{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6I5V4L4JY6PCNMESXAU37JQNHW","short_pith_number":"pith:6I5V4L4J","schema_version":"1.0","canonical_sha256":"f23b5e2f89c79e26b092b829bfa60d3d8f4429e3f5274e070c0302038b3ccc37","source":{"kind":"arxiv","id":"2110.07160","version":1},"attestation_state":"computed","paper":{"title":"Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kelvin Lo, Lan Du, Ming Liu, Weicong Tan, Wray Buntine, Yuan Jin","submitted_at":"2021-10-14T05:26:39Z","abstract_excerpt":"This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level transformer-based segmentation model based on the sentence embeddings. The bottom-level component transfers the pre-trained knowledge learned from large external corpora under both single and pair-wise supervised NLP tasks to model the sentence embeddings for the documents. Given the sentence embeddings, the upper-level transformer is trained to recover the segm"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.07160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T05:26:39Z","cross_cats_sorted":[],"title_canon_sha256":"476a376322326ce9e531ad8f3ce99840b19eba67d406ba16286d89b5dc46191d","abstract_canon_sha256":"0d72a8bb48353ae442e6387227110bcb17d0bde08b4a9eba492dcb76e32ff73f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:39.487063Z","signature_b64":"jVgMCtHBNnXSyrzkevYpz+mMQAygGgLPgBPikmDdDCEH3eurBMUTslpwhzg42MkV4Z5wjFxcu9J4jvXjIAaICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f23b5e2f89c79e26b092b829bfa60d3d8f4429e3f5274e070c0302038b3ccc37","last_reissued_at":"2026-07-05T03:22:39.486618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:39.486618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kelvin Lo, Lan Du, Ming Liu, Weicong Tan, Wray Buntine, Yuan Jin","submitted_at":"2021-10-14T05:26:39Z","abstract_excerpt":"This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level transformer-based segmentation model based on the sentence embeddings. The bottom-level component transfers the pre-trained knowledge learned from large external corpora under both single and pair-wise supervised NLP tasks to model the sentence embeddings for the documents. Given the sentence embeddings, the upper-level transformer is trained to recover the segm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07160","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/2110.07160/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.07160","created_at":"2026-07-05T03:22:39.486670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07160v1","created_at":"2026-07-05T03:22:39.486670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07160","created_at":"2026-07-05T03:22:39.486670+00:00"},{"alias_kind":"pith_short_12","alias_value":"6I5V4L4JY6PC","created_at":"2026-07-05T03:22:39.486670+00:00"},{"alias_kind":"pith_short_16","alias_value":"6I5V4L4JY6PCNMES","created_at":"2026-07-05T03:22:39.486670+00:00"},{"alias_kind":"pith_short_8","alias_value":"6I5V4L4J","created_at":"2026-07-05T03:22:39.486670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.23728","citing_title":"GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6I5V4L4JY6PCNMESXAU37JQNHW","json":"https://pith.science/pith/6I5V4L4JY6PCNMESXAU37JQNHW.json","graph_json":"https://pith.science/api/pith-number/6I5V4L4JY6PCNMESXAU37JQNHW/graph.json","events_json":"https://pith.science/api/pith-number/6I5V4L4JY6PCNMESXAU37JQNHW/events.json","paper":"https://pith.science/paper/6I5V4L4J"},"agent_actions":{"view_html":"https://pith.science/pith/6I5V4L4JY6PCNMESXAU37JQNHW","download_json":"https://pith.science/pith/6I5V4L4JY6PCNMESXAU37JQNHW.json","view_paper":"https://pith.science/paper/6I5V4L4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07160&json=true","fetch_graph":"https://pith.science/api/pith-number/6I5V4L4JY6PCNMESXAU37JQNHW/graph.json","fetch_events":"https://pith.science/api/pith-number/6I5V4L4JY6PCNMESXAU37JQNHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6I5V4L4JY6PCNMESXAU37JQNHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6I5V4L4JY6PCNMESXAU37JQNHW/action/storage_attestation","attest_author":"https://pith.science/pith/6I5V4L4JY6PCNMESXAU37JQNHW/action/author_attestation","sign_citation":"https://pith.science/pith/6I5V4L4JY6PCNMESXAU37JQNHW/action/citation_signature","submit_replication":"https://pith.science/pith/6I5V4L4JY6PCNMESXAU37JQNHW/action/replication_record"}},"created_at":"2026-07-05T03:22:39.486670+00:00","updated_at":"2026-07-05T03:22:39.486670+00:00"}