{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EW6CE667F2F6OWVLPDAJJBEFX5","short_pith_number":"pith:EW6CE667","canonical_record":{"source":{"id":"2607.17857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T11:56:56Z","cross_cats_sorted":[],"title_canon_sha256":"6f4c0552c1f37b7abdfce8a9d3b1ccf5b3b7ddea95e0858938194e756d400e5b","abstract_canon_sha256":"0c983541b264657adc6a1082233bd88f9003b2d8b6d155afa748bc4608804271"},"schema_version":"1.0"},"canonical_sha256":"25bc227bdf2e8be75aab78c0948485bf4697702f546ae70230f0ac307efb9988","source":{"kind":"arxiv","id":"2607.17857","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17857","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17857v1","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17857","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"EW6CE667F2F6","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"EW6CE667F2F6OWVL","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"EW6CE667","created_at":"2026-07-21T02:22:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EW6CE667F2F6OWVLPDAJJBEFX5","target":"record","payload":{"canonical_record":{"source":{"id":"2607.17857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T11:56:56Z","cross_cats_sorted":[],"title_canon_sha256":"6f4c0552c1f37b7abdfce8a9d3b1ccf5b3b7ddea95e0858938194e756d400e5b","abstract_canon_sha256":"0c983541b264657adc6a1082233bd88f9003b2d8b6d155afa748bc4608804271"},"schema_version":"1.0"},"canonical_sha256":"25bc227bdf2e8be75aab78c0948485bf4697702f546ae70230f0ac307efb9988","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:22:03.811137Z","signature_b64":"7vDyFC3VJGZ4SJvAiJo0CanzEOr63+AlRj4kEP/x9r66ndiwvt3cKkvdX+Zjp0yFUAdSDLJFm41nIkiXLqleBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25bc227bdf2e8be75aab78c0948485bf4697702f546ae70230f0ac307efb9988","last_reissued_at":"2026-07-21T02:22:03.810226Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:22:03.810226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.17857","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":"2026-07-21T02:22:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPLkPghOQ+6gRb58kKwxE3Nc/2pl/k9EbUcfDePp2R8TGp5hkteN1VBE2ex857QX05nc7EKHmBoPzEJ1USmwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:11:59.959957Z"},"content_sha256":"c5b291aa13c94ed40f4bc112250bc9cdee4be936a50c90ad44d260639b6a989d","schema_version":"1.0","event_id":"sha256:c5b291aa13c94ed40f4bc112250bc9cdee4be936a50c90ad44d260639b6a989d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EW6CE667F2F6OWVLPDAJJBEFX5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kan Li, Wenxiao Fan","submitted_at":"2026-07-20T11:56:56Z","abstract_excerpt":"Deep learning models excel in visual recognition but suffer severe performance drops when training labels are corrupted by noise. Under label noise prior work cannot learn accurate similarities and thus misguide the learning process. In this paper, we uncover a complementary and novel phenomenon, Dissimilarity Invariance, whereby semantic dissimilarity between unrelated samples remains stable despite label noise. Leveraging this insight, we propose NegScale, a plug-and-play framework that shifts focus from fragile similarity to robust dissimilarity. NegScale integrates: (1) Structured Negative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17857","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/2607.17857/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":"2026-07-21T02:22:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w3noREO8mRcJx2WNv2w2eeLB7QeId+djhTSzxxJi9PN14GFjceofsaVND5zKBiNLj5khuZZQ67SrQ54qpjN5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:11:59.960326Z"},"content_sha256":"d05f74dd3dd95332bf6580f3329cb9c6996a94461af3083dce1271f0596660cc","schema_version":"1.0","event_id":"sha256:d05f74dd3dd95332bf6580f3329cb9c6996a94461af3083dce1271f0596660cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EW6CE667F2F6OWVLPDAJJBEFX5/bundle.json","state_url":"https://pith.science/pith/EW6CE667F2F6OWVLPDAJJBEFX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EW6CE667F2F6OWVLPDAJJBEFX5/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":"2026-08-07T19:11:59Z","links":{"resolver":"https://pith.science/pith/EW6CE667F2F6OWVLPDAJJBEFX5","bundle":"https://pith.science/pith/EW6CE667F2F6OWVLPDAJJBEFX5/bundle.json","state":"https://pith.science/pith/EW6CE667F2F6OWVLPDAJJBEFX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EW6CE667F2F6OWVLPDAJJBEFX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EW6CE667F2F6OWVLPDAJJBEFX5","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":"0c983541b264657adc6a1082233bd88f9003b2d8b6d155afa748bc4608804271","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T11:56:56Z","title_canon_sha256":"6f4c0552c1f37b7abdfce8a9d3b1ccf5b3b7ddea95e0858938194e756d400e5b"},"schema_version":"1.0","source":{"id":"2607.17857","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17857","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17857v1","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17857","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"EW6CE667F2F6","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"EW6CE667F2F6OWVL","created_at":"2026-07-21T02:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"EW6CE667","created_at":"2026-07-21T02:22:03Z"}],"graph_snapshots":[{"event_id":"sha256:d05f74dd3dd95332bf6580f3329cb9c6996a94461af3083dce1271f0596660cc","target":"graph","created_at":"2026-07-21T02:22:03Z","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/2607.17857/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning models excel in visual recognition but suffer severe performance drops when training labels are corrupted by noise. Under label noise prior work cannot learn accurate similarities and thus misguide the learning process. In this paper, we uncover a complementary and novel phenomenon, Dissimilarity Invariance, whereby semantic dissimilarity between unrelated samples remains stable despite label noise. Leveraging this insight, we propose NegScale, a plug-and-play framework that shifts focus from fragile similarity to robust dissimilarity. NegScale integrates: (1) Structured Negative","authors_text":"Kan Li, Wenxiao Fan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T11:56:56Z","title":"Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17857","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:c5b291aa13c94ed40f4bc112250bc9cdee4be936a50c90ad44d260639b6a989d","target":"record","created_at":"2026-07-21T02:22:03Z","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":"0c983541b264657adc6a1082233bd88f9003b2d8b6d155afa748bc4608804271","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T11:56:56Z","title_canon_sha256":"6f4c0552c1f37b7abdfce8a9d3b1ccf5b3b7ddea95e0858938194e756d400e5b"},"schema_version":"1.0","source":{"id":"2607.17857","kind":"arxiv","version":1}},"canonical_sha256":"25bc227bdf2e8be75aab78c0948485bf4697702f546ae70230f0ac307efb9988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25bc227bdf2e8be75aab78c0948485bf4697702f546ae70230f0ac307efb9988","first_computed_at":"2026-07-21T02:22:03.810226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:22:03.810226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7vDyFC3VJGZ4SJvAiJo0CanzEOr63+AlRj4kEP/x9r66ndiwvt3cKkvdX+Zjp0yFUAdSDLJFm41nIkiXLqleBA==","signature_status":"signed_v1","signed_at":"2026-07-21T02:22:03.811137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17857","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5b291aa13c94ed40f4bc112250bc9cdee4be936a50c90ad44d260639b6a989d","sha256:d05f74dd3dd95332bf6580f3329cb9c6996a94461af3083dce1271f0596660cc"],"state_sha256":"3e1185b5a643d72dcdd792d798b373cc4a4ac5bc28a9f9f1fd945ced07611a74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X2hZw52w6MxatlGjqiZrYpPncf7kFw5GD5CWbRrgk41fyEXlJnRQp9y+20u8cbT0swoh+eSfo1kMvh0DNWI8CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:11:59.963199Z","bundle_sha256":"2b551fba81d6bbb2d3f92bd6a2326421ca0574d1cea495025fd8eedaa3e539c8"}}