{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ICBJBWXHMT6JKIHQQR6XUK3HDY","short_pith_number":"pith:ICBJBWXH","canonical_record":{"source":{"id":"2404.10370","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T08:08:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"673b512a6fb6023637ca83743e11e859349f5d824a7bba204b7e8c57a7f2cadf","abstract_canon_sha256":"c4059885a337a8e68dbf9422cf19d09e34c50ef7d3433543a20d4198be67adba"},"schema_version":"1.0"},"canonical_sha256":"408290dae764fc9520f0847d7a2b671e075d7e83e1dea7aa9f97351345bfb06f","source":{"kind":"arxiv","id":"2404.10370","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10370","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10370v4","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10370","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"pith_short_12","alias_value":"ICBJBWXHMT6J","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"pith_short_16","alias_value":"ICBJBWXHMT6JKIHQ","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"pith_short_8","alias_value":"ICBJBWXH","created_at":"2026-06-05T01:15:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ICBJBWXHMT6JKIHQQR6XUK3HDY","target":"record","payload":{"canonical_record":{"source":{"id":"2404.10370","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T08:08:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"673b512a6fb6023637ca83743e11e859349f5d824a7bba204b7e8c57a7f2cadf","abstract_canon_sha256":"c4059885a337a8e68dbf9422cf19d09e34c50ef7d3433543a20d4198be67adba"},"schema_version":"1.0"},"canonical_sha256":"408290dae764fc9520f0847d7a2b671e075d7e83e1dea7aa9f97351345bfb06f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:11.243913Z","signature_b64":"knZlmkJl0V9caJRF0wj0Qo28I7g/Z0HI1JsfLRF3gfu1jsBwCJgurC9reTf9IxQihcvmveDn3z29SWVUa+wOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"408290dae764fc9520f0847d7a2b671e075d7e83e1dea7aa9f97351345bfb06f","last_reissued_at":"2026-06-05T01:15:11.243409Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:11.243409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.10370","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P6ZBZrkvZ/CyK/TBf8CV1/0qPy2k83vde/3l0baPwOZ1mRnMeb3GmazVOGjOC2v9RRc1gdj7l0Tc7oeRPIHMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T18:30:14.535580Z"},"content_sha256":"1ca46608367572a8a3633d5b562b78751896c1a136fd0ecfcbecafeb5dd55d17","schema_version":"1.0","event_id":"sha256:1ca46608367572a8a3633d5b562b78751896c1a136fd0ecfcbecafeb5dd55d17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ICBJBWXHMT6JKIHQQR6XUK3HDY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Learning diverse features for known classes improves a model's ability to detect novel objects.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiawen Xu, Margret Keuper","submitted_at":"2024-04-16T08:08:47Z","abstract_excerpt":"Open set recognition (OSR) is a critical aspect of machine learning, addressing the challenge of detecting novel classes during inference. Within the realm of deep learning, neural classifiers trained on a closed set of data typically struggle to identify novel classes, leading to erroneous predictions. To address this issue, various heuristic methods have been proposed, allowing models to express uncertainty by stating \"I don't know.\" However, a gap in the literature remains, as there has been limited exploration of the underlying mechanisms of these methods. In this paper, we conduct an anal"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"There is a significant correlation between learning diverse discriminative features and enhancing OSR performance; a novel approach leveraging feature diversity demonstrates substantial improvement over state-of-the-art on a standard OSR testbench.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The observed correlation between feature diversity and OSR performance is causal and can be reliably increased by the proposed training procedure without introducing confounding effects on known-class accuracy or benchmark-specific artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Diverse discriminative features correlate with and can be leveraged to improve open set recognition performance over prior methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Learning diverse features for known classes improves a model's ability to detect novel objects.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c0af4e481980d17c04744d32c5c743b997b8b1a2ccb05770197f6ec1e763613f"},"source":{"id":"2404.10370","kind":"arxiv","version":4},"verdict":{"id":"4c881d27-d34b-4077-8dd9-d981c46df001","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-24T02:27:47.676825Z","strongest_claim":"There is a significant correlation between learning diverse discriminative features and enhancing OSR performance; a novel approach leveraging feature diversity demonstrates substantial improvement over state-of-the-art on a standard OSR testbench.","one_line_summary":"Diverse discriminative features correlate with and can be leveraged to improve open set recognition performance over prior methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The observed correlation between feature diversity and OSR performance is causal and can be reliably increased by the proposed training procedure without introducing confounding effects on known-class accuracy or benchmark-specific artifacts.","pith_extraction_headline":"Learning diverse features for known classes improves a model's ability to detect novel objects."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.10370/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":"4c881d27-d34b-4077-8dd9-d981c46df001"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q2QKbOcsNat7LAomMOWgHdXv2Z+4jPQlp6ITjW/pAABNppRhQWRqgyUAK6kSkTWDUP/3WXVwMEbEcixbOf0oDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T18:30:14.536645Z"},"content_sha256":"0dbec5931c10e24b1d1c0b7f01d4856d448da4eb018db567d612dce1c441e86b","schema_version":"1.0","event_id":"sha256:0dbec5931c10e24b1d1c0b7f01d4856d448da4eb018db567d612dce1c441e86b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICBJBWXHMT6JKIHQQR6XUK3HDY/bundle.json","state_url":"https://pith.science/pith/ICBJBWXHMT6JKIHQQR6XUK3HDY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICBJBWXHMT6JKIHQQR6XUK3HDY/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":"2026-06-11T18:30:14Z","links":{"resolver":"https://pith.science/pith/ICBJBWXHMT6JKIHQQR6XUK3HDY","bundle":"https://pith.science/pith/ICBJBWXHMT6JKIHQQR6XUK3HDY/bundle.json","state":"https://pith.science/pith/ICBJBWXHMT6JKIHQQR6XUK3HDY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICBJBWXHMT6JKIHQQR6XUK3HDY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ICBJBWXHMT6JKIHQQR6XUK3HDY","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":"c4059885a337a8e68dbf9422cf19d09e34c50ef7d3433543a20d4198be67adba","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T08:08:47Z","title_canon_sha256":"673b512a6fb6023637ca83743e11e859349f5d824a7bba204b7e8c57a7f2cadf"},"schema_version":"1.0","source":{"id":"2404.10370","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10370","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10370v4","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10370","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"pith_short_12","alias_value":"ICBJBWXHMT6J","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"pith_short_16","alias_value":"ICBJBWXHMT6JKIHQ","created_at":"2026-06-05T01:15:11Z"},{"alias_kind":"pith_short_8","alias_value":"ICBJBWXH","created_at":"2026-06-05T01:15:11Z"}],"graph_snapshots":[{"event_id":"sha256:0dbec5931c10e24b1d1c0b7f01d4856d448da4eb018db567d612dce1c441e86b","target":"graph","created_at":"2026-06-05T01:15:11Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"There is a significant correlation between learning diverse discriminative features and enhancing OSR performance; a novel approach leveraging feature diversity demonstrates substantial improvement over state-of-the-art on a standard OSR testbench."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The observed correlation between feature diversity and OSR performance is causal and can be reliably increased by the proposed training procedure without introducing confounding effects on known-class accuracy or benchmark-specific artifacts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Diverse discriminative features correlate with and can be leveraged to improve open set recognition performance over prior methods."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Learning diverse features for known classes improves a model's ability to detect novel objects."}],"snapshot_sha256":"c0af4e481980d17c04744d32c5c743b997b8b1a2ccb05770197f6ec1e763613f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.10370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open set recognition (OSR) is a critical aspect of machine learning, addressing the challenge of detecting novel classes during inference. Within the realm of deep learning, neural classifiers trained on a closed set of data typically struggle to identify novel classes, leading to erroneous predictions. To address this issue, various heuristic methods have been proposed, allowing models to express uncertainty by stating \"I don't know.\" However, a gap in the literature remains, as there has been limited exploration of the underlying mechanisms of these methods. In this paper, we conduct an anal","authors_text":"Jiawen Xu, Margret Keuper","cross_cats":["cs.LG"],"headline":"Learning diverse features for known classes improves a model's ability to detect novel objects.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T08:08:47Z","title":"Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10370","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-24T02:27:47.676825Z","id":"4c881d27-d34b-4077-8dd9-d981c46df001","model_set":{"reader":"grok-4.3"},"one_line_summary":"Diverse discriminative features correlate with and can be leveraged to improve open set recognition performance over prior methods.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Learning diverse features for known classes improves a model's ability to detect novel objects.","strongest_claim":"There is a significant correlation between learning diverse discriminative features and enhancing OSR performance; a novel approach leveraging feature diversity demonstrates substantial improvement over state-of-the-art on a standard OSR testbench.","weakest_assumption":"The observed correlation between feature diversity and OSR performance is causal and can be reliably increased by the proposed training procedure without introducing confounding effects on known-class accuracy or benchmark-specific artifacts."}},"verdict_id":"4c881d27-d34b-4077-8dd9-d981c46df001"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1ca46608367572a8a3633d5b562b78751896c1a136fd0ecfcbecafeb5dd55d17","target":"record","created_at":"2026-06-05T01:15:11Z","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":"c4059885a337a8e68dbf9422cf19d09e34c50ef7d3433543a20d4198be67adba","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T08:08:47Z","title_canon_sha256":"673b512a6fb6023637ca83743e11e859349f5d824a7bba204b7e8c57a7f2cadf"},"schema_version":"1.0","source":{"id":"2404.10370","kind":"arxiv","version":4}},"canonical_sha256":"408290dae764fc9520f0847d7a2b671e075d7e83e1dea7aa9f97351345bfb06f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"408290dae764fc9520f0847d7a2b671e075d7e83e1dea7aa9f97351345bfb06f","first_computed_at":"2026-06-05T01:15:11.243409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:11.243409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"knZlmkJl0V9caJRF0wj0Qo28I7g/Z0HI1JsfLRF3gfu1jsBwCJgurC9reTf9IxQihcvmveDn3z29SWVUa+wOAQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:11.243913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10370","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ca46608367572a8a3633d5b562b78751896c1a136fd0ecfcbecafeb5dd55d17","sha256:0dbec5931c10e24b1d1c0b7f01d4856d448da4eb018db567d612dce1c441e86b"],"state_sha256":"60215216ec0beeeff79da180a9a7dbccd3d4cfb667dea2353bfe84fa80c43638"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YHHAyL7fdnEdqPs9RQUozoJrBxXtvbc5GGZmCgUT9Y/21uNdDVaRQ21uLSG4eMoAuymJrRVW8/AbWEI0saYaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T18:30:14.541518Z","bundle_sha256":"148cc6afcaf427dd288f85dc28824437d95d52bf2bfb418e2636fe451c86389a"}}