{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:WZEHG3QJJL55RPE7WSRSDLWKIS","short_pith_number":"pith:WZEHG3QJ","canonical_record":{"source":{"id":"1506.00511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-01T14:37:06Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"a856f726bc565216b07fc9b1623141f252a233d333e594ee06c297e234a3c0d9","abstract_canon_sha256":"f216577e299bf748c63453a4c948fee7ff16f207fe85e5ac107b7ee5b3a69ac2"},"schema_version":"1.0"},"canonical_sha256":"b648736e094afbd8bc9fb4a321aeca44a9624b5df8c3856c51cd2b9ee9afe55f","source":{"kind":"arxiv","id":"1506.00511","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.00511","created_at":"2026-05-18T01:32:07Z"},{"alias_kind":"arxiv_version","alias_value":"1506.00511v2","created_at":"2026-05-18T01:32:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.00511","created_at":"2026-05-18T01:32:07Z"},{"alias_kind":"pith_short_12","alias_value":"WZEHG3QJJL55","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WZEHG3QJJL55RPE7","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WZEHG3QJ","created_at":"2026-05-18T12:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:WZEHG3QJJL55RPE7WSRSDLWKIS","target":"record","payload":{"canonical_record":{"source":{"id":"1506.00511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-01T14:37:06Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"a856f726bc565216b07fc9b1623141f252a233d333e594ee06c297e234a3c0d9","abstract_canon_sha256":"f216577e299bf748c63453a4c948fee7ff16f207fe85e5ac107b7ee5b3a69ac2"},"schema_version":"1.0"},"canonical_sha256":"b648736e094afbd8bc9fb4a321aeca44a9624b5df8c3856c51cd2b9ee9afe55f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:07.982112Z","signature_b64":"8hM/sPUFwBgMprFc0yC1hdv2dEl0hkHyACE4425jNTdpM3Om9lQJWeLnAprii76JhC6nNeQr/Smc9np2TuKdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b648736e094afbd8bc9fb4a321aeca44a9624b5df8c3856c51cd2b9ee9afe55f","last_reissued_at":"2026-05-18T01:32:07.981506Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:07.981506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.00511","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:32:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"peltMEMoygBqVK8LbbKb6QOnMd2++nQjB4loqZAEyXzj3K/C60A6gH/ssnP5/SfmICLpW0XaZmvnUQWZtj9fBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T22:53:06.282150Z"},"content_sha256":"a0bf2203788c57ad42e97db9dec6f983fc373c0161a5fe763fbaa1313a88df65","schema_version":"1.0","event_id":"sha256:a0bf2203788c57ad42e97db9dec6f983fc373c0161a5fe763fbaa1313a88df65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:WZEHG3QJJL55RPE7WSRSDLWKIS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jimmy Ba, Kevin Swersky, Ruslan Salakhutdinov, Sanja Fidler","submitted_at":"2015-06-01T14:37:06Z","abstract_excerpt":"One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images. Recent work has shown that learning from textual descriptions, such as Wikipedia articles, avoids the problem of having to explicitly define these attributes. We present a new model that can classify unseen categories from their textual description. Specifically, we use text features to predict the output weights of both the convolutional and the fully connected layers in a deep convolutional neural network (CNN). We take advantage of the architecture of CNNs and learn fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.00511","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:32:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o+OhTzeQfrtWBSlgtnzAh3KCQTsH8pJuGGerBq3Vyh8EXtRLrGG05qNqE2dRomlmKE5eRFru4HocfAmcs253DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T22:53:06.282806Z"},"content_sha256":"537a668b931977c442070d60a9ac939806f2351987cffa3b2da27cd06ed3c6d8","schema_version":"1.0","event_id":"sha256:537a668b931977c442070d60a9ac939806f2351987cffa3b2da27cd06ed3c6d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZEHG3QJJL55RPE7WSRSDLWKIS/bundle.json","state_url":"https://pith.science/pith/WZEHG3QJJL55RPE7WSRSDLWKIS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZEHG3QJJL55RPE7WSRSDLWKIS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T22:53:06Z","links":{"resolver":"https://pith.science/pith/WZEHG3QJJL55RPE7WSRSDLWKIS","bundle":"https://pith.science/pith/WZEHG3QJJL55RPE7WSRSDLWKIS/bundle.json","state":"https://pith.science/pith/WZEHG3QJJL55RPE7WSRSDLWKIS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZEHG3QJJL55RPE7WSRSDLWKIS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:WZEHG3QJJL55RPE7WSRSDLWKIS","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":"f216577e299bf748c63453a4c948fee7ff16f207fe85e5ac107b7ee5b3a69ac2","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-01T14:37:06Z","title_canon_sha256":"a856f726bc565216b07fc9b1623141f252a233d333e594ee06c297e234a3c0d9"},"schema_version":"1.0","source":{"id":"1506.00511","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.00511","created_at":"2026-05-18T01:32:07Z"},{"alias_kind":"arxiv_version","alias_value":"1506.00511v2","created_at":"2026-05-18T01:32:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.00511","created_at":"2026-05-18T01:32:07Z"},{"alias_kind":"pith_short_12","alias_value":"WZEHG3QJJL55","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WZEHG3QJJL55RPE7","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WZEHG3QJ","created_at":"2026-05-18T12:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:537a668b931977c442070d60a9ac939806f2351987cffa3b2da27cd06ed3c6d8","target":"graph","created_at":"2026-05-18T01:32:07Z","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":"One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images. Recent work has shown that learning from textual descriptions, such as Wikipedia articles, avoids the problem of having to explicitly define these attributes. We present a new model that can classify unseen categories from their textual description. Specifically, we use text features to predict the output weights of both the convolutional and the fully connected layers in a deep convolutional neural network (CNN). We take advantage of the architecture of CNNs and learn fe","authors_text":"Jimmy Ba, Kevin Swersky, Ruslan Salakhutdinov, Sanja Fidler","cross_cats":["cs.CV","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-01T14:37:06Z","title":"Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.00511","kind":"arxiv","version":2},"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:a0bf2203788c57ad42e97db9dec6f983fc373c0161a5fe763fbaa1313a88df65","target":"record","created_at":"2026-05-18T01:32:07Z","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":"f216577e299bf748c63453a4c948fee7ff16f207fe85e5ac107b7ee5b3a69ac2","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-01T14:37:06Z","title_canon_sha256":"a856f726bc565216b07fc9b1623141f252a233d333e594ee06c297e234a3c0d9"},"schema_version":"1.0","source":{"id":"1506.00511","kind":"arxiv","version":2}},"canonical_sha256":"b648736e094afbd8bc9fb4a321aeca44a9624b5df8c3856c51cd2b9ee9afe55f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b648736e094afbd8bc9fb4a321aeca44a9624b5df8c3856c51cd2b9ee9afe55f","first_computed_at":"2026-05-18T01:32:07.981506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:32:07.981506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8hM/sPUFwBgMprFc0yC1hdv2dEl0hkHyACE4425jNTdpM3Om9lQJWeLnAprii76JhC6nNeQr/Smc9np2TuKdCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:32:07.982112Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.00511","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0bf2203788c57ad42e97db9dec6f983fc373c0161a5fe763fbaa1313a88df65","sha256:537a668b931977c442070d60a9ac939806f2351987cffa3b2da27cd06ed3c6d8"],"state_sha256":"7a48321cdb61105e0ac8aed997e55454d7c8246bf6baab7ce9bd244fd51f4d1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qAYhOT8SeCmnBADzNrl6btc4kpWy622qvUWkWLZDi+lpQ76aa8ZGeek8HbBUZb9R90nHNtTGOhfB/ppB4LaCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T22:53:06.286173Z","bundle_sha256":"fdc0bb575995468739e1d5730e525b69c286cee4070f280d5ac57de285870b23"}}