{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:NAPXL5IWHRD65O7KOKWQQ4KYKV","short_pith_number":"pith:NAPXL5IW","canonical_record":{"source":{"id":"1707.07013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-21T18:12:15Z","cross_cats_sorted":[],"title_canon_sha256":"15522c591fcf265ef56e02991fa35f89913d8a1b9b178bfb74485cca328bc87b","abstract_canon_sha256":"d171c8ff375040f0835e982e955ba387665a791b29a262a73af09a750569e609"},"schema_version":"1.0"},"canonical_sha256":"681f75f5163c47eebbea72ad087158557a95c174be63eb1cc23b920678b2382d","source":{"kind":"arxiv","id":"1707.07013","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.07013","created_at":"2026-05-18T00:39:45Z"},{"alias_kind":"arxiv_version","alias_value":"1707.07013v1","created_at":"2026-05-18T00:39:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07013","created_at":"2026-05-18T00:39:45Z"},{"alias_kind":"pith_short_12","alias_value":"NAPXL5IWHRD6","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"NAPXL5IWHRD65O7K","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"NAPXL5IW","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:NAPXL5IWHRD65O7KOKWQQ4KYKV","target":"record","payload":{"canonical_record":{"source":{"id":"1707.07013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-21T18:12:15Z","cross_cats_sorted":[],"title_canon_sha256":"15522c591fcf265ef56e02991fa35f89913d8a1b9b178bfb74485cca328bc87b","abstract_canon_sha256":"d171c8ff375040f0835e982e955ba387665a791b29a262a73af09a750569e609"},"schema_version":"1.0"},"canonical_sha256":"681f75f5163c47eebbea72ad087158557a95c174be63eb1cc23b920678b2382d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:45.572368Z","signature_b64":"gFprxJkXB0rPTgFXOdDUrvsvLdO47zgJ9aMpFqiH+zVo4GP1LPKv2XwWJ6g1LoQD/aa/p9PjDQYYOJtEuNTmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"681f75f5163c47eebbea72ad087158557a95c174be63eb1cc23b920678b2382d","last_reissued_at":"2026-05-18T00:39:45.571810Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:45.571810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.07013","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":"2026-05-18T00:39:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/CUsI+Sd5/4HVUh/vjQNYT/owGfqt+lUZqK5r+xWL5oTqrtvKydIUkhi57PFZkssYF9RtbwdkwrRvE912rYNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T17:00:32.344559Z"},"content_sha256":"e55acae7518308fd2701fc2df2742f8374d82375279be430191424a4fd23e509","schema_version":"1.0","event_id":"sha256:e55acae7518308fd2701fc2df2742f8374d82375279be430191424a4fd23e509"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:NAPXL5IWHRD65O7KOKWQQ4KYKV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Confidence estimation in Deep Neural networks via density modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akshayvarun Subramanya, R.Venkatesh Babu, Suraj Srinivas","submitted_at":"2017-07-21T18:12:15Z","abstract_excerpt":"State-of-the-art Deep Neural Networks can be easily fooled into providing incorrect high-confidence predictions for images with small amounts of adversarial noise. Does this expose a flaw with deep neural networks, or do we simply need a better way to estimate confidence? In this paper we consider the problem of accurately estimating predictive confidence. We formulate this problem as that of density modelling, and show how traditional methods such as softmax produce poor estimates. To address this issue, we propose a novel confidence measure based on density modelling approaches. We test thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07013","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":"2026-05-18T00:39:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsdcHdKUrFUGHt8KQF32MP0z17UANPDEPD+JSlO2uINn+2tniuWHFVrKl1wCBlkL/dUQFHmkCIJa9wW1KhI+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T17:00:32.345226Z"},"content_sha256":"dec417d81a97943f06ad8f324016c0d17c8ddf5e1a48a3dcec4c319d401acd48","schema_version":"1.0","event_id":"sha256:dec417d81a97943f06ad8f324016c0d17c8ddf5e1a48a3dcec4c319d401acd48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NAPXL5IWHRD65O7KOKWQQ4KYKV/bundle.json","state_url":"https://pith.science/pith/NAPXL5IWHRD65O7KOKWQQ4KYKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NAPXL5IWHRD65O7KOKWQQ4KYKV/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":"2026-08-16T17:00:32Z","links":{"resolver":"https://pith.science/pith/NAPXL5IWHRD65O7KOKWQQ4KYKV","bundle":"https://pith.science/pith/NAPXL5IWHRD65O7KOKWQQ4KYKV/bundle.json","state":"https://pith.science/pith/NAPXL5IWHRD65O7KOKWQQ4KYKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NAPXL5IWHRD65O7KOKWQQ4KYKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:NAPXL5IWHRD65O7KOKWQQ4KYKV","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":"d171c8ff375040f0835e982e955ba387665a791b29a262a73af09a750569e609","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-21T18:12:15Z","title_canon_sha256":"15522c591fcf265ef56e02991fa35f89913d8a1b9b178bfb74485cca328bc87b"},"schema_version":"1.0","source":{"id":"1707.07013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.07013","created_at":"2026-05-18T00:39:45Z"},{"alias_kind":"arxiv_version","alias_value":"1707.07013v1","created_at":"2026-05-18T00:39:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07013","created_at":"2026-05-18T00:39:45Z"},{"alias_kind":"pith_short_12","alias_value":"NAPXL5IWHRD6","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"NAPXL5IWHRD65O7K","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"NAPXL5IW","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:dec417d81a97943f06ad8f324016c0d17c8ddf5e1a48a3dcec4c319d401acd48","target":"graph","created_at":"2026-05-18T00:39:45Z","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":"State-of-the-art Deep Neural Networks can be easily fooled into providing incorrect high-confidence predictions for images with small amounts of adversarial noise. Does this expose a flaw with deep neural networks, or do we simply need a better way to estimate confidence? In this paper we consider the problem of accurately estimating predictive confidence. We formulate this problem as that of density modelling, and show how traditional methods such as softmax produce poor estimates. To address this issue, we propose a novel confidence measure based on density modelling approaches. We test thes","authors_text":"Akshayvarun Subramanya, R.Venkatesh Babu, Suraj Srinivas","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-21T18:12:15Z","title":"Confidence estimation in Deep Neural networks via density modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07013","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:e55acae7518308fd2701fc2df2742f8374d82375279be430191424a4fd23e509","target":"record","created_at":"2026-05-18T00:39:45Z","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":"d171c8ff375040f0835e982e955ba387665a791b29a262a73af09a750569e609","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-21T18:12:15Z","title_canon_sha256":"15522c591fcf265ef56e02991fa35f89913d8a1b9b178bfb74485cca328bc87b"},"schema_version":"1.0","source":{"id":"1707.07013","kind":"arxiv","version":1}},"canonical_sha256":"681f75f5163c47eebbea72ad087158557a95c174be63eb1cc23b920678b2382d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"681f75f5163c47eebbea72ad087158557a95c174be63eb1cc23b920678b2382d","first_computed_at":"2026-05-18T00:39:45.571810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:45.571810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gFprxJkXB0rPTgFXOdDUrvsvLdO47zgJ9aMpFqiH+zVo4GP1LPKv2XwWJ6g1LoQD/aa/p9PjDQYYOJtEuNTmAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:45.572368Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.07013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e55acae7518308fd2701fc2df2742f8374d82375279be430191424a4fd23e509","sha256:dec417d81a97943f06ad8f324016c0d17c8ddf5e1a48a3dcec4c319d401acd48"],"state_sha256":"2462f666744b1c7b6ab94adb666569c15c8f8f5a708b59e2989b7eb5eb38820e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TtapZL+BKl4BnyKZYX5Yb5VoVKCOzOgtqUs7Ap/e0JylKNGfZP9dO41VPV4mhHhL2wGqwwJnEDNcJwNBX8BtCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T17:00:32.351086Z","bundle_sha256":"bde83f67c37c5c6219ceeff57922dda89d7022d282f4bb766f0d9c1b8c90d603"}}