{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZR2F6V3CJ5U3TLYULFGMT2I3RI","short_pith_number":"pith:ZR2F6V3C","canonical_record":{"source":{"id":"1910.06893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T16:07:34Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"8e2666415e722154999eee45545a7a2f1ddcbc82661be53db111bbef0432df5c","abstract_canon_sha256":"51085b96afe112cc7189fee327a965d7267e71bffcb6c91e5269ba3ac43ad33d"},"schema_version":"1.0"},"canonical_sha256":"cc745f57624f69b9af14594cc9e91b8a35ba27374c39e1400bba78cf0cfa6843","source":{"kind":"arxiv","id":"1910.06893","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.06893","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"1910.06893v1","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06893","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZR2F6V3CJ5U3","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZR2F6V3CJ5U3TLYU","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZR2F6V3C","created_at":"2026-07-05T00:12:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZR2F6V3CJ5U3TLYULFGMT2I3RI","target":"record","payload":{"canonical_record":{"source":{"id":"1910.06893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T16:07:34Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"8e2666415e722154999eee45545a7a2f1ddcbc82661be53db111bbef0432df5c","abstract_canon_sha256":"51085b96afe112cc7189fee327a965d7267e71bffcb6c91e5269ba3ac43ad33d"},"schema_version":"1.0"},"canonical_sha256":"cc745f57624f69b9af14594cc9e91b8a35ba27374c39e1400bba78cf0cfa6843","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:12:16.388968Z","signature_b64":"3NDz+PiupTuBiO8Tvw8S4t75spxWoGV0J1Z9czk8OtdT0RfND3jjmM3U+c4oc9E0RAH5rVRkU6uS1H5XvBAmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc745f57624f69b9af14594cc9e91b8a35ba27374c39e1400bba78cf0cfa6843","last_reissued_at":"2026-07-05T00:12:16.388613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:12:16.388613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.06893","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":"2026-07-05T00:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yKI+jiQhxcpA6XZLJLfCCKo6z77MBN4l6sFlcv1UCfKRe6q5Q3IehBBnwD1NTt4QD96gwN7BcFfvU289ytXoAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:08:52.307278Z"},"content_sha256":"43a49181a26d656d0b9c1d5ac7adcabe1c2ee12356829b8aaa3847c252cffe4a","schema_version":"1.0","event_id":"sha256:43a49181a26d656d0b9c1d5ac7adcabe1c2ee12356829b8aaa3847c252cffe4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZR2F6V3CJ5U3TLYULFGMT2I3RI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting robust and accurate features via a robust information bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ankit Pensia, Po-Ling Loh, Varun Jog","submitted_at":"2019-10-15T16:07:34Z","abstract_excerpt":"We propose a novel strategy for extracting features in supervised learning that can be used to construct a classifier which is more robust to small perturbations in the input space. Our method builds upon the idea of the information bottleneck by introducing an additional penalty term that encourages the Fisher information of the extracted features to be small, when parametrized by the inputs. By tuning the regularization parameter, we can explicitly trade off the opposing desiderata of robustness and accuracy when constructing a classifier. We derive the optimal solution to the robust informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06893","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/1910.06893/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":"2026-07-05T00:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8uqPVYH+7To7Z/mT5THyQ52ox0KmZgJH5PldGQ0a/qT3v3ONtShfWiViTfHDuW8hXn+kbbiHw77cLo9b8onDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:08:52.307822Z"},"content_sha256":"efab4705916407d21a7ce0608859659ed0528aed0d25c0d961310ab2cd818502","schema_version":"1.0","event_id":"sha256:efab4705916407d21a7ce0608859659ed0528aed0d25c0d961310ab2cd818502"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZR2F6V3CJ5U3TLYULFGMT2I3RI/bundle.json","state_url":"https://pith.science/pith/ZR2F6V3CJ5U3TLYULFGMT2I3RI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZR2F6V3CJ5U3TLYULFGMT2I3RI/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":"2026-08-16T15:08:52Z","links":{"resolver":"https://pith.science/pith/ZR2F6V3CJ5U3TLYULFGMT2I3RI","bundle":"https://pith.science/pith/ZR2F6V3CJ5U3TLYULFGMT2I3RI/bundle.json","state":"https://pith.science/pith/ZR2F6V3CJ5U3TLYULFGMT2I3RI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZR2F6V3CJ5U3TLYULFGMT2I3RI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZR2F6V3CJ5U3TLYULFGMT2I3RI","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":"51085b96afe112cc7189fee327a965d7267e71bffcb6c91e5269ba3ac43ad33d","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T16:07:34Z","title_canon_sha256":"8e2666415e722154999eee45545a7a2f1ddcbc82661be53db111bbef0432df5c"},"schema_version":"1.0","source":{"id":"1910.06893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.06893","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"1910.06893v1","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06893","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZR2F6V3CJ5U3","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZR2F6V3CJ5U3TLYU","created_at":"2026-07-05T00:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZR2F6V3C","created_at":"2026-07-05T00:12:16Z"}],"graph_snapshots":[{"event_id":"sha256:efab4705916407d21a7ce0608859659ed0528aed0d25c0d961310ab2cd818502","target":"graph","created_at":"2026-07-05T00:12:16Z","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/1910.06893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel strategy for extracting features in supervised learning that can be used to construct a classifier which is more robust to small perturbations in the input space. Our method builds upon the idea of the information bottleneck by introducing an additional penalty term that encourages the Fisher information of the extracted features to be small, when parametrized by the inputs. By tuning the regularization parameter, we can explicitly trade off the opposing desiderata of robustness and accuracy when constructing a classifier. We derive the optimal solution to the robust informa","authors_text":"Ankit Pensia, Po-Ling Loh, Varun Jog","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T16:07:34Z","title":"Extracting robust and accurate features via a robust information bottleneck"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06893","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":"sha256:43a49181a26d656d0b9c1d5ac7adcabe1c2ee12356829b8aaa3847c252cffe4a","target":"record","created_at":"2026-07-05T00:12:16Z","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":"51085b96afe112cc7189fee327a965d7267e71bffcb6c91e5269ba3ac43ad33d","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T16:07:34Z","title_canon_sha256":"8e2666415e722154999eee45545a7a2f1ddcbc82661be53db111bbef0432df5c"},"schema_version":"1.0","source":{"id":"1910.06893","kind":"arxiv","version":1}},"canonical_sha256":"cc745f57624f69b9af14594cc9e91b8a35ba27374c39e1400bba78cf0cfa6843","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc745f57624f69b9af14594cc9e91b8a35ba27374c39e1400bba78cf0cfa6843","first_computed_at":"2026-07-05T00:12:16.388613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:12:16.388613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3NDz+PiupTuBiO8Tvw8S4t75spxWoGV0J1Z9czk8OtdT0RfND3jjmM3U+c4oc9E0RAH5rVRkU6uS1H5XvBAmAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:12:16.388968Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.06893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43a49181a26d656d0b9c1d5ac7adcabe1c2ee12356829b8aaa3847c252cffe4a","sha256:efab4705916407d21a7ce0608859659ed0528aed0d25c0d961310ab2cd818502"],"state_sha256":"d17cde2da8c07efb786d940691d2a5195a087749733e2ae432fd15017d19ec6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"avNttOXh75vLU8rjzF/PvDWqwUFK3IB//nPj6HIKCIfTGNHEg/W5dVypT3PFXlqorUxH86MOeIq2k6sNMBylDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T15:08:52.313325Z","bundle_sha256":"b508fa8b43cf08a9fb347b4d57b83818095930f1b20d4be2a73a79046e07b93d"}}