{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:726JLOJLB7CZD4TZM5RCQILSIY","short_pith_number":"pith:726JLOJL","schema_version":"1.0","canonical_sha256":"febc95b92b0fc591f2796762282172463bf1eac340d03497e07560ca6cff5f49","source":{"kind":"arxiv","id":"2012.04203","version":1},"attestation_state":"computed","paper":{"title":"A Topological Method for Comparing Document Semantics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Benjamin Carterette, Fanchao Meng, Yuqi Kong","submitted_at":"2020-12-08T04:21:40Z","abstract_excerpt":"Comparing document semantics is one of the toughest tasks in both Natural Language Processing and Information Retrieval. To date, on one hand, the tools for this task are still rare. On the other hand, most relevant methods are devised from the statistic or the vector space model perspectives but nearly none from a topological perspective. In this paper, we hope to make a different sound. A novel algorithm based on topological persistence for comparing semantics similarity between two documents is proposed. Our experiments are conducted on a document dataset with human judges' results. A colle"},"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":"2012.04203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-08T04:21:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"a18024bc01b6a6c0cc6664c51ab9e6fa494c1548760c96f8f391342f48d176e8","abstract_canon_sha256":"8755b3bc88f8d13862952de4471238851796317b2ebe373c0b251fa02c586888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:01.843730Z","signature_b64":"KX+qDooX2UK1Tv7QW3IhC2hTaWRtdvpDJwJxZjIztVNPNxDZnaP5RMzkuUllZP0+oupjLjwSdru9MNfPjtbKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"febc95b92b0fc591f2796762282172463bf1eac340d03497e07560ca6cff5f49","last_reissued_at":"2026-07-05T01:58:01.843398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:01.843398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Topological Method for Comparing Document Semantics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Benjamin Carterette, Fanchao Meng, Yuqi Kong","submitted_at":"2020-12-08T04:21:40Z","abstract_excerpt":"Comparing document semantics is one of the toughest tasks in both Natural Language Processing and Information Retrieval. To date, on one hand, the tools for this task are still rare. On the other hand, most relevant methods are devised from the statistic or the vector space model perspectives but nearly none from a topological perspective. In this paper, we hope to make a different sound. A novel algorithm based on topological persistence for comparing semantics similarity between two documents is proposed. Our experiments are conducted on a document dataset with human judges' results. A colle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04203","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/2012.04203/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":"2012.04203","created_at":"2026-07-05T01:58:01.843453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.04203v1","created_at":"2026-07-05T01:58:01.843453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04203","created_at":"2026-07-05T01:58:01.843453+00:00"},{"alias_kind":"pith_short_12","alias_value":"726JLOJLB7CZ","created_at":"2026-07-05T01:58:01.843453+00:00"},{"alias_kind":"pith_short_16","alias_value":"726JLOJLB7CZD4TZ","created_at":"2026-07-05T01:58:01.843453+00:00"},{"alias_kind":"pith_short_8","alias_value":"726JLOJL","created_at":"2026-07-05T01:58:01.843453+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/726JLOJLB7CZD4TZM5RCQILSIY","json":"https://pith.science/pith/726JLOJLB7CZD4TZM5RCQILSIY.json","graph_json":"https://pith.science/api/pith-number/726JLOJLB7CZD4TZM5RCQILSIY/graph.json","events_json":"https://pith.science/api/pith-number/726JLOJLB7CZD4TZM5RCQILSIY/events.json","paper":"https://pith.science/paper/726JLOJL"},"agent_actions":{"view_html":"https://pith.science/pith/726JLOJLB7CZD4TZM5RCQILSIY","download_json":"https://pith.science/pith/726JLOJLB7CZD4TZM5RCQILSIY.json","view_paper":"https://pith.science/paper/726JLOJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.04203&json=true","fetch_graph":"https://pith.science/api/pith-number/726JLOJLB7CZD4TZM5RCQILSIY/graph.json","fetch_events":"https://pith.science/api/pith-number/726JLOJLB7CZD4TZM5RCQILSIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/726JLOJLB7CZD4TZM5RCQILSIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/726JLOJLB7CZD4TZM5RCQILSIY/action/storage_attestation","attest_author":"https://pith.science/pith/726JLOJLB7CZD4TZM5RCQILSIY/action/author_attestation","sign_citation":"https://pith.science/pith/726JLOJLB7CZD4TZM5RCQILSIY/action/citation_signature","submit_replication":"https://pith.science/pith/726JLOJLB7CZD4TZM5RCQILSIY/action/replication_record"}},"created_at":"2026-07-05T01:58:01.843453+00:00","updated_at":"2026-07-05T01:58:01.843453+00:00"}