{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2010:JIOOFB5WTGX6OXNSHJOUKFN77A","short_pith_number":"pith:JIOOFB5W","canonical_record":{"source":{"id":"1006.1029","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2010-06-05T08:14:27Z","cross_cats_sorted":["stat.AP","stat.ML"],"title_canon_sha256":"30cb876885ff9e67d675b8b73d21049a049d6a48e0475ad287bb49ecbac91347","abstract_canon_sha256":"b5c53a16a38f02deb022c3d645293531a4e8cba10cab3daf7ee5b6ec03a65076"},"schema_version":"1.0"},"canonical_sha256":"4a1ce287b699afe75db23a5d4515bff821f3d929cbc309d05e5cc18da8bf07bb","source":{"kind":"arxiv","id":"1006.1029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1006.1029","created_at":"2026-05-18T00:19:43Z"},{"alias_kind":"arxiv_version","alias_value":"1006.1029v1","created_at":"2026-05-18T00:19:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1006.1029","created_at":"2026-05-18T00:19:43Z"},{"alias_kind":"pith_short_12","alias_value":"JIOOFB5WTGX6","created_at":"2026-05-18T12:26:09Z"},{"alias_kind":"pith_short_16","alias_value":"JIOOFB5WTGX6OXNS","created_at":"2026-05-18T12:26:09Z"},{"alias_kind":"pith_short_8","alias_value":"JIOOFB5W","created_at":"2026-05-18T12:26:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2010:JIOOFB5WTGX6OXNSHJOUKFN77A","target":"record","payload":{"canonical_record":{"source":{"id":"1006.1029","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2010-06-05T08:14:27Z","cross_cats_sorted":["stat.AP","stat.ML"],"title_canon_sha256":"30cb876885ff9e67d675b8b73d21049a049d6a48e0475ad287bb49ecbac91347","abstract_canon_sha256":"b5c53a16a38f02deb022c3d645293531a4e8cba10cab3daf7ee5b6ec03a65076"},"schema_version":"1.0"},"canonical_sha256":"4a1ce287b699afe75db23a5d4515bff821f3d929cbc309d05e5cc18da8bf07bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:43.202940Z","signature_b64":"1Iy1kKCYiYJM0dskc49kdFogdo+znMFKIphvuOAoCv8idyr4/ukyTe1MXvc02zFlSWMTDsXj0VLLoUAKG5c9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a1ce287b699afe75db23a5d4515bff821f3d929cbc309d05e5cc18da8bf07bb","last_reissued_at":"2026-05-18T00:19:43.202217Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:43.202217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1006.1029","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":"2026-05-18T00:19:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lI92rFXOsW9bKDGnP2sYADbakCDADNnqT/6quW7oEez8K8Gs1cgBc2/1tRhZsKksgqtlUeZ9BAynzmrE+BqbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:51:22.945481Z"},"content_sha256":"dc6c319a1c5771d6ad09fcd91099dfeb90deee04d6f8c948adffd8a8269c223e","schema_version":"1.0","event_id":"sha256:dc6c319a1c5771d6ad09fcd91099dfeb90deee04d6f8c948adffd8a8269c223e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2010:JIOOFB5WTGX6OXNSHJOUKFN77A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chi-square-based scoring function for categorization of MEDLINE citations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.IR","authors_text":"Andrej Kastrin, Borut Peterlin, Dimitar Hristovski","submitted_at":"2010-06-05T08:14:27Z","abstract_excerpt":"Objectives: Text categorization has been used in biomedical informatics for identifying documents containing relevant topics of interest. We developed a simple method that uses a chi-square-based scoring function to determine the likelihood of MEDLINE citations containing genetic relevant topic. Methods: Our procedure requires construction of a genetic and a nongenetic domain document corpus. We used MeSH descriptors assigned to MEDLINE citations for this categorization task. We compared frequencies of MeSH descriptors between two corpora applying chi-square test. A MeSH descriptor was conside"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1006.1029","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":"2026-05-18T00:19:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"guN4/QISs3ikzm8yi+xdRSydn3Z7UlCEiV68om7DEn3KB5mw3TpPY5FqjFkG4zxAkAC56ADuEeoZs52qsXAeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:51:22.946126Z"},"content_sha256":"74f0f83c1e89d1d7c44cf6319f995eb634ffe76d80915a4d4019ae5cf0ed2006","schema_version":"1.0","event_id":"sha256:74f0f83c1e89d1d7c44cf6319f995eb634ffe76d80915a4d4019ae5cf0ed2006"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JIOOFB5WTGX6OXNSHJOUKFN77A/bundle.json","state_url":"https://pith.science/pith/JIOOFB5WTGX6OXNSHJOUKFN77A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JIOOFB5WTGX6OXNSHJOUKFN77A/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":"2026-05-31T06:51:22Z","links":{"resolver":"https://pith.science/pith/JIOOFB5WTGX6OXNSHJOUKFN77A","bundle":"https://pith.science/pith/JIOOFB5WTGX6OXNSHJOUKFN77A/bundle.json","state":"https://pith.science/pith/JIOOFB5WTGX6OXNSHJOUKFN77A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JIOOFB5WTGX6OXNSHJOUKFN77A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:JIOOFB5WTGX6OXNSHJOUKFN77A","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":"b5c53a16a38f02deb022c3d645293531a4e8cba10cab3daf7ee5b6ec03a65076","cross_cats_sorted":["stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2010-06-05T08:14:27Z","title_canon_sha256":"30cb876885ff9e67d675b8b73d21049a049d6a48e0475ad287bb49ecbac91347"},"schema_version":"1.0","source":{"id":"1006.1029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1006.1029","created_at":"2026-05-18T00:19:43Z"},{"alias_kind":"arxiv_version","alias_value":"1006.1029v1","created_at":"2026-05-18T00:19:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1006.1029","created_at":"2026-05-18T00:19:43Z"},{"alias_kind":"pith_short_12","alias_value":"JIOOFB5WTGX6","created_at":"2026-05-18T12:26:09Z"},{"alias_kind":"pith_short_16","alias_value":"JIOOFB5WTGX6OXNS","created_at":"2026-05-18T12:26:09Z"},{"alias_kind":"pith_short_8","alias_value":"JIOOFB5W","created_at":"2026-05-18T12:26:09Z"}],"graph_snapshots":[{"event_id":"sha256:74f0f83c1e89d1d7c44cf6319f995eb634ffe76d80915a4d4019ae5cf0ed2006","target":"graph","created_at":"2026-05-18T00:19:43Z","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":"Objectives: Text categorization has been used in biomedical informatics for identifying documents containing relevant topics of interest. We developed a simple method that uses a chi-square-based scoring function to determine the likelihood of MEDLINE citations containing genetic relevant topic. Methods: Our procedure requires construction of a genetic and a nongenetic domain document corpus. We used MeSH descriptors assigned to MEDLINE citations for this categorization task. We compared frequencies of MeSH descriptors between two corpora applying chi-square test. A MeSH descriptor was conside","authors_text":"Andrej Kastrin, Borut Peterlin, Dimitar Hristovski","cross_cats":["stat.AP","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2010-06-05T08:14:27Z","title":"Chi-square-based scoring function for categorization of MEDLINE citations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1006.1029","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:dc6c319a1c5771d6ad09fcd91099dfeb90deee04d6f8c948adffd8a8269c223e","target":"record","created_at":"2026-05-18T00:19:43Z","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":"b5c53a16a38f02deb022c3d645293531a4e8cba10cab3daf7ee5b6ec03a65076","cross_cats_sorted":["stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2010-06-05T08:14:27Z","title_canon_sha256":"30cb876885ff9e67d675b8b73d21049a049d6a48e0475ad287bb49ecbac91347"},"schema_version":"1.0","source":{"id":"1006.1029","kind":"arxiv","version":1}},"canonical_sha256":"4a1ce287b699afe75db23a5d4515bff821f3d929cbc309d05e5cc18da8bf07bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a1ce287b699afe75db23a5d4515bff821f3d929cbc309d05e5cc18da8bf07bb","first_computed_at":"2026-05-18T00:19:43.202217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:43.202217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Iy1kKCYiYJM0dskc49kdFogdo+znMFKIphvuOAoCv8idyr4/ukyTe1MXvc02zFlSWMTDsXj0VLLoUAKG5c9BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:43.202940Z","signed_message":"canonical_sha256_bytes"},"source_id":"1006.1029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc6c319a1c5771d6ad09fcd91099dfeb90deee04d6f8c948adffd8a8269c223e","sha256:74f0f83c1e89d1d7c44cf6319f995eb634ffe76d80915a4d4019ae5cf0ed2006"],"state_sha256":"fe0fcf62fb79dd1f7c5c6e3d0efdec263ac0ffff819159e0d32713b7b165fc6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2f3bEz0uVEPfb5C/akqqUZBx6dYCoYDMUXgh/NurHYZ9u8Q3lfDolqVNy3zi6bT3tWY6G9vHpY/67BAfRYdBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:51:22.950254Z","bundle_sha256":"bf88774d593c29e8a5964c898ea8e2c706d455ad25b1c9880cd5bbe4369aaaec"}}