{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YQK2SGBHDYHM4KY6BTZ7LSB3CD","short_pith_number":"pith:YQK2SGBH","canonical_record":{"source":{"id":"2506.22602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T19:53:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e63183e01d79e5d147683823f8f4bb46c340fe5c4785fd75c40ef40066652d92","abstract_canon_sha256":"74fb2e6e5456a4530d741db9e42d0f004870cc7d916671c39cb5a271dd86acf1"},"schema_version":"1.0"},"canonical_sha256":"c415a918271e0ece2b1e0cf3f5c83b10ef1c818c5e63831a90a9916d91831de0","source":{"kind":"arxiv","id":"2506.22602","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22602","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22602v1","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22602","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"YQK2SGBHDYHM","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"YQK2SGBHDYHM4KY6","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"YQK2SGBH","created_at":"2026-07-05T11:28:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YQK2SGBHDYHM4KY6BTZ7LSB3CD","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T19:53:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e63183e01d79e5d147683823f8f4bb46c340fe5c4785fd75c40ef40066652d92","abstract_canon_sha256":"74fb2e6e5456a4530d741db9e42d0f004870cc7d916671c39cb5a271dd86acf1"},"schema_version":"1.0"},"canonical_sha256":"c415a918271e0ece2b1e0cf3f5c83b10ef1c818c5e63831a90a9916d91831de0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:41.676825Z","signature_b64":"2LbiOmA/O7fXagF/sZpDWnDGGGpvCYlvJMB4VBaqcEjc0NHcgBZVq/yWCs6u4Dx6MHRBD2cb5GfVf4KOLXtHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c415a918271e0ece2b1e0cf3f5c83b10ef1c818c5e63831a90a9916d91831de0","last_reissued_at":"2026-07-05T11:28:41.676394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:41.676394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22602","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":"2026-07-05T11:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gKMtdONpbnco9k/+D9ufBnaz9yI4sUTK5JTPhICsOLMxtJWm0tpPkFuyBzfOF2HQL73MstpSrLzU0iBI8Tx/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:15:45.351543Z"},"content_sha256":"f5cbbd6650ec330803f8ac921eb8733faeee685fc25b496bc7af52d63309a930","schema_version":"1.0","event_id":"sha256:f5cbbd6650ec330803f8ac921eb8733faeee685fc25b496bc7af52d63309a930"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YQK2SGBHDYHM4KY6BTZ7LSB3CD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are Fast Methods Stable in Adversarially Robust Transfer Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Joshua C. Zhao, Saurabh Bagchi","submitted_at":"2025-06-27T19:53:53Z","abstract_excerpt":"Transfer learning is often used to decrease the computational cost of model training, as fine-tuning a model allows a downstream task to leverage the features learned from the pre-training dataset and quickly adapt them to a new task. This is particularly useful for achieving adversarial robustness, as adversarially training models from scratch is very computationally expensive. However, high robustness in transfer learning still requires adversarial training during the fine-tuning phase, which requires up to an order of magnitude more time than standard fine-tuning. In this work, we revisit t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22602","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.22602/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T11:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLpBj/MkzCJ678YvTUseG10mMmjDsjUWkDtwDvHBOwZotq6J/6BKDZVw50RDggOPtKdyJTaqRXvoZnbFPUvyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:15:45.352031Z"},"content_sha256":"26456b0156f3de5228c16d88a1beda36c1c5754bdf8caea866d4c5075c695eb3","schema_version":"1.0","event_id":"sha256:26456b0156f3de5228c16d88a1beda36c1c5754bdf8caea866d4c5075c695eb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQK2SGBHDYHM4KY6BTZ7LSB3CD/bundle.json","state_url":"https://pith.science/pith/YQK2SGBHDYHM4KY6BTZ7LSB3CD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQK2SGBHDYHM4KY6BTZ7LSB3CD/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":"2026-08-08T12:15:45Z","links":{"resolver":"https://pith.science/pith/YQK2SGBHDYHM4KY6BTZ7LSB3CD","bundle":"https://pith.science/pith/YQK2SGBHDYHM4KY6BTZ7LSB3CD/bundle.json","state":"https://pith.science/pith/YQK2SGBHDYHM4KY6BTZ7LSB3CD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQK2SGBHDYHM4KY6BTZ7LSB3CD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YQK2SGBHDYHM4KY6BTZ7LSB3CD","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":"74fb2e6e5456a4530d741db9e42d0f004870cc7d916671c39cb5a271dd86acf1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T19:53:53Z","title_canon_sha256":"e63183e01d79e5d147683823f8f4bb46c340fe5c4785fd75c40ef40066652d92"},"schema_version":"1.0","source":{"id":"2506.22602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22602","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22602v1","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22602","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"YQK2SGBHDYHM","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"YQK2SGBHDYHM4KY6","created_at":"2026-07-05T11:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"YQK2SGBH","created_at":"2026-07-05T11:28:41Z"}],"graph_snapshots":[{"event_id":"sha256:26456b0156f3de5228c16d88a1beda36c1c5754bdf8caea866d4c5075c695eb3","target":"graph","created_at":"2026-07-05T11:28:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.22602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer learning is often used to decrease the computational cost of model training, as fine-tuning a model allows a downstream task to leverage the features learned from the pre-training dataset and quickly adapt them to a new task. This is particularly useful for achieving adversarial robustness, as adversarially training models from scratch is very computationally expensive. However, high robustness in transfer learning still requires adversarial training during the fine-tuning phase, which requires up to an order of magnitude more time than standard fine-tuning. In this work, we revisit t","authors_text":"Joshua C. Zhao, Saurabh Bagchi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T19:53:53Z","title":"Are Fast Methods Stable in Adversarially Robust Transfer Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22602","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:f5cbbd6650ec330803f8ac921eb8733faeee685fc25b496bc7af52d63309a930","target":"record","created_at":"2026-07-05T11:28:41Z","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":"74fb2e6e5456a4530d741db9e42d0f004870cc7d916671c39cb5a271dd86acf1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T19:53:53Z","title_canon_sha256":"e63183e01d79e5d147683823f8f4bb46c340fe5c4785fd75c40ef40066652d92"},"schema_version":"1.0","source":{"id":"2506.22602","kind":"arxiv","version":1}},"canonical_sha256":"c415a918271e0ece2b1e0cf3f5c83b10ef1c818c5e63831a90a9916d91831de0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c415a918271e0ece2b1e0cf3f5c83b10ef1c818c5e63831a90a9916d91831de0","first_computed_at":"2026-07-05T11:28:41.676394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:41.676394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2LbiOmA/O7fXagF/sZpDWnDGGGpvCYlvJMB4VBaqcEjc0NHcgBZVq/yWCs6u4Dx6MHRBD2cb5GfVf4KOLXtHAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:41.676825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5cbbd6650ec330803f8ac921eb8733faeee685fc25b496bc7af52d63309a930","sha256:26456b0156f3de5228c16d88a1beda36c1c5754bdf8caea866d4c5075c695eb3"],"state_sha256":"0d02711d72051842e0081371cc482f0eb69f518c5e8ba0dea19b56ebac502bfa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9svkGxFmv7XNf2kG7FWj4wqPMNsVoqdPj5RvSVYVhmH3HBgiAXuLGc3IhGkGSo8wWN2SAWnyXLXWzbfDTX1PBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:15:45.355824Z","bundle_sha256":"20d8b06dfea662d57b1fff6d0bdfb29bd50a17f2a61282726d36321e3a195b2e"}}