{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:546YC4DGAE23RLNUNUBB3OU7KA","short_pith_number":"pith:546YC4DG","canonical_record":{"source":{"id":"2104.09011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-19T01:56:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6a10f9fc3e0ca6258d316625b03b6993401b3ef5a8263cfd4b66982033dbc360","abstract_canon_sha256":"3a8a268ee84b3648d77c839e7e88957d42c4e5816d5cd12330004a2a941d882b"},"schema_version":"1.0"},"canonical_sha256":"ef3d8170660135b8adb46d021dba9f500f8266ffcad996b0b085d2291afee990","source":{"kind":"arxiv","id":"2104.09011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09011","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09011v1","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09011","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"pith_short_12","alias_value":"546YC4DGAE23","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"pith_short_16","alias_value":"546YC4DGAE23RLNU","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"pith_short_8","alias_value":"546YC4DG","created_at":"2026-07-05T02:32:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:546YC4DGAE23RLNUNUBB3OU7KA","target":"record","payload":{"canonical_record":{"source":{"id":"2104.09011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-19T01:56:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6a10f9fc3e0ca6258d316625b03b6993401b3ef5a8263cfd4b66982033dbc360","abstract_canon_sha256":"3a8a268ee84b3648d77c839e7e88957d42c4e5816d5cd12330004a2a941d882b"},"schema_version":"1.0"},"canonical_sha256":"ef3d8170660135b8adb46d021dba9f500f8266ffcad996b0b085d2291afee990","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:57.801061Z","signature_b64":"f6dgn+zql/hVmJ1lGuu8wYit+khs3LThplEG54LaA3bBj0GKpx4ypSoJKgZLokFspIPj/x5EWx3k2QsN3N3/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef3d8170660135b8adb46d021dba9f500f8266ffcad996b0b085d2291afee990","last_reissued_at":"2026-07-05T02:32:57.800554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:57.800554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.09011","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":"2026-07-05T02:32:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ggTbYx+OsliOoT715UAEDufaVTT3AMMHfvhhGncRljxxjU6xWnIz/A4u0oWmuTr5iAlovMNHWOosnbjdZggHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:47:35.668287Z"},"content_sha256":"28dfc7ef17d068742768ac8ac5d9a7e07a10cad4cb2aa08e9cdf46c6fd200d21","schema_version":"1.0","event_id":"sha256:28dfc7ef17d068742768ac8ac5d9a7e07a10cad4cb2aa08e9cdf46c6fd200d21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:546YC4DGAE23RLNUNUBB3OU7KA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-shot Learning for Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Tomoharu Iwata","submitted_at":"2021-04-19T01:56:48Z","abstract_excerpt":"Topic models have been successfully used for analyzing text documents. However, with existing topic models, many documents are required for training. In this paper, we propose a neural network-based few-shot learning method that can learn a topic model from just a few documents. The neural networks in our model take a small number of documents as inputs, and output topic model priors. The proposed method trains the neural networks such that the expected test likelihood is improved when topic model parameters are estimated by maximizing the posterior probability using the priors based on the EM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09011","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/2104.09011/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":"2026-07-05T02:32:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yKDIxhMiOqZG/nzVrnmRuH4Yw9DEQ8CB8gLBDY4xFuUSQLRT6QbcQdATBdUb0pIsfz9pkw415su3cPOgN6FaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:47:35.668797Z"},"content_sha256":"83731ae1242aded9310c2d414032392f7597b1638f113ce58466f4e9844741d7","schema_version":"1.0","event_id":"sha256:83731ae1242aded9310c2d414032392f7597b1638f113ce58466f4e9844741d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/546YC4DGAE23RLNUNUBB3OU7KA/bundle.json","state_url":"https://pith.science/pith/546YC4DGAE23RLNUNUBB3OU7KA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/546YC4DGAE23RLNUNUBB3OU7KA/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":"2026-08-08T08:47:35Z","links":{"resolver":"https://pith.science/pith/546YC4DGAE23RLNUNUBB3OU7KA","bundle":"https://pith.science/pith/546YC4DGAE23RLNUNUBB3OU7KA/bundle.json","state":"https://pith.science/pith/546YC4DGAE23RLNUNUBB3OU7KA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/546YC4DGAE23RLNUNUBB3OU7KA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:546YC4DGAE23RLNUNUBB3OU7KA","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":"3a8a268ee84b3648d77c839e7e88957d42c4e5816d5cd12330004a2a941d882b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-19T01:56:48Z","title_canon_sha256":"6a10f9fc3e0ca6258d316625b03b6993401b3ef5a8263cfd4b66982033dbc360"},"schema_version":"1.0","source":{"id":"2104.09011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09011","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09011v1","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09011","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"pith_short_12","alias_value":"546YC4DGAE23","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"pith_short_16","alias_value":"546YC4DGAE23RLNU","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"pith_short_8","alias_value":"546YC4DG","created_at":"2026-07-05T02:32:57Z"}],"graph_snapshots":[{"event_id":"sha256:83731ae1242aded9310c2d414032392f7597b1638f113ce58466f4e9844741d7","target":"graph","created_at":"2026-07-05T02:32:57Z","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/2104.09011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic models have been successfully used for analyzing text documents. However, with existing topic models, many documents are required for training. In this paper, we propose a neural network-based few-shot learning method that can learn a topic model from just a few documents. The neural networks in our model take a small number of documents as inputs, and output topic model priors. The proposed method trains the neural networks such that the expected test likelihood is improved when topic model parameters are estimated by maximizing the posterior probability using the priors based on the EM","authors_text":"Tomoharu Iwata","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-19T01:56:48Z","title":"Few-shot Learning for Topic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09011","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":"sha256:28dfc7ef17d068742768ac8ac5d9a7e07a10cad4cb2aa08e9cdf46c6fd200d21","target":"record","created_at":"2026-07-05T02:32:57Z","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":"3a8a268ee84b3648d77c839e7e88957d42c4e5816d5cd12330004a2a941d882b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-19T01:56:48Z","title_canon_sha256":"6a10f9fc3e0ca6258d316625b03b6993401b3ef5a8263cfd4b66982033dbc360"},"schema_version":"1.0","source":{"id":"2104.09011","kind":"arxiv","version":1}},"canonical_sha256":"ef3d8170660135b8adb46d021dba9f500f8266ffcad996b0b085d2291afee990","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef3d8170660135b8adb46d021dba9f500f8266ffcad996b0b085d2291afee990","first_computed_at":"2026-07-05T02:32:57.800554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:57.800554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f6dgn+zql/hVmJ1lGuu8wYit+khs3LThplEG54LaA3bBj0GKpx4ypSoJKgZLokFspIPj/x5EWx3k2QsN3N3/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:57.801061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28dfc7ef17d068742768ac8ac5d9a7e07a10cad4cb2aa08e9cdf46c6fd200d21","sha256:83731ae1242aded9310c2d414032392f7597b1638f113ce58466f4e9844741d7"],"state_sha256":"4e6c53485a5f20b504c12e0042a7462519b11040846bf3f1775beb7dc9abaed0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9s+Ag1kWWuM61IDV20C/Ax4OqmcNpvUj7G6ijottMq9/1i6ITKZcJyDVLs3W9bEgVB9Q2fx9RhZ2RN/3KQqdDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:47:35.673797Z","bundle_sha256":"2b55bc6d96cbf18979c082109c30df95ab49b799a7757d51cce957aafdb5bd07"}}