{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:V3JGOSEDLPZCNQHRLEVKSOXXSC","short_pith_number":"pith:V3JGOSED","canonical_record":{"source":{"id":"2105.07107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-15T00:46:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f4a40027e7d924f20aad708456b90c567c545541f6afa3564648104b7d7ef77","abstract_canon_sha256":"833da2685725ea01705ed8249ee968ee5c155f24e83915adf6ca35194d651bcf"},"schema_version":"1.0"},"canonical_sha256":"aed26748835bf226c0f1592aa93af7908fb59a845e39cd35dba2e4b47209896c","source":{"kind":"arxiv","id":"2105.07107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.07107","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"arxiv_version","alias_value":"2105.07107v1","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07107","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"pith_short_12","alias_value":"V3JGOSEDLPZC","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"pith_short_16","alias_value":"V3JGOSEDLPZCNQHR","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"pith_short_8","alias_value":"V3JGOSED","created_at":"2026-07-05T02:40:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:V3JGOSEDLPZCNQHRLEVKSOXXSC","target":"record","payload":{"canonical_record":{"source":{"id":"2105.07107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-15T00:46:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f4a40027e7d924f20aad708456b90c567c545541f6afa3564648104b7d7ef77","abstract_canon_sha256":"833da2685725ea01705ed8249ee968ee5c155f24e83915adf6ca35194d651bcf"},"schema_version":"1.0"},"canonical_sha256":"aed26748835bf226c0f1592aa93af7908fb59a845e39cd35dba2e4b47209896c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:37.056274Z","signature_b64":"t57kJ7+L+ml4wxQt8TZQdmGo2UdL43hlgrpWHa5T7R/4L+vgLj+Pg/VZhHjfYiWeVsukAWCyhsmpP3VX27lcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aed26748835bf226c0f1592aa93af7908fb59a845e39cd35dba2e4b47209896c","last_reissued_at":"2026-07-05T02:40:37.055880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:37.055880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.07107","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":"2026-07-05T02:40:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l/HXTZ2f6dQ2Cz6aa5ZrHIbuuckVLgln/lRWrujUEfmyvTW/+rBtYMhp4RQdkS91AddKyQPlUKvFWPqqizAIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T03:54:47.132301Z"},"content_sha256":"7ff679c7a766fede3dcc2ad946c1f2ff14827bc362bf5c75366edd798581cb52","schema_version":"1.0","event_id":"sha256:7ff679c7a766fede3dcc2ad946c1f2ff14827bc362bf5c75366edd798581cb52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:V3JGOSEDLPZCNQHRLEVKSOXXSC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Effective Baseline for Robustness to Distributional Shift","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gopinath Chennupati, Jeff Bilmes, Sayera Dhaubhadel, Sunil Thulasidasan, Sushil Thapa, Tanmoy Bhattacharya","submitted_at":"2021-05-15T00:46:11Z","abstract_excerpt":"Refraining from confidently predicting when faced with categories of inputs different from those seen during training is an important requirement for the safe deployment of deep learning systems. While simple to state, this has been a particularly challenging problem in deep learning, where models often end up making overconfident predictions in such situations. In this work we present a simple, but highly effective approach to deal with out-of-distribution detection that uses the principle of abstention: when encountering a sample from an unseen class, the desired behavior is to abstain from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07107","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/2105.07107/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":"2026-07-05T02:40:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b/iXW9L0Mx9dwK1XEiQIE/SmLLUJuRBCWUbU3kzZXZG50bX6p+qk1lu2e6MQh7zDHJD7vLno46uaNXdzSssRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T03:54:47.132915Z"},"content_sha256":"a91cabe73f0247649ca8ef0ed372c55212898a9763cbc38a552f2a52df55f54e","schema_version":"1.0","event_id":"sha256:a91cabe73f0247649ca8ef0ed372c55212898a9763cbc38a552f2a52df55f54e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V3JGOSEDLPZCNQHRLEVKSOXXSC/bundle.json","state_url":"https://pith.science/pith/V3JGOSEDLPZCNQHRLEVKSOXXSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V3JGOSEDLPZCNQHRLEVKSOXXSC/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":"2026-08-23T03:54:47Z","links":{"resolver":"https://pith.science/pith/V3JGOSEDLPZCNQHRLEVKSOXXSC","bundle":"https://pith.science/pith/V3JGOSEDLPZCNQHRLEVKSOXXSC/bundle.json","state":"https://pith.science/pith/V3JGOSEDLPZCNQHRLEVKSOXXSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V3JGOSEDLPZCNQHRLEVKSOXXSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:V3JGOSEDLPZCNQHRLEVKSOXXSC","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":"833da2685725ea01705ed8249ee968ee5c155f24e83915adf6ca35194d651bcf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-15T00:46:11Z","title_canon_sha256":"7f4a40027e7d924f20aad708456b90c567c545541f6afa3564648104b7d7ef77"},"schema_version":"1.0","source":{"id":"2105.07107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.07107","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"arxiv_version","alias_value":"2105.07107v1","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07107","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"pith_short_12","alias_value":"V3JGOSEDLPZC","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"pith_short_16","alias_value":"V3JGOSEDLPZCNQHR","created_at":"2026-07-05T02:40:37Z"},{"alias_kind":"pith_short_8","alias_value":"V3JGOSED","created_at":"2026-07-05T02:40:37Z"}],"graph_snapshots":[{"event_id":"sha256:a91cabe73f0247649ca8ef0ed372c55212898a9763cbc38a552f2a52df55f54e","target":"graph","created_at":"2026-07-05T02:40:37Z","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/2105.07107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Refraining from confidently predicting when faced with categories of inputs different from those seen during training is an important requirement for the safe deployment of deep learning systems. While simple to state, this has been a particularly challenging problem in deep learning, where models often end up making overconfident predictions in such situations. In this work we present a simple, but highly effective approach to deal with out-of-distribution detection that uses the principle of abstention: when encountering a sample from an unseen class, the desired behavior is to abstain from ","authors_text":"Gopinath Chennupati, Jeff Bilmes, Sayera Dhaubhadel, Sunil Thulasidasan, Sushil Thapa, Tanmoy Bhattacharya","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-15T00:46:11Z","title":"An Effective Baseline for Robustness to Distributional Shift"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07107","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":"sha256:7ff679c7a766fede3dcc2ad946c1f2ff14827bc362bf5c75366edd798581cb52","target":"record","created_at":"2026-07-05T02:40:37Z","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":"833da2685725ea01705ed8249ee968ee5c155f24e83915adf6ca35194d651bcf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-15T00:46:11Z","title_canon_sha256":"7f4a40027e7d924f20aad708456b90c567c545541f6afa3564648104b7d7ef77"},"schema_version":"1.0","source":{"id":"2105.07107","kind":"arxiv","version":1}},"canonical_sha256":"aed26748835bf226c0f1592aa93af7908fb59a845e39cd35dba2e4b47209896c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aed26748835bf226c0f1592aa93af7908fb59a845e39cd35dba2e4b47209896c","first_computed_at":"2026-07-05T02:40:37.055880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:37.055880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t57kJ7+L+ml4wxQt8TZQdmGo2UdL43hlgrpWHa5T7R/4L+vgLj+Pg/VZhHjfYiWeVsukAWCyhsmpP3VX27lcCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:37.056274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.07107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ff679c7a766fede3dcc2ad946c1f2ff14827bc362bf5c75366edd798581cb52","sha256:a91cabe73f0247649ca8ef0ed372c55212898a9763cbc38a552f2a52df55f54e"],"state_sha256":"8fc991b44f4920b4871368899b1bbc96c4c28c65706c3228c9037e23e0da6e2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wxdz79gFoMxWvfELkEM9F7GpZ8tIX1iIemlTkABXzp5cygu03p91v64IclYmVm67N7LyQsoLmTYFxQxH707dAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T03:54:47.138220Z","bundle_sha256":"bc28dbf17981d15f144c24e5dd264e43a6a8f0417b9a2629a58d3670904212d5"}}