{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DHHBUU542TJWJNWHYJ6MTWM3HY","short_pith_number":"pith:DHHBUU54","canonical_record":{"source":{"id":"1803.10082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T13:55:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"54613a0f19cbc10118004f82b6e972135e2d835aae2f8cf308c45b1f845a235a","abstract_canon_sha256":"98ceda30e01d1f3849dd5daea992866aac510fca52f28cc61fd5f3d474f1d5d4"},"schema_version":"1.0"},"canonical_sha256":"19ce1a53bcd4d364b6c7c27cc9d99b3e389a82398783d4fb6b6c1c05c77d7889","source":{"kind":"arxiv","id":"1803.10082","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10082","created_at":"2026-05-18T00:20:00Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10082v1","created_at":"2026-05-18T00:20:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10082","created_at":"2026-05-18T00:20:00Z"},{"alias_kind":"pith_short_12","alias_value":"DHHBUU542TJW","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DHHBUU542TJWJNWH","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DHHBUU54","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DHHBUU542TJWJNWHYJ6MTWM3HY","target":"record","payload":{"canonical_record":{"source":{"id":"1803.10082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T13:55:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"54613a0f19cbc10118004f82b6e972135e2d835aae2f8cf308c45b1f845a235a","abstract_canon_sha256":"98ceda30e01d1f3849dd5daea992866aac510fca52f28cc61fd5f3d474f1d5d4"},"schema_version":"1.0"},"canonical_sha256":"19ce1a53bcd4d364b6c7c27cc9d99b3e389a82398783d4fb6b6c1c05c77d7889","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:00.509613Z","signature_b64":"HteiGwOrCGNL1sJeUi4+dqyTT9DfupOVudGBFhcHyOfwhVd0NE/eCLR8Y1L8uHrM8NqF/Wyl6On7u2ByQi6ZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19ce1a53bcd4d364b6c7c27cc9d99b3e389a82398783d4fb6b6c1c05c77d7889","last_reissued_at":"2026-05-18T00:20:00.509056Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:00.509056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.10082","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afbpSVoiM+PEqcVcBsBxLfrz00/s1yFiu32brOPCUrWPODm3rNd7aL8cKyNZY4WpCWTe37696C/P54ys2yRHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:09:59.249881Z"},"content_sha256":"13f6c435bc5be6eb9f1954e969ecef34336d21915f81154d1278ed86bf155379","schema_version":"1.0","event_id":"sha256:13f6c435bc5be6eb9f1954e969ecef34336d21915f81154d1278ed86bf155379"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DHHBUU542TJWJNWHYJ6MTWM3HY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient parametrization of multi-domain deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Hakan Bilen, Sylvestre-Alvise Rebuffi","submitted_at":"2018-03-27T13:55:56Z","abstract_excerpt":"A practical limitation of deep neural networks is their high degree of specialization to a single task and visual domain. Recently, inspired by the successes of transfer learning, several authors have proposed to learn instead universal, fixed feature extractors that, used as the first stage of any deep network, work well for several tasks and domains simultaneously. Nevertheless, such universal features are still somewhat inferior to specialized networks.\n  To overcome this limitation, in this paper we propose to consider instead universal parametric families of neural networks, which still c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10082","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jv7Y5PLztM+iBqfSHZsmpAq19NDXGkD0Y8IwB3ubJ0gMT7oksrTc97UzsUcZVtzrGCjJ6v9ekiY2jgeoFlqUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:09:59.250577Z"},"content_sha256":"03cf23c1ccf8352a9c0de530691dec6f1167458da70ca3f1477ea485ae9cff70","schema_version":"1.0","event_id":"sha256:03cf23c1ccf8352a9c0de530691dec6f1167458da70ca3f1477ea485ae9cff70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHHBUU542TJWJNWHYJ6MTWM3HY/bundle.json","state_url":"https://pith.science/pith/DHHBUU542TJWJNWHYJ6MTWM3HY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHHBUU542TJWJNWHYJ6MTWM3HY/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":"2026-05-26T07:09:59Z","links":{"resolver":"https://pith.science/pith/DHHBUU542TJWJNWHYJ6MTWM3HY","bundle":"https://pith.science/pith/DHHBUU542TJWJNWHYJ6MTWM3HY/bundle.json","state":"https://pith.science/pith/DHHBUU542TJWJNWHYJ6MTWM3HY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHHBUU542TJWJNWHYJ6MTWM3HY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DHHBUU542TJWJNWHYJ6MTWM3HY","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":"98ceda30e01d1f3849dd5daea992866aac510fca52f28cc61fd5f3d474f1d5d4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T13:55:56Z","title_canon_sha256":"54613a0f19cbc10118004f82b6e972135e2d835aae2f8cf308c45b1f845a235a"},"schema_version":"1.0","source":{"id":"1803.10082","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10082","created_at":"2026-05-18T00:20:00Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10082v1","created_at":"2026-05-18T00:20:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10082","created_at":"2026-05-18T00:20:00Z"},{"alias_kind":"pith_short_12","alias_value":"DHHBUU542TJW","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DHHBUU542TJWJNWH","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DHHBUU54","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:03cf23c1ccf8352a9c0de530691dec6f1167458da70ca3f1477ea485ae9cff70","target":"graph","created_at":"2026-05-18T00:20:00Z","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":"A practical limitation of deep neural networks is their high degree of specialization to a single task and visual domain. Recently, inspired by the successes of transfer learning, several authors have proposed to learn instead universal, fixed feature extractors that, used as the first stage of any deep network, work well for several tasks and domains simultaneously. Nevertheless, such universal features are still somewhat inferior to specialized networks.\n  To overcome this limitation, in this paper we propose to consider instead universal parametric families of neural networks, which still c","authors_text":"Andrea Vedaldi, Hakan Bilen, Sylvestre-Alvise Rebuffi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T13:55:56Z","title":"Efficient parametrization of multi-domain deep neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10082","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":"sha256:13f6c435bc5be6eb9f1954e969ecef34336d21915f81154d1278ed86bf155379","target":"record","created_at":"2026-05-18T00:20:00Z","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":"98ceda30e01d1f3849dd5daea992866aac510fca52f28cc61fd5f3d474f1d5d4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T13:55:56Z","title_canon_sha256":"54613a0f19cbc10118004f82b6e972135e2d835aae2f8cf308c45b1f845a235a"},"schema_version":"1.0","source":{"id":"1803.10082","kind":"arxiv","version":1}},"canonical_sha256":"19ce1a53bcd4d364b6c7c27cc9d99b3e389a82398783d4fb6b6c1c05c77d7889","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19ce1a53bcd4d364b6c7c27cc9d99b3e389a82398783d4fb6b6c1c05c77d7889","first_computed_at":"2026-05-18T00:20:00.509056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:00.509056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HteiGwOrCGNL1sJeUi4+dqyTT9DfupOVudGBFhcHyOfwhVd0NE/eCLR8Y1L8uHrM8NqF/Wyl6On7u2ByQi6ZCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:00.509613Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.10082","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13f6c435bc5be6eb9f1954e969ecef34336d21915f81154d1278ed86bf155379","sha256:03cf23c1ccf8352a9c0de530691dec6f1167458da70ca3f1477ea485ae9cff70"],"state_sha256":"ab32d60c0edb5149011eb64f4e75d8bf38a16ce7b7fcde3bc5279f5707bada4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7jBI8u2TJakat9Fw/HAyg1cYp2s7tW/R5DaPYS2It81srLQpgSVoVpWO7x1/AkEB0Dpw3rE+0ubcrmFkpBd/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:09:59.254105Z","bundle_sha256":"a4fff9e39020c1d1259208d8482a32278bb1b5482f4ca6fea10bb0ce51f8dd36"}}