{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:KFDWPMWUZQNXPWWRX32I5W4FIG","short_pith_number":"pith:KFDWPMWU","canonical_record":{"source":{"id":"1502.02277","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-02-08T17:32:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d967e2f7d35065f73f3b4535a05564b808c34bb7c09395987814316924838845","abstract_canon_sha256":"b63b5395d14b74549422b8f8ee1f38d3f7ede07ed02baad18f183d2695c9e86f"},"schema_version":"1.0"},"canonical_sha256":"514767b2d4cc1b77dad1bef48edb85418aa77af9f4d4643cbab7b162a692fa98","source":{"kind":"arxiv","id":"1502.02277","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.02277","created_at":"2026-05-18T02:27:43Z"},{"alias_kind":"arxiv_version","alias_value":"1502.02277v1","created_at":"2026-05-18T02:27:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.02277","created_at":"2026-05-18T02:27:43Z"},{"alias_kind":"pith_short_12","alias_value":"KFDWPMWUZQNX","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"KFDWPMWUZQNXPWWR","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"KFDWPMWU","created_at":"2026-05-18T12:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:KFDWPMWUZQNXPWWRX32I5W4FIG","target":"record","payload":{"canonical_record":{"source":{"id":"1502.02277","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-02-08T17:32:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d967e2f7d35065f73f3b4535a05564b808c34bb7c09395987814316924838845","abstract_canon_sha256":"b63b5395d14b74549422b8f8ee1f38d3f7ede07ed02baad18f183d2695c9e86f"},"schema_version":"1.0"},"canonical_sha256":"514767b2d4cc1b77dad1bef48edb85418aa77af9f4d4643cbab7b162a692fa98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:27:43.038541Z","signature_b64":"qAM9kDISqqcvVzEd/OIuoB6VPbU+4NlXHRWEH7hIdKXX+K0muh7bzF2Z7CtpCIPo+xkaQPdN+Smx9bj65TpoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514767b2d4cc1b77dad1bef48edb85418aa77af9f4d4643cbab7b162a692fa98","last_reissued_at":"2026-05-18T02:27:43.037736Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:27:43.037736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.02277","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":"2026-05-18T02:27:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WI23QD5EdPQMO2NveIsZ8zz1GiIn6RN3M31PQlSYZSP6NmIjZfsh6D+eOMYXtf1EpCV4O2SZGomL1XDS6FZqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:02:32.102390Z"},"content_sha256":"bc3ae94213b2d8c4f6017969d3a8c4da5b8c1496d9cb2adde472c1228b08cc87","schema_version":"1.0","event_id":"sha256:bc3ae94213b2d8c4f6017969d3a8c4da5b8c1496d9cb2adde472c1228b08cc87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:KFDWPMWUZQNXPWWRX32I5W4FIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Term Frequency Normalization for Multi-topical Documents, and Application to Language Modeling Approaches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"In-Su Kang, Jong-Hyeok Lee, Seung-Hoon Na","submitted_at":"2015-02-08T17:32:44Z","abstract_excerpt":"Term frequency normalization is a serious issue since lengths of documents are various. Generally, documents become long due to two different reasons - verbosity and multi-topicality. First, verbosity means that the same topic is repeatedly mentioned by terms related to the topic, so that term frequency is more increased than the well-summarized one. Second, multi-topicality indicates that a document has a broad discussion of multi-topics, rather than single topic. Although these document characteristics should be differently handled, all previous methods of term frequency normalization have i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.02277","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":"2026-05-18T02:27:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GdgadKEB1D9CM3lUIqz86kd36QHyKV7UND7keZDB/bBQze4mrPlpUwZj1vOzBMxuYG7JlNolMzuegifzAv0RCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:02:32.103082Z"},"content_sha256":"e8db925f1bd07e949d3dc117bac169e28ca5380e932a18f4f7eabec77b388e72","schema_version":"1.0","event_id":"sha256:e8db925f1bd07e949d3dc117bac169e28ca5380e932a18f4f7eabec77b388e72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/bundle.json","state_url":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/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":"2026-06-11T23:02:32Z","links":{"resolver":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG","bundle":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/bundle.json","state":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:KFDWPMWUZQNXPWWRX32I5W4FIG","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":"b63b5395d14b74549422b8f8ee1f38d3f7ede07ed02baad18f183d2695c9e86f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-02-08T17:32:44Z","title_canon_sha256":"d967e2f7d35065f73f3b4535a05564b808c34bb7c09395987814316924838845"},"schema_version":"1.0","source":{"id":"1502.02277","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.02277","created_at":"2026-05-18T02:27:43Z"},{"alias_kind":"arxiv_version","alias_value":"1502.02277v1","created_at":"2026-05-18T02:27:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.02277","created_at":"2026-05-18T02:27:43Z"},{"alias_kind":"pith_short_12","alias_value":"KFDWPMWUZQNX","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"KFDWPMWUZQNXPWWR","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"KFDWPMWU","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:e8db925f1bd07e949d3dc117bac169e28ca5380e932a18f4f7eabec77b388e72","target":"graph","created_at":"2026-05-18T02:27:43Z","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":"Term frequency normalization is a serious issue since lengths of documents are various. Generally, documents become long due to two different reasons - verbosity and multi-topicality. First, verbosity means that the same topic is repeatedly mentioned by terms related to the topic, so that term frequency is more increased than the well-summarized one. Second, multi-topicality indicates that a document has a broad discussion of multi-topics, rather than single topic. Although these document characteristics should be differently handled, all previous methods of term frequency normalization have i","authors_text":"In-Su Kang, Jong-Hyeok Lee, Seung-Hoon Na","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-02-08T17:32:44Z","title":"Improving Term Frequency Normalization for Multi-topical Documents, and Application to Language Modeling Approaches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.02277","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:bc3ae94213b2d8c4f6017969d3a8c4da5b8c1496d9cb2adde472c1228b08cc87","target":"record","created_at":"2026-05-18T02:27:43Z","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":"b63b5395d14b74549422b8f8ee1f38d3f7ede07ed02baad18f183d2695c9e86f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-02-08T17:32:44Z","title_canon_sha256":"d967e2f7d35065f73f3b4535a05564b808c34bb7c09395987814316924838845"},"schema_version":"1.0","source":{"id":"1502.02277","kind":"arxiv","version":1}},"canonical_sha256":"514767b2d4cc1b77dad1bef48edb85418aa77af9f4d4643cbab7b162a692fa98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"514767b2d4cc1b77dad1bef48edb85418aa77af9f4d4643cbab7b162a692fa98","first_computed_at":"2026-05-18T02:27:43.037736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:27:43.037736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qAM9kDISqqcvVzEd/OIuoB6VPbU+4NlXHRWEH7hIdKXX+K0muh7bzF2Z7CtpCIPo+xkaQPdN+Smx9bj65TpoCA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:27:43.038541Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.02277","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc3ae94213b2d8c4f6017969d3a8c4da5b8c1496d9cb2adde472c1228b08cc87","sha256:e8db925f1bd07e949d3dc117bac169e28ca5380e932a18f4f7eabec77b388e72"],"state_sha256":"d61dc9aefe4a7e38a804c53a8543825aec95fc2e02bb5c5a0ce3f2e1cc461761"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LzwxUxHtA53hHDJYy45GkRKjb6goNrvxCLFNGMAqbCt9S5TliXI+gapJ/Dkor6ndG+H5RaMoDK1LImc3weIaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T23:02:32.106844Z","bundle_sha256":"680ce9e8618e516e77b2ba1c9bfa0215dec357004649009d00efa944ed94af24"}}