{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3QN7EINV5YCAHPM46B3YG6TEKH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1dd0ed2f0fe0d451ad5599e90d185b1c39dd8ea09f45c0a49234bb2073abe405","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-03T11:11:13Z","title_canon_sha256":"54bd1bdc924c1f78c208ae929ffc7aba4d377882ee8e51b0b4f387d7d3071b2c"},"schema_version":"1.0","source":{"id":"1706.00932","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00932","created_at":"2026-05-18T00:43:07Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00932v1","created_at":"2026-05-18T00:43:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00932","created_at":"2026-05-18T00:43:07Z"},{"alias_kind":"pith_short_12","alias_value":"3QN7EINV5YCA","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3QN7EINV5YCAHPM4","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3QN7EINV","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:5cff5d87558f34ea5683214e7b27540b7d89beb2f207ced4df8517c3a1746ff0","target":"graph","created_at":"2026-05-18T00:43:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Antonio Torralba, Carl Vondrick, Yusuf Aytar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-03T11:11:13Z","title":"See, Hear, and Read: Deep Aligned Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00932","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c269a03395700d80d1c88c01be78aeffa93dccd3ba59bb1875624f8817b62230","target":"record","created_at":"2026-05-18T00:43:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1dd0ed2f0fe0d451ad5599e90d185b1c39dd8ea09f45c0a49234bb2073abe405","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-03T11:11:13Z","title_canon_sha256":"54bd1bdc924c1f78c208ae929ffc7aba4d377882ee8e51b0b4f387d7d3071b2c"},"schema_version":"1.0","source":{"id":"1706.00932","kind":"arxiv","version":1}},"canonical_sha256":"dc1bf221b5ee0403bd9cf077837a6451f7157f9ec46338869a4d902fe0f86709","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc1bf221b5ee0403bd9cf077837a6451f7157f9ec46338869a4d902fe0f86709","first_computed_at":"2026-05-18T00:43:07.352486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:07.352486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uxd3FLsXTx4gG1YSyZvCU0e6E4f5jf8KrKP8eDhcJ9gy6I9EKs/yYRVcPWJkx5B1eVYENSsMWqXg0EBXHNBOCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:07.353360Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.00932","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c269a03395700d80d1c88c01be78aeffa93dccd3ba59bb1875624f8817b62230","sha256:5cff5d87558f34ea5683214e7b27540b7d89beb2f207ced4df8517c3a1746ff0"],"state_sha256":"7169c5131e83b252ff32a6c34a89c0e91e37b5393e74e825be274dad38b316e6"}