{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3QN7EINV5YCAHPM46B3YG6TEKH","short_pith_number":"pith:3QN7EINV","schema_version":"1.0","canonical_sha256":"dc1bf221b5ee0403bd9cf077837a6451f7157f9ec46338869a4d902fe0f86709","source":{"kind":"arxiv","id":"1706.00932","version":1},"attestation_state":"computed","paper":{"title":"See, Hear, and Read: Deep Aligned Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Carl Vondrick, Yusuf Aytar","submitted_at":"2017-06-03T11:11:13Z","abstract_excerpt":"We capitalize on large amounts of readily-available, synchronous data to learn a deep discriminative representations shared across three major natural modalities: vision, sound and language. By leveraging over a year of sound from video and millions of sentences paired with images, we jointly train a deep convolutional network for aligned representation learning. Our experiments suggest that this representation is useful for several tasks, such as cross-modal retrieval or transferring classifiers between modalities. Moreover, although our network is only trained with image+text and image+sound"},"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":"1706.00932","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-03T11:11:13Z","cross_cats_sorted":[],"title_canon_sha256":"54bd1bdc924c1f78c208ae929ffc7aba4d377882ee8e51b0b4f387d7d3071b2c","abstract_canon_sha256":"1dd0ed2f0fe0d451ad5599e90d185b1c39dd8ea09f45c0a49234bb2073abe405"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:07.353360Z","signature_b64":"uxd3FLsXTx4gG1YSyZvCU0e6E4f5jf8KrKP8eDhcJ9gy6I9EKs/yYRVcPWJkx5B1eVYENSsMWqXg0EBXHNBOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc1bf221b5ee0403bd9cf077837a6451f7157f9ec46338869a4d902fe0f86709","last_reissued_at":"2026-05-18T00:43:07.352486Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:07.352486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"See, Hear, and Read: Deep Aligned Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Carl Vondrick, Yusuf Aytar","submitted_at":"2017-06-03T11:11:13Z","abstract_excerpt":"We capitalize on large amounts of readily-available, synchronous data to learn a deep discriminative representations shared across three major natural modalities: vision, sound and language. By leveraging over a year of sound from video and millions of sentences paired with images, we jointly train a deep convolutional network for aligned representation learning. Our experiments suggest that this representation is useful for several tasks, such as cross-modal retrieval or transferring classifiers between modalities. Moreover, although our network is only trained with image+text and image+sound"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00932","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":""},"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":"1706.00932","created_at":"2026-05-18T00:43:07.352582+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.00932v1","created_at":"2026-05-18T00:43:07.352582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00932","created_at":"2026-05-18T00:43:07.352582+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QN7EINV5YCA","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QN7EINV5YCAHPM4","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QN7EINV","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.12069","citing_title":"Tac-DINO: Learning Vision-Tactile Features with Patch Alignment","ref_index":117,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QN7EINV5YCAHPM46B3YG6TEKH","json":"https://pith.science/pith/3QN7EINV5YCAHPM46B3YG6TEKH.json","graph_json":"https://pith.science/api/pith-number/3QN7EINV5YCAHPM46B3YG6TEKH/graph.json","events_json":"https://pith.science/api/pith-number/3QN7EINV5YCAHPM46B3YG6TEKH/events.json","paper":"https://pith.science/paper/3QN7EINV"},"agent_actions":{"view_html":"https://pith.science/pith/3QN7EINV5YCAHPM46B3YG6TEKH","download_json":"https://pith.science/pith/3QN7EINV5YCAHPM46B3YG6TEKH.json","view_paper":"https://pith.science/paper/3QN7EINV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.00932&json=true","fetch_graph":"https://pith.science/api/pith-number/3QN7EINV5YCAHPM46B3YG6TEKH/graph.json","fetch_events":"https://pith.science/api/pith-number/3QN7EINV5YCAHPM46B3YG6TEKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QN7EINV5YCAHPM46B3YG6TEKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QN7EINV5YCAHPM46B3YG6TEKH/action/storage_attestation","attest_author":"https://pith.science/pith/3QN7EINV5YCAHPM46B3YG6TEKH/action/author_attestation","sign_citation":"https://pith.science/pith/3QN7EINV5YCAHPM46B3YG6TEKH/action/citation_signature","submit_replication":"https://pith.science/pith/3QN7EINV5YCAHPM46B3YG6TEKH/action/replication_record"}},"created_at":"2026-05-18T00:43:07.352582+00:00","updated_at":"2026-05-18T00:43:07.352582+00:00"}