{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QS7VYBWPTSM3CBJ7ALCQ5MNKNF","short_pith_number":"pith:QS7VYBWP","schema_version":"1.0","canonical_sha256":"84bf5c06cf9c99b1053f02c50eb1aa69598990d0879e7f3c0386715c406ca0ad","source":{"kind":"arxiv","id":"1608.00466","version":2},"attestation_state":"computed","paper":{"title":"Learning Semantically Coherent and Reusable Kernels in Convolution Neural Nets for Sentence Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Keerthi Selvaraj, Madhusudan Lakshmana, Shirish Shevade, Sundararajan Sellamanickam","submitted_at":"2016-08-01T15:14:08Z","abstract_excerpt":"The state-of-the-art CNN models give good performance on sentence classification tasks. The purpose of this work is to empirically study desirable properties such as semantic coherence, attention mechanism and reusability of CNNs in these tasks. Semantically coherent kernels are preferable as they are a lot more interpretable for explaining the decision of the learned CNN model. We observe that the learned kernels do not have semantic coherence. Motivated by this observation, we propose to learn kernels with semantic coherence using clustering scheme combined with Word2Vec representation and d"},"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":"1608.00466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-01T15:14:08Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"470836478a6f800718308e23658d05cd8b609d9a026cc4d247ec4dc5df6c57ed","abstract_canon_sha256":"eb87f9ccf3e7154a3ebf42c62f5c96cbb71febfa6abbaffcd5dffb93a56d64e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:51.867560Z","signature_b64":"2xud2jJ68o6rEfNq3THkXnghiPzM6KvdzUqX+5T4+7TZH6WPzwR6SBDj+h/8EL6KioC1670ShKsDpgn9gNHnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84bf5c06cf9c99b1053f02c50eb1aa69598990d0879e7f3c0386715c406ca0ad","last_reissued_at":"2026-05-18T01:02:51.867195Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:51.867195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Semantically Coherent and Reusable Kernels in Convolution Neural Nets for Sentence Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Keerthi Selvaraj, Madhusudan Lakshmana, Shirish Shevade, Sundararajan Sellamanickam","submitted_at":"2016-08-01T15:14:08Z","abstract_excerpt":"The state-of-the-art CNN models give good performance on sentence classification tasks. The purpose of this work is to empirically study desirable properties such as semantic coherence, attention mechanism and reusability of CNNs in these tasks. Semantically coherent kernels are preferable as they are a lot more interpretable for explaining the decision of the learned CNN model. We observe that the learned kernels do not have semantic coherence. Motivated by this observation, we propose to learn kernels with semantic coherence using clustering scheme combined with Word2Vec representation and d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.00466","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":"1608.00466","created_at":"2026-05-18T01:02:51.867250+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.00466v2","created_at":"2026-05-18T01:02:51.867250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.00466","created_at":"2026-05-18T01:02:51.867250+00:00"},{"alias_kind":"pith_short_12","alias_value":"QS7VYBWPTSM3","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"QS7VYBWPTSM3CBJ7","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"QS7VYBWP","created_at":"2026-05-18T12:30:41.710351+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/QS7VYBWPTSM3CBJ7ALCQ5MNKNF","json":"https://pith.science/pith/QS7VYBWPTSM3CBJ7ALCQ5MNKNF.json","graph_json":"https://pith.science/api/pith-number/QS7VYBWPTSM3CBJ7ALCQ5MNKNF/graph.json","events_json":"https://pith.science/api/pith-number/QS7VYBWPTSM3CBJ7ALCQ5MNKNF/events.json","paper":"https://pith.science/paper/QS7VYBWP"},"agent_actions":{"view_html":"https://pith.science/pith/QS7VYBWPTSM3CBJ7ALCQ5MNKNF","download_json":"https://pith.science/pith/QS7VYBWPTSM3CBJ7ALCQ5MNKNF.json","view_paper":"https://pith.science/paper/QS7VYBWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.00466&json=true","fetch_graph":"https://pith.science/api/pith-number/QS7VYBWPTSM3CBJ7ALCQ5MNKNF/graph.json","fetch_events":"https://pith.science/api/pith-number/QS7VYBWPTSM3CBJ7ALCQ5MNKNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QS7VYBWPTSM3CBJ7ALCQ5MNKNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QS7VYBWPTSM3CBJ7ALCQ5MNKNF/action/storage_attestation","attest_author":"https://pith.science/pith/QS7VYBWPTSM3CBJ7ALCQ5MNKNF/action/author_attestation","sign_citation":"https://pith.science/pith/QS7VYBWPTSM3CBJ7ALCQ5MNKNF/action/citation_signature","submit_replication":"https://pith.science/pith/QS7VYBWPTSM3CBJ7ALCQ5MNKNF/action/replication_record"}},"created_at":"2026-05-18T01:02:51.867250+00:00","updated_at":"2026-05-18T01:02:51.867250+00:00"}