{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5P7WIPVPZKSGNYBQ5M7RPXZC2Q","short_pith_number":"pith:5P7WIPVP","schema_version":"1.0","canonical_sha256":"ebff643eafcaa466e030eb3f17df22d41c8f43ea0a9a813a388f5cf0e3d71b2a","source":{"kind":"arxiv","id":"1703.01720","version":4},"attestation_state":"computed","paper":{"title":"Sound-Word2Vec: Learning Word Representations Grounded in Sounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.CL","authors_text":"Ashwin K Vijayakumar, Devi Parikh, Ramakrishna Vedantam","submitted_at":"2017-03-06T04:30:12Z","abstract_excerpt":"To be able to interact better with humans, it is crucial for machines to understand sound - a primary modality of human perception. Previous works have used sound to learn embeddings for improved generic textual similarity assessment. In this work, we treat sound as a first-class citizen, studying downstream textual tasks which require aural grounding. To this end, we propose sound-word2vec - a new embedding scheme that learns specialized word embeddings grounded in sounds. For example, we learn that two seemingly (semantically) unrelated concepts, like leaves and paper are similar due to the "},"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":"1703.01720","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-06T04:30:12Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"54a716a971913824a7288e5fedd5da1b6fc8a3bf894fcd6e4f3c6da62441aa62","abstract_canon_sha256":"d763c40006ba33fa6e117b873839fbc85710afa0f82f82e4a98d057aba78c336"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:32.490270Z","signature_b64":"8N+NbVah/VvLr5QRQBvNDCgWmHQnbhTOh+mxcl5rogLFSDRsltidH7QsjJnHMCbLggPwD2rNXHQlc9baAKcLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebff643eafcaa466e030eb3f17df22d41c8f43ea0a9a813a388f5cf0e3d71b2a","last_reissued_at":"2026-05-18T00:36:32.489718Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:32.489718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sound-Word2Vec: Learning Word Representations Grounded in Sounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.CL","authors_text":"Ashwin K Vijayakumar, Devi Parikh, Ramakrishna Vedantam","submitted_at":"2017-03-06T04:30:12Z","abstract_excerpt":"To be able to interact better with humans, it is crucial for machines to understand sound - a primary modality of human perception. Previous works have used sound to learn embeddings for improved generic textual similarity assessment. In this work, we treat sound as a first-class citizen, studying downstream textual tasks which require aural grounding. To this end, we propose sound-word2vec - a new embedding scheme that learns specialized word embeddings grounded in sounds. For example, we learn that two seemingly (semantically) unrelated concepts, like leaves and paper are similar due to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01720","kind":"arxiv","version":4},"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":"1703.01720","created_at":"2026-05-18T00:36:32.489803+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.01720v4","created_at":"2026-05-18T00:36:32.489803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01720","created_at":"2026-05-18T00:36:32.489803+00:00"},{"alias_kind":"pith_short_12","alias_value":"5P7WIPVPZKSG","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5P7WIPVPZKSGNYBQ","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5P7WIPVP","created_at":"2026-05-18T12:31:00.734936+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/5P7WIPVPZKSGNYBQ5M7RPXZC2Q","json":"https://pith.science/pith/5P7WIPVPZKSGNYBQ5M7RPXZC2Q.json","graph_json":"https://pith.science/api/pith-number/5P7WIPVPZKSGNYBQ5M7RPXZC2Q/graph.json","events_json":"https://pith.science/api/pith-number/5P7WIPVPZKSGNYBQ5M7RPXZC2Q/events.json","paper":"https://pith.science/paper/5P7WIPVP"},"agent_actions":{"view_html":"https://pith.science/pith/5P7WIPVPZKSGNYBQ5M7RPXZC2Q","download_json":"https://pith.science/pith/5P7WIPVPZKSGNYBQ5M7RPXZC2Q.json","view_paper":"https://pith.science/paper/5P7WIPVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.01720&json=true","fetch_graph":"https://pith.science/api/pith-number/5P7WIPVPZKSGNYBQ5M7RPXZC2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/5P7WIPVPZKSGNYBQ5M7RPXZC2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5P7WIPVPZKSGNYBQ5M7RPXZC2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5P7WIPVPZKSGNYBQ5M7RPXZC2Q/action/storage_attestation","attest_author":"https://pith.science/pith/5P7WIPVPZKSGNYBQ5M7RPXZC2Q/action/author_attestation","sign_citation":"https://pith.science/pith/5P7WIPVPZKSGNYBQ5M7RPXZC2Q/action/citation_signature","submit_replication":"https://pith.science/pith/5P7WIPVPZKSGNYBQ5M7RPXZC2Q/action/replication_record"}},"created_at":"2026-05-18T00:36:32.489803+00:00","updated_at":"2026-05-18T00:36:32.489803+00:00"}