{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GRMCDEZJWE5CX3SNFGPHWHVPUU","short_pith_number":"pith:GRMCDEZJ","schema_version":"1.0","canonical_sha256":"3458219329b13a2bee4d299e7b1eafa52aee5a52e904129dcd40c4a35593d9f6","source":{"kind":"arxiv","id":"2607.19845","version":1},"attestation_state":"computed","paper":{"title":"Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmad Pouramini, Mahsa Afsharizadeh","submitted_at":"2026-07-22T07:30:39Z","abstract_excerpt":"This paper introduces Sentence Splitter, a self-supervised framework built upon a T5-based encoder--decoder architecture for uncovering the latent factual structure of natural language sentences. The proposed method identifies the semantic boundary between a descriptive prefix (head) and its factual completion (tail) by formulating sentence splitting as a discrete segmentation problem, where a sentence of length $N$ admits $N$ possible split points but only one recovers the intended head--tail structure. Rather than explicitly searching over all candidate boundaries, the model learns to recove"},"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":"2607.19845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-22T07:30:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4fd049d141de7bcf8f981a7d76fde11cc410ce1f925370021f4486e1d43740df","abstract_canon_sha256":"95749d5bec44fe937da4a93a5b947845fb9ae2154ebe0b8948dba19f5f40d4e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:24:03.303259Z","signature_b64":"PLKqyjcb/iFeCrkGPoJEG6DzxfUM6uj4C27YWr+J2XQHh4XBQ59pxUIngIzJnUrXtv5rNo4hXfwr6uym2wGCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3458219329b13a2bee4d299e7b1eafa52aee5a52e904129dcd40c4a35593d9f6","last_reissued_at":"2026-07-23T01:24:03.302443Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:24:03.302443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmad Pouramini, Mahsa Afsharizadeh","submitted_at":"2026-07-22T07:30:39Z","abstract_excerpt":"This paper introduces Sentence Splitter, a self-supervised framework built upon a T5-based encoder--decoder architecture for uncovering the latent factual structure of natural language sentences. The proposed method identifies the semantic boundary between a descriptive prefix (head) and its factual completion (tail) by formulating sentence splitting as a discrete segmentation problem, where a sentence of length $N$ admits $N$ possible split points but only one recovers the intended head--tail structure. Rather than explicitly searching over all candidate boundaries, the model learns to recove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19845","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/2607.19845/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":"2607.19845","created_at":"2026-07-23T01:24:03.302868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19845v1","created_at":"2026-07-23T01:24:03.302868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19845","created_at":"2026-07-23T01:24:03.302868+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRMCDEZJWE5C","created_at":"2026-07-23T01:24:03.302868+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRMCDEZJWE5CX3SN","created_at":"2026-07-23T01:24:03.302868+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRMCDEZJ","created_at":"2026-07-23T01:24:03.302868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GRMCDEZJWE5CX3SNFGPHWHVPUU","json":"https://pith.science/pith/GRMCDEZJWE5CX3SNFGPHWHVPUU.json","graph_json":"https://pith.science/api/pith-number/GRMCDEZJWE5CX3SNFGPHWHVPUU/graph.json","events_json":"https://pith.science/api/pith-number/GRMCDEZJWE5CX3SNFGPHWHVPUU/events.json","paper":"https://pith.science/paper/GRMCDEZJ"},"agent_actions":{"view_html":"https://pith.science/pith/GRMCDEZJWE5CX3SNFGPHWHVPUU","download_json":"https://pith.science/pith/GRMCDEZJWE5CX3SNFGPHWHVPUU.json","view_paper":"https://pith.science/paper/GRMCDEZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19845&json=true","fetch_graph":"https://pith.science/api/pith-number/GRMCDEZJWE5CX3SNFGPHWHVPUU/graph.json","fetch_events":"https://pith.science/api/pith-number/GRMCDEZJWE5CX3SNFGPHWHVPUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRMCDEZJWE5CX3SNFGPHWHVPUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRMCDEZJWE5CX3SNFGPHWHVPUU/action/storage_attestation","attest_author":"https://pith.science/pith/GRMCDEZJWE5CX3SNFGPHWHVPUU/action/author_attestation","sign_citation":"https://pith.science/pith/GRMCDEZJWE5CX3SNFGPHWHVPUU/action/citation_signature","submit_replication":"https://pith.science/pith/GRMCDEZJWE5CX3SNFGPHWHVPUU/action/replication_record"}},"created_at":"2026-07-23T01:24:03.302868+00:00","updated_at":"2026-07-23T01:24:03.302868+00:00"}