{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3ZCMYJ2HBMFWH7ZW4X6K6BHGBT","short_pith_number":"pith:3ZCMYJ2H","canonical_record":{"source":{"id":"1811.01183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-03T09:29:36Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"cf09ad5a542384f79a938f17dd4ee05ded337b34b0a567bd5e9f6b33bba87daa","abstract_canon_sha256":"1c99a53406d9366608d34dd3a1119d4fda4cd5ed920910dbfa18113fda78c45a"},"schema_version":"1.0"},"canonical_sha256":"de44cc27470b0b63ff36e5fcaf04e60cc4fc6ce456038d8715ba58d8cd8ea359","source":{"kind":"arxiv","id":"1811.01183","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01183","created_at":"2026-05-18T00:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01183v1","created_at":"2026-05-18T00:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01183","created_at":"2026-05-18T00:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"3ZCMYJ2HBMFW","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"3ZCMYJ2HBMFWH7ZW","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"3ZCMYJ2H","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3ZCMYJ2HBMFWH7ZW4X6K6BHGBT","target":"record","payload":{"canonical_record":{"source":{"id":"1811.01183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-03T09:29:36Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"cf09ad5a542384f79a938f17dd4ee05ded337b34b0a567bd5e9f6b33bba87daa","abstract_canon_sha256":"1c99a53406d9366608d34dd3a1119d4fda4cd5ed920910dbfa18113fda78c45a"},"schema_version":"1.0"},"canonical_sha256":"de44cc27470b0b63ff36e5fcaf04e60cc4fc6ce456038d8715ba58d8cd8ea359","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:35.112604Z","signature_b64":"NdwU51M4OObfUPAfOYvxUByyyzKeyAt+I/Y/n1t/3I4ixlRNNwMagGHX+ibbHETexeSA6g3pyJrTkrEegYB/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de44cc27470b0b63ff36e5fcaf04e60cc4fc6ce456038d8715ba58d8cd8ea359","last_reissued_at":"2026-05-18T00:01:35.112085Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:35.112085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.01183","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":"2026-05-18T00:01:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1LwN57PzdgYcsQNPlatyq7qq7l20PDKk3FbWefpID4huGgNPgUjdZDH0IQulSFaBGYPZ1Hx/ChQ6ViWB72vbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:56:07.502307Z"},"content_sha256":"730c21f8ccd1e8f42d3539af5dee247abd70780717caeb58eb4d23742db08031","schema_version":"1.0","event_id":"sha256:730c21f8ccd1e8f42d3539af5dee247abd70780717caeb58eb4d23742db08031"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3ZCMYJ2HBMFWH7ZW4X6K6BHGBT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"Christopher G. Stahl, Drahomira Herrmannova, Mary S. Wolfe, Nicole C. Kleinstreuer, Robert M. Patton, Steven R. Young","submitted_at":"2018-11-03T09:29:36Z","abstract_excerpt":"Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks. In this paper we address the question of identifying data elements in an unsupervised manner. Specifically, provided a set of criteria describing specific study parameters, such as species, route of administration, and dosing regimen, we develop an unsupervised approach to identify text segments (sentences) relevant to the criteria. A binary classifier trained to identify publications that met the criteria performs better "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01183","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":"2026-05-18T00:01:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JO42SwsX6E4LZiucXG+ElpVUrn5qDWjmMOu+NAWPSC2hAJsLWI/3XvJtG9COynvB6P4w6ELVLUvju773gwMMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:56:07.503043Z"},"content_sha256":"e06cc3894cf82664082ed27d45adfbc8cb61739dc33eb27c81d6617c9877a29c","schema_version":"1.0","event_id":"sha256:e06cc3894cf82664082ed27d45adfbc8cb61739dc33eb27c81d6617c9877a29c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/bundle.json","state_url":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/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":"2026-05-27T11:56:07Z","links":{"resolver":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT","bundle":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/bundle.json","state":"https://pith.science/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ZCMYJ2HBMFWH7ZW4X6K6BHGBT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3ZCMYJ2HBMFWH7ZW4X6K6BHGBT","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":"1c99a53406d9366608d34dd3a1119d4fda4cd5ed920910dbfa18113fda78c45a","cross_cats_sorted":["cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-03T09:29:36Z","title_canon_sha256":"cf09ad5a542384f79a938f17dd4ee05ded337b34b0a567bd5e9f6b33bba87daa"},"schema_version":"1.0","source":{"id":"1811.01183","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01183","created_at":"2026-05-18T00:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01183v1","created_at":"2026-05-18T00:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01183","created_at":"2026-05-18T00:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"3ZCMYJ2HBMFW","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"3ZCMYJ2HBMFWH7ZW","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"3ZCMYJ2H","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:e06cc3894cf82664082ed27d45adfbc8cb61739dc33eb27c81d6617c9877a29c","target":"graph","created_at":"2026-05-18T00:01:35Z","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":"Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks. In this paper we address the question of identifying data elements in an unsupervised manner. Specifically, provided a set of criteria describing specific study parameters, such as species, route of administration, and dosing regimen, we develop an unsupervised approach to identify text segments (sentences) relevant to the criteria. A binary classifier trained to identify publications that met the criteria performs better ","authors_text":"Christopher G. Stahl, Drahomira Herrmannova, Mary S. Wolfe, Nicole C. Kleinstreuer, Robert M. Patton, Steven R. Young","cross_cats":["cs.DL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-03T09:29:36Z","title":"Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01183","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":"sha256:730c21f8ccd1e8f42d3539af5dee247abd70780717caeb58eb4d23742db08031","target":"record","created_at":"2026-05-18T00:01:35Z","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":"1c99a53406d9366608d34dd3a1119d4fda4cd5ed920910dbfa18113fda78c45a","cross_cats_sorted":["cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-03T09:29:36Z","title_canon_sha256":"cf09ad5a542384f79a938f17dd4ee05ded337b34b0a567bd5e9f6b33bba87daa"},"schema_version":"1.0","source":{"id":"1811.01183","kind":"arxiv","version":1}},"canonical_sha256":"de44cc27470b0b63ff36e5fcaf04e60cc4fc6ce456038d8715ba58d8cd8ea359","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de44cc27470b0b63ff36e5fcaf04e60cc4fc6ce456038d8715ba58d8cd8ea359","first_computed_at":"2026-05-18T00:01:35.112085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:35.112085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NdwU51M4OObfUPAfOYvxUByyyzKeyAt+I/Y/n1t/3I4ixlRNNwMagGHX+ibbHETexeSA6g3pyJrTkrEegYB/CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:35.112604Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.01183","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:730c21f8ccd1e8f42d3539af5dee247abd70780717caeb58eb4d23742db08031","sha256:e06cc3894cf82664082ed27d45adfbc8cb61739dc33eb27c81d6617c9877a29c"],"state_sha256":"48412168b1acb12825150dd74559773f696cf29f5f80ccdd34d613b6819e929b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z7EaW7Vi3vb1heKi5utIb36/inmdamz1QqEBMdq3no1iChacAQZAvRr/7GW+GF2F6rmjQLlFDvZj7332ZxLUBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T11:56:07.507018Z","bundle_sha256":"fb8c59d9a82cb2ab87dda3b21338cd3175d09ba065a671fc1871efcda35bfcba"}}