"9173126006d1c66724e3b6e5248314e5bb9cecc07cbcd17b690512a8f6e5dc2f","schema_version":"1.0","event_id":"sha256:9173126006d1c66724e3b6e5248314e5bb9cecc07cbcd17b690512a8f6e5dc2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DO4EK7DVOMSHKDLLNLHLBJMREP/bundle.json","state_url":"https://pith.science/pith/DO4EK7DVOMSHKDLLNLHLBJMREP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DO4EK7DVOMSHKDLLNLHLBJMREP/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":"2026-06-20T03:12:13Z","links":{"resolver":"https://pith.science/pith/DO4EK7DVOMSHKDLLNLHLBJMREP","bundle":"https://pith.science/pith/DO4EK7DVOMSHKDLLNLHLBJMREP/bundle.json","state":"https://pith.science/pith/DO4EK7DVOMSHKDLLNLHLBJMREP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DO4EK7DVOMSHKDLLNLHLBJMREP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:DO4EK7DVOMSHKDLLNLHLBJMREP","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":"c605aa8c7ca23df6a770baef482ef71674a6b3bbaa5d7d65af2e9d0fadfb168d","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-04-16T12:59:29Z","title_canon_sha256":"80f4f72e61a255320f81802ff8a7bdab61ac5b05de4c33ad3ba0a98bafb15703"},"schema_version":"1.0","source":{"id":"1404.4606","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1404.4606","created_at":"2026-05-18T02:49:28Z"},{"alias_kind":"arxiv_version","alias_value":"1404.4606v3","created_at":"2026-05-18T02:49:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.4606","created_at":"2026-05-18T02:49:28Z"},{"alias_kind":"pith_short_12","alias_value":"DO4EK7DVOMSH","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DO4EK7DVOMSHKDLL","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DO4EK7DV","created_at":"2026-05-18T12:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:9173126006d1c66724e3b6e5248314e5bb9cecc07cbcd17b690512a8f6e5dc2f","target":"graph","created_at":"2026-05-18T02:49:28Z","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":"Topic modeling refers to the task of discovering the underlying thematic structure in a text corpus, where the output is commonly presented as a report of the top terms appearing in each topic. Despite the diversity of topic modeling algorithms that have been proposed, a common challenge in successfully applying these techniques is the selection of an appropriate number of topics for a given corpus. Choosing too few topics will produce results that are overly broad, while choosing too many will result in the \"over-clustering\" of a corpus into many small, highly-similar topics. In this paper, w","authors_text":"Derek Greene, Derek O'Callaghan, P\\'adraig Cunningham","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-04-16T12:59:29Z","title":"How Many Topics? Stability Analysis for Topic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.4606","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":"sha256:19558aed25e7e862103ad14d6d2b60afb6826589050e88c2feada695ea7c98f3","target":"record","created_at":"2026-05-18T02:49:28Z","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":"c605aa8c7ca23df6a770baef482ef71674a6b3bbaa5d7d65af2e9d0fadfb168d","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-04-16T12:59:29Z","title_canon_sha256":"80f4f72e61a255320f81802ff8a7bdab61ac5b05de4c33ad3ba0a98bafb15703"},"schema_version":"1.0","source":{"id":"1404.4606","kind":"arxiv","version":3}},"canonical_sha256":"1bb8457c757324750d6b6aceb0a59123fa52ae77d235c44ad18aa1b6b99e4956","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bb8457c757324750d6b6aceb0a59123fa52ae77d235c44ad18aa1b6b99e4956","first_computed_at":"2026-05-18T02:49:28.400640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:49:28.400640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kGeBjL9NgC5fBnNa774VRz1Zq14BrpONA2H9wRYphpeAvHcXpwzinIoZkHmcmR56yjaKy6m0iX7uyT2xiFyYAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:49:28.401278Z","signed_message":"canonical_sha256_bytes"},"source_id":"1404.4606","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19558aed25e7e862103ad14d6d2b60afb6826589050e88c2feada695ea7c98f3","sha256:9173126006d1c66724e3b6e5248314e5bb9cecc07cbcd17b690512a8f6e5dc2f"],"state_sha256":"230a77117b9935f6951324c13a0d7abeeec64ce5f3009f0307f8ca2f23c9ddf3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sGkCg+cPlELAYUEESg50B7JK9vA3cIrU6sFWaPzQod8zu03V0geVMW6yAFvPNf27FBK619Qj1SljRvg697i+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T03:12:13.774596Z","bundle_sha256":"7744e82373c07dde0475c01ea446f374b185d8ca8b83afcb816866865d4c9f12"}}