{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WDZAMREHZESGQ5HAPNE3XGBGSF","short_pith_number":"pith:WDZAMREH","canonical_record":{"source":{"id":"1904.06730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T17:32:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc9d485be0ebeaa12901b9965292f6450aae21582e6eac0e41406781f4db065a","abstract_canon_sha256":"c63cf060202c4878c940320005a09f727f736797ead739801b9edafb78dfd84b"},"schema_version":"1.0"},"canonical_sha256":"b0f2064487c9246874e07b49bb98269166c7cd38f737a6ae5d2d76b392624ff9","source":{"kind":"arxiv","id":"1904.06730","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06730","created_at":"2026-05-17T23:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06730v1","created_at":"2026-05-17T23:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06730","created_at":"2026-05-17T23:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"WDZAMREHZESG","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WDZAMREHZESGQ5HA","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WDZAMREH","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WDZAMREHZESGQ5HAPNE3XGBGSF","target":"record","payload":{"canonical_record":{"source":{"id":"1904.06730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T17:32:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc9d485be0ebeaa12901b9965292f6450aae21582e6eac0e41406781f4db065a","abstract_canon_sha256":"c63cf060202c4878c940320005a09f727f736797ead739801b9edafb78dfd84b"},"schema_version":"1.0"},"canonical_sha256":"b0f2064487c9246874e07b49bb98269166c7cd38f737a6ae5d2d76b392624ff9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:36.380925Z","signature_b64":"ivc417zN9iPEKSi7wDIfTwAaiWagnGw3UgaaUwOrBX/dsJKkLabqQlqxvaDWeQ4Y/csKBJ6/AwxD79wemm8QBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0f2064487c9246874e07b49bb98269166c7cd38f737a6ae5d2d76b392624ff9","last_reissued_at":"2026-05-17T23:48:36.380236Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:36.380236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.06730","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":"2026-05-17T23:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oynY5F0+0RNEZB3njRNEVqJffPCAPoGn2p7NMU4EoOcqJdFpiYJUa2i//didcPF8nAMFMHkB0wnxtdweiBX0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:31:47.895336Z"},"content_sha256":"41ef92ee0110070e9a08dbd99d9276dbf333129f9e80830968b5b0a5980d8224","schema_version":"1.0","event_id":"sha256:41ef92ee0110070e9a08dbd99d9276dbf333129f9e80830968b5b0a5980d8224"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WDZAMREHZESGQ5HAPNE3XGBGSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text segmentation on multilabel documents: A distant-supervised approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"George Karypis, Saurav Manchanda","submitted_at":"2019-04-14T17:32:44Z","abstract_excerpt":"Segmenting text into semantically coherent segments is an important task with applications in information retrieval and text summarization. Developing accurate topical segmentation requires the availability of training data with ground truth information at the segment level. However, generating such labeled datasets, especially for applications in which the meaning of the labels is user-defined, is expensive and time-consuming. In this paper, we develop an approach that instead of using segment-level ground truth information, it instead uses the set of labels that are associated with a documen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06730","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":"2026-05-17T23:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rxtwvo62sDUJdZSCS6EX0XfogLpdn7AQZ8HEXDjRCaEht1vXo1sL7ROVyyRqfCDrvnb5R+zNe72mlT8oninaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:31:47.895691Z"},"content_sha256":"a695b742742332e98368b111ba1af24c2e76807a6f47fc7c58981d8031a4d095","schema_version":"1.0","event_id":"sha256:a695b742742332e98368b111ba1af24c2e76807a6f47fc7c58981d8031a4d095"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WDZAMREHZESGQ5HAPNE3XGBGSF/bundle.json","state_url":"https://pith.science/pith/WDZAMREHZESGQ5HAPNE3XGBGSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WDZAMREHZESGQ5HAPNE3XGBGSF/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":"2026-07-06T23:31:47Z","links":{"resolver":"https://pith.science/pith/WDZAMREHZESGQ5HAPNE3XGBGSF","bundle":"https://pith.science/pith/WDZAMREHZESGQ5HAPNE3XGBGSF/bundle.json","state":"https://pith.science/pith/WDZAMREHZESGQ5HAPNE3XGBGSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WDZAMREHZESGQ5HAPNE3XGBGSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WDZAMREHZESGQ5HAPNE3XGBGSF","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":"c63cf060202c4878c940320005a09f727f736797ead739801b9edafb78dfd84b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T17:32:44Z","title_canon_sha256":"bc9d485be0ebeaa12901b9965292f6450aae21582e6eac0e41406781f4db065a"},"schema_version":"1.0","source":{"id":"1904.06730","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06730","created_at":"2026-05-17T23:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06730v1","created_at":"2026-05-17T23:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06730","created_at":"2026-05-17T23:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"WDZAMREHZESG","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WDZAMREHZESGQ5HA","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WDZAMREH","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:a695b742742332e98368b111ba1af24c2e76807a6f47fc7c58981d8031a4d095","target":"graph","created_at":"2026-05-17T23:48:36Z","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":"Segmenting text into semantically coherent segments is an important task with applications in information retrieval and text summarization. Developing accurate topical segmentation requires the availability of training data with ground truth information at the segment level. However, generating such labeled datasets, especially for applications in which the meaning of the labels is user-defined, is expensive and time-consuming. In this paper, we develop an approach that instead of using segment-level ground truth information, it instead uses the set of labels that are associated with a documen","authors_text":"George Karypis, Saurav Manchanda","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T17:32:44Z","title":"Text segmentation on multilabel documents: A distant-supervised approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06730","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":"sha256:41ef92ee0110070e9a08dbd99d9276dbf333129f9e80830968b5b0a5980d8224","target":"record","created_at":"2026-05-17T23:48:36Z","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":"c63cf060202c4878c940320005a09f727f736797ead739801b9edafb78dfd84b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T17:32:44Z","title_canon_sha256":"bc9d485be0ebeaa12901b9965292f6450aae21582e6eac0e41406781f4db065a"},"schema_version":"1.0","source":{"id":"1904.06730","kind":"arxiv","version":1}},"canonical_sha256":"b0f2064487c9246874e07b49bb98269166c7cd38f737a6ae5d2d76b392624ff9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0f2064487c9246874e07b49bb98269166c7cd38f737a6ae5d2d76b392624ff9","first_computed_at":"2026-05-17T23:48:36.380236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:36.380236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ivc417zN9iPEKSi7wDIfTwAaiWagnGw3UgaaUwOrBX/dsJKkLabqQlqxvaDWeQ4Y/csKBJ6/AwxD79wemm8QBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:36.380925Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.06730","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41ef92ee0110070e9a08dbd99d9276dbf333129f9e80830968b5b0a5980d8224","sha256:a695b742742332e98368b111ba1af24c2e76807a6f47fc7c58981d8031a4d095"],"state_sha256":"3501a21f0e3d5c7f496bab0789a8be298a23aa778aabb47e4bb6587c04bbec77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UzMQlBp1s0TrCArOAj4cWsh89D5GF8LCWYEVkmt+wX183qzOIsW+k9jjn+B0/mzibCF4AzzlXAxLapaMg+oHAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:31:47.897719Z","bundle_sha256":"1f7acd74b6955668d1dc57b6b19b0384088200f0421921b7e52f28f1b6889c10"}}