{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FOFPVLJUK57QMEAW5AJGKFNBCV","short_pith_number":"pith:FOFPVLJU","canonical_record":{"source":{"id":"1810.10703","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-25T03:12:37Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"ea49919c4eaca1d2291d634fd75026f91db57d6a3ee5d1d1f1a7fbeee97d5036","abstract_canon_sha256":"7e87820b1987da77720405a7e0a93bd8ea235b54315f176235fe012d4f869f9b"},"schema_version":"1.0"},"canonical_sha256":"2b8afaad34577f061016e8126515a1156c3612c44a165c818e9bd922968a097b","source":{"kind":"arxiv","id":"1810.10703","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.10703","created_at":"2026-05-17T23:52:51Z"},{"alias_kind":"arxiv_version","alias_value":"1810.10703v2","created_at":"2026-05-17T23:52:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10703","created_at":"2026-05-17T23:52:51Z"},{"alias_kind":"pith_short_12","alias_value":"FOFPVLJUK57Q","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FOFPVLJUK57QMEAW","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FOFPVLJU","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FOFPVLJUK57QMEAW5AJGKFNBCV","target":"record","payload":{"canonical_record":{"source":{"id":"1810.10703","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-25T03:12:37Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"ea49919c4eaca1d2291d634fd75026f91db57d6a3ee5d1d1f1a7fbeee97d5036","abstract_canon_sha256":"7e87820b1987da77720405a7e0a93bd8ea235b54315f176235fe012d4f869f9b"},"schema_version":"1.0"},"canonical_sha256":"2b8afaad34577f061016e8126515a1156c3612c44a165c818e9bd922968a097b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:51.777128Z","signature_b64":"XL3BGJMcydTCL9avpOW4+Vy+fFj19BdzUiwrXFQz6MX4H4874nHIVFGbbf674kUNPRII+PxWTAUxoECusCepAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b8afaad34577f061016e8126515a1156c3612c44a165c818e9bd922968a097b","last_reissued_at":"2026-05-17T23:52:51.776457Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:51.776457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.10703","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":"2026-05-17T23:52:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MznWB9wVfmygza3pOo+tN0Yw1APXsEq0scgmgTQkxukBHJ7RrRkQI4HuVjDtXCkcYEW/gR+P1OZ0Jm1zANd0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:39:48.110437Z"},"content_sha256":"af1cf564194c7cc0b6248d3263fb3bb24d4fe258e1f2b6b6428260f6d495eee5","schema_version":"1.0","event_id":"sha256:af1cf564194c7cc0b6248d3263fb3bb24d4fe258e1f2b6b6428260f6d495eee5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FOFPVLJUK57QMEAW5AJGKFNBCV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Howard, Andrey Zhmoginov, Mark Sandler, Pramod Kaushik Mudrakarta","submitted_at":"2018-10-25T03:12:37Z","abstract_excerpt":"We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead of fine-tuning the last layer or the entire network. For instance, we show that learning a set of scales and biases is sufficient to convert a pretrained network to perform well on qualitatively different problems (e.g. converting a Single Shot MultiBox Detection (SSD) model into a 1000-class image classification model while reusing 98% of parameters of the S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10703","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":"2026-05-17T23:52:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"29fhjIQbPgvCkfcZOq1MhGjtFDsVsnpn9NJz53c2MpD80yZy832neE336V7cZpap8HS9K0vwXQGj0mu75z4HBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:39:48.110791Z"},"content_sha256":"6be8a01bbbfaacd16a02e04957b1ffd292f138201bbfb18a1ab4edbf8cf3da31","schema_version":"1.0","event_id":"sha256:6be8a01bbbfaacd16a02e04957b1ffd292f138201bbfb18a1ab4edbf8cf3da31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FOFPVLJUK57QMEAW5AJGKFNBCV/bundle.json","state_url":"https://pith.science/pith/FOFPVLJUK57QMEAW5AJGKFNBCV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FOFPVLJUK57QMEAW5AJGKFNBCV/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":"2026-06-01T03:39:48Z","links":{"resolver":"https://pith.science/pith/FOFPVLJUK57QMEAW5AJGKFNBCV","bundle":"https://pith.science/pith/FOFPVLJUK57QMEAW5AJGKFNBCV/bundle.json","state":"https://pith.science/pith/FOFPVLJUK57QMEAW5AJGKFNBCV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FOFPVLJUK57QMEAW5AJGKFNBCV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FOFPVLJUK57QMEAW5AJGKFNBCV","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":"7e87820b1987da77720405a7e0a93bd8ea235b54315f176235fe012d4f869f9b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-25T03:12:37Z","title_canon_sha256":"ea49919c4eaca1d2291d634fd75026f91db57d6a3ee5d1d1f1a7fbeee97d5036"},"schema_version":"1.0","source":{"id":"1810.10703","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.10703","created_at":"2026-05-17T23:52:51Z"},{"alias_kind":"arxiv_version","alias_value":"1810.10703v2","created_at":"2026-05-17T23:52:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10703","created_at":"2026-05-17T23:52:51Z"},{"alias_kind":"pith_short_12","alias_value":"FOFPVLJUK57Q","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FOFPVLJUK57QMEAW","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FOFPVLJU","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:6be8a01bbbfaacd16a02e04957b1ffd292f138201bbfb18a1ab4edbf8cf3da31","target":"graph","created_at":"2026-05-17T23:52:51Z","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 introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead of fine-tuning the last layer or the entire network. For instance, we show that learning a set of scales and biases is sufficient to convert a pretrained network to perform well on qualitatively different problems (e.g. converting a Single Shot MultiBox Detection (SSD) model into a 1000-class image classification model while reusing 98% of parameters of the S","authors_text":"Andrew Howard, Andrey Zhmoginov, Mark Sandler, Pramod Kaushik Mudrakarta","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-25T03:12:37Z","title":"K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10703","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:af1cf564194c7cc0b6248d3263fb3bb24d4fe258e1f2b6b6428260f6d495eee5","target":"record","created_at":"2026-05-17T23:52:51Z","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":"7e87820b1987da77720405a7e0a93bd8ea235b54315f176235fe012d4f869f9b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-25T03:12:37Z","title_canon_sha256":"ea49919c4eaca1d2291d634fd75026f91db57d6a3ee5d1d1f1a7fbeee97d5036"},"schema_version":"1.0","source":{"id":"1810.10703","kind":"arxiv","version":2}},"canonical_sha256":"2b8afaad34577f061016e8126515a1156c3612c44a165c818e9bd922968a097b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b8afaad34577f061016e8126515a1156c3612c44a165c818e9bd922968a097b","first_computed_at":"2026-05-17T23:52:51.776457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:51.776457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XL3BGJMcydTCL9avpOW4+Vy+fFj19BdzUiwrXFQz6MX4H4874nHIVFGbbf674kUNPRII+PxWTAUxoECusCepAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:51.777128Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.10703","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af1cf564194c7cc0b6248d3263fb3bb24d4fe258e1f2b6b6428260f6d495eee5","sha256:6be8a01bbbfaacd16a02e04957b1ffd292f138201bbfb18a1ab4edbf8cf3da31"],"state_sha256":"9aede4a62cbd9856b2ccb2b1126a155297bea2071b95f83e538579e81deba79d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jz8e876iBNzjkl1/VzpfaH4YXXpquR+rkPR2TH/bwMPlm3CXdMxqXcF9edHs3+7OyyzyhKYEotJmiVJCFyUUAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T03:39:48.113134Z","bundle_sha256":"c8eed44cde5a414f2786ab3547b0b278df4bada6d7838ba0743d42411a5b6521"}}