{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:B6QQIIAGEYC6RT5UE2SWYTRX5K","short_pith_number":"pith:B6QQIIAG","canonical_record":{"source":{"id":"1705.08045","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-22T23:59:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8d7e243fef85e9a5e50fc862733d5ced0099f4c74f51647865f63feb67b2ba69","abstract_canon_sha256":"26b083b14ef47960156a1f7f982a10ab4ff2480cdfbfbf15cef9f0cecb1cf20d"},"schema_version":"1.0"},"canonical_sha256":"0fa10420062605e8cfb426a56c4e37ea898a25896c409dbe8fc4eec639c62c58","source":{"kind":"arxiv","id":"1705.08045","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08045","created_at":"2026-05-18T00:29:39Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08045v5","created_at":"2026-05-18T00:29:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08045","created_at":"2026-05-18T00:29:39Z"},{"alias_kind":"pith_short_12","alias_value":"B6QQIIAGEYC6","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"B6QQIIAGEYC6RT5U","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"B6QQIIAG","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:B6QQIIAGEYC6RT5UE2SWYTRX5K","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08045","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-22T23:59:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8d7e243fef85e9a5e50fc862733d5ced0099f4c74f51647865f63feb67b2ba69","abstract_canon_sha256":"26b083b14ef47960156a1f7f982a10ab4ff2480cdfbfbf15cef9f0cecb1cf20d"},"schema_version":"1.0"},"canonical_sha256":"0fa10420062605e8cfb426a56c4e37ea898a25896c409dbe8fc4eec639c62c58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:39.057402Z","signature_b64":"Pnt4AuyZ5hjBoTB6BCk76S+d0pUMJT2wzncgQQTBapbB1zw5NP5B/QU3UpDgo9RgL3YAqHDAysi8h9SUAQRDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fa10420062605e8cfb426a56c4e37ea898a25896c409dbe8fc4eec639c62c58","last_reissued_at":"2026-05-18T00:29:39.056830Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:39.056830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08045","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:29:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3DhrhL6wiKO2kJGV8kcnRrU8nTadhE0uPyMbrOxvXUmDGXEORK1zygrvWncsl3u+WS++Tmoirn3gLrCGfKCmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:22:33.737083Z"},"content_sha256":"8a029b7e137bc23bb55c654e76a60cb53b507b38b1de1ee8e79fc7b220d28186","schema_version":"1.0","event_id":"sha256:8a029b7e137bc23bb55c654e76a60cb53b507b38b1de1ee8e79fc7b220d28186"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:B6QQIIAGEYC6RT5UE2SWYTRX5K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning multiple visual domains with residual adapters","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":"2017-05-22T23:59:23Z","abstract_excerpt":"There is a growing interest in learning data representations that work well for many different types of problems and data. In this paper, we look in particular at the task of learning a single visual representation that can be successfully utilized in the analysis of very different types of images, from dog breeds to stop signs and digits. Inspired by recent work on learning networks that predict the parameters of another, we develop a tunable deep network architecture that, by means of adapter residual modules, can be steered on the fly to diverse visual domains. Our method achieves a high de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08045","kind":"arxiv","version":5},"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":"2026-05-18T00:29:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jmFtJb7zEcB8iUppegZ1Ei1Arat9HpNLZZA71bTSqI3qitcEQz7hTd7V0UfghdeK3l05wmPXeBOiaUfUtat6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:22:33.737452Z"},"content_sha256":"fa9d27a1dfa3008c155bd0618f5cb2b4ec1868bd2ffb05db823a9ce0919b2445","schema_version":"1.0","event_id":"sha256:fa9d27a1dfa3008c155bd0618f5cb2b4ec1868bd2ffb05db823a9ce0919b2445"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B6QQIIAGEYC6RT5UE2SWYTRX5K/bundle.json","state_url":"https://pith.science/pith/B6QQIIAGEYC6RT5UE2SWYTRX5K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B6QQIIAGEYC6RT5UE2SWYTRX5K/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":"2026-06-02T23:22:33Z","links":{"resolver":"https://pith.science/pith/B6QQIIAGEYC6RT5UE2SWYTRX5K","bundle":"https://pith.science/pith/B6QQIIAGEYC6RT5UE2SWYTRX5K/bundle.json","state":"https://pith.science/pith/B6QQIIAGEYC6RT5UE2SWYTRX5K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B6QQIIAGEYC6RT5UE2SWYTRX5K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:B6QQIIAGEYC6RT5UE2SWYTRX5K","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":"26b083b14ef47960156a1f7f982a10ab4ff2480cdfbfbf15cef9f0cecb1cf20d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-22T23:59:23Z","title_canon_sha256":"8d7e243fef85e9a5e50fc862733d5ced0099f4c74f51647865f63feb67b2ba69"},"schema_version":"1.0","source":{"id":"1705.08045","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08045","created_at":"2026-05-18T00:29:39Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08045v5","created_at":"2026-05-18T00:29:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08045","created_at":"2026-05-18T00:29:39Z"},{"alias_kind":"pith_short_12","alias_value":"B6QQIIAGEYC6","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"B6QQIIAGEYC6RT5U","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"B6QQIIAG","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:fa9d27a1dfa3008c155bd0618f5cb2b4ec1868bd2ffb05db823a9ce0919b2445","target":"graph","created_at":"2026-05-18T00:29:39Z","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":"There is a growing interest in learning data representations that work well for many different types of problems and data. In this paper, we look in particular at the task of learning a single visual representation that can be successfully utilized in the analysis of very different types of images, from dog breeds to stop signs and digits. Inspired by recent work on learning networks that predict the parameters of another, we develop a tunable deep network architecture that, by means of adapter residual modules, can be steered on the fly to diverse visual domains. Our method achieves a high de","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":"2017-05-22T23:59:23Z","title":"Learning multiple visual domains with residual adapters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08045","kind":"arxiv","version":5},"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":"sha256:8a029b7e137bc23bb55c654e76a60cb53b507b38b1de1ee8e79fc7b220d28186","target":"record","created_at":"2026-05-18T00:29:39Z","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":"26b083b14ef47960156a1f7f982a10ab4ff2480cdfbfbf15cef9f0cecb1cf20d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-22T23:59:23Z","title_canon_sha256":"8d7e243fef85e9a5e50fc862733d5ced0099f4c74f51647865f63feb67b2ba69"},"schema_version":"1.0","source":{"id":"1705.08045","kind":"arxiv","version":5}},"canonical_sha256":"0fa10420062605e8cfb426a56c4e37ea898a25896c409dbe8fc4eec639c62c58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fa10420062605e8cfb426a56c4e37ea898a25896c409dbe8fc4eec639c62c58","first_computed_at":"2026-05-18T00:29:39.056830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:39.056830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pnt4AuyZ5hjBoTB6BCk76S+d0pUMJT2wzncgQQTBapbB1zw5NP5B/QU3UpDgo9RgL3YAqHDAysi8h9SUAQRDDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:39.057402Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08045","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a029b7e137bc23bb55c654e76a60cb53b507b38b1de1ee8e79fc7b220d28186","sha256:fa9d27a1dfa3008c155bd0618f5cb2b4ec1868bd2ffb05db823a9ce0919b2445"],"state_sha256":"06de4e3fe1c117f93ce0f51b8fb8e9d0bab9b614b17a651ac68889cb40d4e83f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWXjj+LyhJYIi9k1ezq2l3oizd2TdTSNWwfVaGDrMC5aQ5CpxufrN+t/z7TgFeJcpxF2WWIb14osJAIoDLJfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:22:33.739404Z","bundle_sha256":"0f9813a029d8c27b24e78f42e28f84bf8507683b0f89bfcf9890827fed8c96aa"}}