{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:IV5ZMSJ6PVTYWMH6T5YW47B2OI","short_pith_number":"pith:IV5ZMSJ6","schema_version":"1.0","canonical_sha256":"457b96493e7d678b30fe9f716e7c3a72081293a3c01b3ab99a8b6fa88bb233c4","source":{"kind":"arxiv","id":"1611.04822","version":2},"attestation_state":"computed","paper":{"title":"SimDoc: Topic Sequence Alignment based Document Similarity Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gaurav Maheshwari, Harshita Sahijwani, Jens Lehmann, Kunal Jha, Priyansh Trivedi, Sourish Dasgupta","submitted_at":"2016-11-15T13:31:28Z","abstract_excerpt":"Document similarity is the problem of estimating the degree to which a given pair of documents has similar semantic content. An accurate document similarity measure can improve several enterprise relevant tasks such as document clustering, text mining, and question-answering. In this paper, we show that a document's thematic flow, which is often disregarded by bag-of-word techniques, is pivotal in estimating their similarity. To this end, we propose a novel semantic document similarity framework, called SimDoc. We model documents as topic-sequences, where topics represent latent generative clu"},"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":"1611.04822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-15T13:31:28Z","cross_cats_sorted":[],"title_canon_sha256":"374845c4c06a286cc54e246047cb5ba30cad16732723e2d9a7118486f52419e0","abstract_canon_sha256":"b636bb8004286a9cc40746371969c47345798cc8d04151a31209882e6cdef9ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:46.604303Z","signature_b64":"8Q3pNFNScrebt6nIs+UiDvS7sJv7EA8533oXXJ5cdreGuNOIhX9X9aLf8R+g3loyNDSSlw2+elitgLk7j5uMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457b96493e7d678b30fe9f716e7c3a72081293a3c01b3ab99a8b6fa88bb233c4","last_reissued_at":"2026-05-18T00:30:46.603737Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:46.603737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimDoc: Topic Sequence Alignment based Document Similarity Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gaurav Maheshwari, Harshita Sahijwani, Jens Lehmann, Kunal Jha, Priyansh Trivedi, Sourish Dasgupta","submitted_at":"2016-11-15T13:31:28Z","abstract_excerpt":"Document similarity is the problem of estimating the degree to which a given pair of documents has similar semantic content. An accurate document similarity measure can improve several enterprise relevant tasks such as document clustering, text mining, and question-answering. In this paper, we show that a document's thematic flow, which is often disregarded by bag-of-word techniques, is pivotal in estimating their similarity. To this end, we propose a novel semantic document similarity framework, called SimDoc. We model documents as topic-sequences, where topics represent latent generative clu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04822","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1611.04822","created_at":"2026-05-18T00:30:46.603818+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.04822v2","created_at":"2026-05-18T00:30:46.603818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04822","created_at":"2026-05-18T00:30:46.603818+00:00"},{"alias_kind":"pith_short_12","alias_value":"IV5ZMSJ6PVTY","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"IV5ZMSJ6PVTYWMH6","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"IV5ZMSJ6","created_at":"2026-05-18T12:30:22.444734+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/IV5ZMSJ6PVTYWMH6T5YW47B2OI","json":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI.json","graph_json":"https://pith.science/api/pith-number/IV5ZMSJ6PVTYWMH6T5YW47B2OI/graph.json","events_json":"https://pith.science/api/pith-number/IV5ZMSJ6PVTYWMH6T5YW47B2OI/events.json","paper":"https://pith.science/paper/IV5ZMSJ6"},"agent_actions":{"view_html":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI","download_json":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI.json","view_paper":"https://pith.science/paper/IV5ZMSJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.04822&json=true","fetch_graph":"https://pith.science/api/pith-number/IV5ZMSJ6PVTYWMH6T5YW47B2OI/graph.json","fetch_events":"https://pith.science/api/pith-number/IV5ZMSJ6PVTYWMH6T5YW47B2OI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/action/storage_attestation","attest_author":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/action/author_attestation","sign_citation":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/action/citation_signature","submit_replication":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/action/replication_record"}},"created_at":"2026-05-18T00:30:46.603818+00:00","updated_at":"2026-05-18T00:30:46.603818+00:00"}