{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:S5KYNGLF3V5OQWA4OJHFPAECON","short_pith_number":"pith:S5KYNGLF","canonical_record":{"source":{"id":"2011.10428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-20T14:51:07Z","cross_cats_sorted":[],"title_canon_sha256":"b1cdfa99bc9866a2886b7c860231ead930948025ecfa0aefdbd1f2b390aa50dd","abstract_canon_sha256":"d385c1f00aca80fdd6bb75661802a748ab2e0aae6fe49441d446c30e959325b8"},"schema_version":"1.0"},"canonical_sha256":"9755869965dd7ae8581c724e578082737fcbb8f24e003c628cb715926eb7b931","source":{"kind":"arxiv","id":"2011.10428","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.10428","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"arxiv_version","alias_value":"2011.10428v1","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.10428","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"pith_short_12","alias_value":"S5KYNGLF3V5O","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"pith_short_16","alias_value":"S5KYNGLF3V5OQWA4","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"pith_short_8","alias_value":"S5KYNGLF","created_at":"2026-07-05T01:53:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:S5KYNGLF3V5OQWA4OJHFPAECON","target":"record","payload":{"canonical_record":{"source":{"id":"2011.10428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-20T14:51:07Z","cross_cats_sorted":[],"title_canon_sha256":"b1cdfa99bc9866a2886b7c860231ead930948025ecfa0aefdbd1f2b390aa50dd","abstract_canon_sha256":"d385c1f00aca80fdd6bb75661802a748ab2e0aae6fe49441d446c30e959325b8"},"schema_version":"1.0"},"canonical_sha256":"9755869965dd7ae8581c724e578082737fcbb8f24e003c628cb715926eb7b931","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:15.024938Z","signature_b64":"Ykjpv3BUrUgvVdixu2+MMePA9NrASmUCfZLHusMAggGXRJLLVLdELNox+myRRwnovWi78ja0DezCDJkF3x7lBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9755869965dd7ae8581c724e578082737fcbb8f24e003c628cb715926eb7b931","last_reissued_at":"2026-07-05T01:53:15.024530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:15.024530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.10428","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":"2026-07-05T01:53:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZs9aW6UBw8n8XDGvpzeHbR4jil9KZ7Db82H3kqVEzwBw0dDI0y6s0rTGHYxa///SPf+2G5yVKkgis8l8MiJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:24:46.939060Z"},"content_sha256":"f2d40a870c2c683991252cad5d4ad2b097a046f3909e9dcca856b6697ca141f7","schema_version":"1.0","event_id":"sha256:f2d40a870c2c683991252cad5d4ad2b097a046f3909e9dcca856b6697ca141f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:S5KYNGLF3V5OQWA4OJHFPAECON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic modelling discourse dynamics in historical newspapers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elaine Zosa, Jani Marjanen, Lidia Pivovarova, Mikko Tolonen, Simon Hengchen","submitted_at":"2020-11-20T14:51:07Z","abstract_excerpt":"This paper addresses methodological issues in diachronic data analysis for historical research. We apply two families of topic models (LDA and DTM) on a relatively large set of historical newspapers, with the aim of capturing and understanding discourse dynamics. Our case study focuses on newspapers and periodicals published in Finland between 1854 and 1917, but our method can easily be transposed to any diachronic data. Our main contributions are a) a combined sampling, training and inference procedure for applying topic models to huge and imbalanced diachronic text collections; b) a discussi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.10428","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.10428/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:53:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rRurNAxgYhv/Xor3H5HM1QbvmFzEHlSc5q6kqMyKQPcqu/W95qBQvp9bJjA3rjjHykAYV4KlkP8USu4mPjleAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:24:46.939730Z"},"content_sha256":"19536b6747c0add823f026099c88eaca1488de3fa559dc87853a89086844ae04","schema_version":"1.0","event_id":"sha256:19536b6747c0add823f026099c88eaca1488de3fa559dc87853a89086844ae04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S5KYNGLF3V5OQWA4OJHFPAECON/bundle.json","state_url":"https://pith.science/pith/S5KYNGLF3V5OQWA4OJHFPAECON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S5KYNGLF3V5OQWA4OJHFPAECON/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":"2026-07-07T07:24:46Z","links":{"resolver":"https://pith.science/pith/S5KYNGLF3V5OQWA4OJHFPAECON","bundle":"https://pith.science/pith/S5KYNGLF3V5OQWA4OJHFPAECON/bundle.json","state":"https://pith.science/pith/S5KYNGLF3V5OQWA4OJHFPAECON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S5KYNGLF3V5OQWA4OJHFPAECON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:S5KYNGLF3V5OQWA4OJHFPAECON","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":"d385c1f00aca80fdd6bb75661802a748ab2e0aae6fe49441d446c30e959325b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-20T14:51:07Z","title_canon_sha256":"b1cdfa99bc9866a2886b7c860231ead930948025ecfa0aefdbd1f2b390aa50dd"},"schema_version":"1.0","source":{"id":"2011.10428","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.10428","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"arxiv_version","alias_value":"2011.10428v1","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.10428","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"pith_short_12","alias_value":"S5KYNGLF3V5O","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"pith_short_16","alias_value":"S5KYNGLF3V5OQWA4","created_at":"2026-07-05T01:53:15Z"},{"alias_kind":"pith_short_8","alias_value":"S5KYNGLF","created_at":"2026-07-05T01:53:15Z"}],"graph_snapshots":[{"event_id":"sha256:19536b6747c0add823f026099c88eaca1488de3fa559dc87853a89086844ae04","target":"graph","created_at":"2026-07-05T01:53:15Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.10428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses methodological issues in diachronic data analysis for historical research. We apply two families of topic models (LDA and DTM) on a relatively large set of historical newspapers, with the aim of capturing and understanding discourse dynamics. Our case study focuses on newspapers and periodicals published in Finland between 1854 and 1917, but our method can easily be transposed to any diachronic data. Our main contributions are a) a combined sampling, training and inference procedure for applying topic models to huge and imbalanced diachronic text collections; b) a discussi","authors_text":"Elaine Zosa, Jani Marjanen, Lidia Pivovarova, Mikko Tolonen, Simon Hengchen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-20T14:51:07Z","title":"Topic modelling discourse dynamics in historical newspapers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.10428","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:f2d40a870c2c683991252cad5d4ad2b097a046f3909e9dcca856b6697ca141f7","target":"record","created_at":"2026-07-05T01:53:15Z","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":"d385c1f00aca80fdd6bb75661802a748ab2e0aae6fe49441d446c30e959325b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-20T14:51:07Z","title_canon_sha256":"b1cdfa99bc9866a2886b7c860231ead930948025ecfa0aefdbd1f2b390aa50dd"},"schema_version":"1.0","source":{"id":"2011.10428","kind":"arxiv","version":1}},"canonical_sha256":"9755869965dd7ae8581c724e578082737fcbb8f24e003c628cb715926eb7b931","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9755869965dd7ae8581c724e578082737fcbb8f24e003c628cb715926eb7b931","first_computed_at":"2026-07-05T01:53:15.024530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:15.024530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ykjpv3BUrUgvVdixu2+MMePA9NrASmUCfZLHusMAggGXRJLLVLdELNox+myRRwnovWi78ja0DezCDJkF3x7lBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:15.024938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.10428","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2d40a870c2c683991252cad5d4ad2b097a046f3909e9dcca856b6697ca141f7","sha256:19536b6747c0add823f026099c88eaca1488de3fa559dc87853a89086844ae04"],"state_sha256":"1fbef6755496084aef40732a95dbc61e616520bf8c8eb060786b9c0a0ec86ea5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nwu4cQLJti6EV1rbZO3r7pU4+Z4aqpbL1YXu5/bZ2qQD7MeKlorfm1WJg0QoyMz6Ut6yS9+4fqaH6UkY2W2kCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:24:46.943538Z","bundle_sha256":"e51f1c80373223b7a8afa6b80ebeb8ad9993811414c5992d4631e02807182b95"}}