{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:Q7OJDS56SWZZUD532AS4STV6SF","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":"475c74c82b1fa41653ddcac8da805a00b366cf44391c182171a9fdb30852f335","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-07-29T17:40:19Z","title_canon_sha256":"6954e3f32989581d60c317d207a1c461e71dc29974588cb43e702a480a7aaa7a"},"schema_version":"1.0","source":{"id":"1507.08234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.08234","created_at":"2026-05-18T01:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"1507.08234v1","created_at":"2026-05-18T01:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08234","created_at":"2026-05-18T01:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"Q7OJDS56SWZZ","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q7OJDS56SWZZUD53","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q7OJDS56","created_at":"2026-05-18T12:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:e772467c4b07d3c88b65d840a6489b8fd24e11a93010216a3798ae8b79d1ae68","target":"graph","created_at":"2026-05-18T01:01:01Z","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":"We present two novel models of document coherence and their application to information retrieval (IR). Both models approximate document coherence using discourse entities, e.g. the subject or object of a sentence. Our first model views text as a Markov process generating sequences of discourse entities (entity n-grams); we use the entropy of these entity n-grams to approximate the rate at which new information appears in text, reasoning that as more new words appear, the topic increasingly drifts and text coherence decreases. Our second model extends the work of Guinaudeau & Strube [28] that r","authors_text":"Birger Larsen, Casper Petersen, Christina Lioma, Jakob Grue Simonsen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-07-29T17:40:19Z","title":"Entropy and Graph Based Modelling of Document Coherence using Discourse Entities: An Application"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08234","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:f99f524f70ae6f09220f21b81adbb7b15b425bb8a508f85b9f5bef65d0abe7fb","target":"record","created_at":"2026-05-18T01:01:01Z","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":"475c74c82b1fa41653ddcac8da805a00b366cf44391c182171a9fdb30852f335","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-07-29T17:40:19Z","title_canon_sha256":"6954e3f32989581d60c317d207a1c461e71dc29974588cb43e702a480a7aaa7a"},"schema_version":"1.0","source":{"id":"1507.08234","kind":"arxiv","version":1}},"canonical_sha256":"87dc91cbbe95b39a0fbbd025c94ebe916ef5a216bb99557cdb46fd8af70bf7e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87dc91cbbe95b39a0fbbd025c94ebe916ef5a216bb99557cdb46fd8af70bf7e5","first_computed_at":"2026-05-18T01:01:01.297490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:01:01.297490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1uLHMUNWhLhtIUxhXxa1LF9wAMS5cpZa2KDHxQ6YXY5mzp1x9VHMIC0WoUpzy1xkXuCuGm/46drRBbl2q9NNAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:01:01.298180Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.08234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f99f524f70ae6f09220f21b81adbb7b15b425bb8a508f85b9f5bef65d0abe7fb","sha256:e772467c4b07d3c88b65d840a6489b8fd24e11a93010216a3798ae8b79d1ae68"],"state_sha256":"fb94275f4e0c771be4e3b0d143f9006fb6604d5421fc3bc7c38a7c60cf0ccbbf"}