{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5UPLRKW6IMMQQYIIZ2PXGY5Y3J","short_pith_number":"pith:5UPLRKW6","canonical_record":{"source":{"id":"2207.08210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-17T16:02:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"37c102db637814ffb60feda72a74171e466ae985a03a47eb9ca6b7cd27ae4b11","abstract_canon_sha256":"5605539af254594c7daf78d23df63af76759af0f887489ba9c82ff71345b893e"},"schema_version":"1.0"},"canonical_sha256":"ed1eb8aade4319086108ce9f7363b8da54684a77e5f34b46e12f7438f9211702","source":{"kind":"arxiv","id":"2207.08210","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.08210","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2207.08210v1","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08210","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"5UPLRKW6IMMQ","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"5UPLRKW6IMMQQYII","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"5UPLRKW6","created_at":"2026-07-05T04:41:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5UPLRKW6IMMQQYIIZ2PXGY5Y3J","target":"record","payload":{"canonical_record":{"source":{"id":"2207.08210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-17T16:02:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"37c102db637814ffb60feda72a74171e466ae985a03a47eb9ca6b7cd27ae4b11","abstract_canon_sha256":"5605539af254594c7daf78d23df63af76759af0f887489ba9c82ff71345b893e"},"schema_version":"1.0"},"canonical_sha256":"ed1eb8aade4319086108ce9f7363b8da54684a77e5f34b46e12f7438f9211702","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:02.074559Z","signature_b64":"njfj2iU9IMjUqnLCooC4QGrAh7T05/aN3IWouCScV1d5Ch5FI2T38qmuzi1zQAuYTbgIAfxsBVzTETo7IYXkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed1eb8aade4319086108ce9f7363b8da54684a77e5f34b46e12f7438f9211702","last_reissued_at":"2026-07-05T04:41:02.074155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:02.074155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.08210","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":"2026-07-05T04:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pybyzpN9OQ9Tl3vXz/Pf8VvucTMEgWkmzzOIVuJ8VLQbc0LPQLi6tklGfLrWbHkDI4iFxtqrI0QqxXg1XUxWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:03.085763Z"},"content_sha256":"aecb5a10ad60b40ddf9b064e055ed39b0cfcb3160d8e252674851b70409304ba","schema_version":"1.0","event_id":"sha256:aecb5a10ad60b40ddf9b064e055ed39b0cfcb3160d8e252674851b70409304ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5UPLRKW6IMMQQYIIZ2PXGY5Y3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Simple Test-Time Method for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Da Li, Ke Fan, Qian Yu, Yanwei Fu, Yikai Wang","submitted_at":"2022-07-17T16:02:58Z","abstract_excerpt":"Neural networks are known to produce over-confident predictions on input images, even when these images are out-of-distribution (OOD) samples. This limits the applications of neural network models in real-world scenarios, where OOD samples exist. Many existing approaches identify the OOD instances via exploiting various cues, such as finding irregular patterns in the feature space, logits space, gradient space or the raw space of images. In contrast, this paper proposes a simple Test-time Linear Training (ETLT) method for OOD detection. Empirically, we find that the probabilities of input imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08210","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/2207.08210/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":"2026-07-05T04:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zE3F27OgpLoW8pDQk3uvu2r6FMxrsNil2zlXvgQg+rPVkBRu6pw8W7bCd0e4jopuzI6dw/MVKL+D/+k9hhWLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:03.086515Z"},"content_sha256":"2c8b4715863493955822c82501fe24c95fb9a857d9cfcdc14b2f542fba4475a5","schema_version":"1.0","event_id":"sha256:2c8b4715863493955822c82501fe24c95fb9a857d9cfcdc14b2f542fba4475a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UPLRKW6IMMQQYIIZ2PXGY5Y3J/bundle.json","state_url":"https://pith.science/pith/5UPLRKW6IMMQQYIIZ2PXGY5Y3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UPLRKW6IMMQQYIIZ2PXGY5Y3J/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":"2026-08-05T10:32:03Z","links":{"resolver":"https://pith.science/pith/5UPLRKW6IMMQQYIIZ2PXGY5Y3J","bundle":"https://pith.science/pith/5UPLRKW6IMMQQYIIZ2PXGY5Y3J/bundle.json","state":"https://pith.science/pith/5UPLRKW6IMMQQYIIZ2PXGY5Y3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UPLRKW6IMMQQYIIZ2PXGY5Y3J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5UPLRKW6IMMQQYIIZ2PXGY5Y3J","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":"5605539af254594c7daf78d23df63af76759af0f887489ba9c82ff71345b893e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-17T16:02:58Z","title_canon_sha256":"37c102db637814ffb60feda72a74171e466ae985a03a47eb9ca6b7cd27ae4b11"},"schema_version":"1.0","source":{"id":"2207.08210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.08210","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2207.08210v1","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08210","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"5UPLRKW6IMMQ","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"5UPLRKW6IMMQQYII","created_at":"2026-07-05T04:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"5UPLRKW6","created_at":"2026-07-05T04:41:02Z"}],"graph_snapshots":[{"event_id":"sha256:2c8b4715863493955822c82501fe24c95fb9a857d9cfcdc14b2f542fba4475a5","target":"graph","created_at":"2026-07-05T04:41:02Z","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/2207.08210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks are known to produce over-confident predictions on input images, even when these images are out-of-distribution (OOD) samples. This limits the applications of neural network models in real-world scenarios, where OOD samples exist. Many existing approaches identify the OOD instances via exploiting various cues, such as finding irregular patterns in the feature space, logits space, gradient space or the raw space of images. In contrast, this paper proposes a simple Test-time Linear Training (ETLT) method for OOD detection. Empirically, we find that the probabilities of input imag","authors_text":"Da Li, Ke Fan, Qian Yu, Yanwei Fu, Yikai Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-17T16:02:58Z","title":"A Simple Test-Time Method for Out-of-Distribution Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08210","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:aecb5a10ad60b40ddf9b064e055ed39b0cfcb3160d8e252674851b70409304ba","target":"record","created_at":"2026-07-05T04:41:02Z","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":"5605539af254594c7daf78d23df63af76759af0f887489ba9c82ff71345b893e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-17T16:02:58Z","title_canon_sha256":"37c102db637814ffb60feda72a74171e466ae985a03a47eb9ca6b7cd27ae4b11"},"schema_version":"1.0","source":{"id":"2207.08210","kind":"arxiv","version":1}},"canonical_sha256":"ed1eb8aade4319086108ce9f7363b8da54684a77e5f34b46e12f7438f9211702","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed1eb8aade4319086108ce9f7363b8da54684a77e5f34b46e12f7438f9211702","first_computed_at":"2026-07-05T04:41:02.074155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:41:02.074155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"njfj2iU9IMjUqnLCooC4QGrAh7T05/aN3IWouCScV1d5Ch5FI2T38qmuzi1zQAuYTbgIAfxsBVzTETo7IYXkBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:41:02.074559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.08210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aecb5a10ad60b40ddf9b064e055ed39b0cfcb3160d8e252674851b70409304ba","sha256:2c8b4715863493955822c82501fe24c95fb9a857d9cfcdc14b2f542fba4475a5"],"state_sha256":"ae202fc84eb4fc2d60f387bb7ad5cad26c06cbdeca2c6a85d14005a88414e029"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEJePbQ7bmi140yjRkQLeXyQETZ79jBjt3ygzlQLcITu5/SkLzIhyG5tU1JOpNGYyZr84ZoqrpYsBVtlilF+Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:32:03.092028Z","bundle_sha256":"9a5f92a708c99c7bcb6b645b895deb18bf52637640c20a56a1c85881a5af7a7f"}}