{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:S6GNXMSAAPYIE3DB4WSDF7QXD5","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":"7badecca2ef816b473b71f701db2d59df44dad8cf373993e032be3e5909ab339","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-05-17T07:58:58Z","title_canon_sha256":"5df07f3a7a4c06d4c5cdfcf28c0465f5d4e8540893f4d02eba6e075d283f7197"},"schema_version":"1.0","source":{"id":"1405.4364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.4364","created_at":"2026-05-18T02:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"1405.4364v1","created_at":"2026-05-18T02:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.4364","created_at":"2026-05-18T02:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"S6GNXMSAAPYI","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"S6GNXMSAAPYIE3DB","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"S6GNXMSA","created_at":"2026-05-18T12:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:481515da3fe8334f44b4170e06cddb5d1d169c5f97a00aeac5620117ae9963a7","target":"graph","created_at":"2026-05-18T02:51:41Z","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 an extended, thematically reinforced version of Gabrilovich and Markovitch's Explicit Semantic Analysis (ESA), where we obtain thematic information through the category structure of Wikipedia. For this we first define a notion of categorical tfidf which measures the relevance of terms in categories. Using this measure as a weight we calculate a maximal spanning tree of the Wikipedia corpus considered as a directed graph of pages and categories. This tree provides us with a unique path of \"most related categories\" between each page and the top of the hierarchy. We reinforce tfidf of ","authors_text":"Vitaly Klyuev, Yannis Haralambous","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-05-17T07:58:58Z","title":"Thematically Reinforced Explicit Semantic Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.4364","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":"sha256:1a29a69179bda586ab8cb48040ee0e6a371772fbdd5f53a7c2eb743cea0b4b69","target":"record","created_at":"2026-05-18T02:51:41Z","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":"7badecca2ef816b473b71f701db2d59df44dad8cf373993e032be3e5909ab339","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-05-17T07:58:58Z","title_canon_sha256":"5df07f3a7a4c06d4c5cdfcf28c0465f5d4e8540893f4d02eba6e075d283f7197"},"schema_version":"1.0","source":{"id":"1405.4364","kind":"arxiv","version":1}},"canonical_sha256":"978cdbb24003f0826c61e5a432fe171f570186da535fa7f3b560b19c1719a79a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"978cdbb24003f0826c61e5a432fe171f570186da535fa7f3b560b19c1719a79a","first_computed_at":"2026-05-18T02:51:41.082516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:51:41.082516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aBxtDlBVFC/1dl0RHwYWVZ/lH30Ubp6hq708KTwJZqud0hkeVI6h3YT99GlV53fNsPemq2UyPCggJMSunt31Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:51:41.083020Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.4364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a29a69179bda586ab8cb48040ee0e6a371772fbdd5f53a7c2eb743cea0b4b69","sha256:481515da3fe8334f44b4170e06cddb5d1d169c5f97a00aeac5620117ae9963a7"],"state_sha256":"76536de3a36d55e0bb3b3935462708c0250fe97baa75da40bc4904cdd3673e47"}