{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4GX2JJXN5UINHAIHRNDOX2YGOB","short_pith_number":"pith:4GX2JJXN","canonical_record":{"source":{"id":"2509.18919","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-23T12:35:32Z","cross_cats_sorted":[],"title_canon_sha256":"ff30ec09f643804382b5c113ed201b8e784a0ce42d61f718b35f8a6de90ddddd","abstract_canon_sha256":"23fdee7e9523bed9ee4e681217ba34fc93b41b4d50c3f93b6f5079c2079981ba"},"schema_version":"1.0"},"canonical_sha256":"e1afa4a6eded10d381078b46ebeb067045b84564640c11dd6a7b21cb8de4adbb","source":{"kind":"arxiv","id":"2509.18919","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.18919","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2509.18919v2","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.18919","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"4GX2JJXN5UIN","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"4GX2JJXN5UINHAIH","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"4GX2JJXN","created_at":"2026-05-27T01:05:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4GX2JJXN5UINHAIHRNDOX2YGOB","target":"record","payload":{"canonical_record":{"source":{"id":"2509.18919","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-23T12:35:32Z","cross_cats_sorted":[],"title_canon_sha256":"ff30ec09f643804382b5c113ed201b8e784a0ce42d61f718b35f8a6de90ddddd","abstract_canon_sha256":"23fdee7e9523bed9ee4e681217ba34fc93b41b4d50c3f93b6f5079c2079981ba"},"schema_version":"1.0"},"canonical_sha256":"e1afa4a6eded10d381078b46ebeb067045b84564640c11dd6a7b21cb8de4adbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:38.067879Z","signature_b64":"x2lFlfulwMbL2W1p8NXkttBMB8VbmiECm6hiOqp/2pS0QUaD8Y65fKxdFg2Lo1JsVtZT4Lx1wDprJUcH7r+HAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1afa4a6eded10d381078b46ebeb067045b84564640c11dd6a7b21cb8de4adbb","last_reissued_at":"2026-05-27T01:05:38.067119Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:38.067119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.18919","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DBXboSpprIU5q8LtF0n2pp6+sOzzUNCWyGGEI0TZbW6uXfnS4QMeWcQa4QPPAVOf5hyD+k1cA4Yh5m+XYVoDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:02:00.013636Z"},"content_sha256":"99f15f484bd3d78bccd71f28ef0016651262ba9fd41c6a72337271f237a49a93","schema_version":"1.0","event_id":"sha256:99f15f484bd3d78bccd71f28ef0016651262ba9fd41c6a72337271f237a49a93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4GX2JJXN5UINHAIHRNDOX2YGOB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuni Liu, Hongjie Li, Jiaqi Du, Ke Xu, Lei Jin, Qian Sun, Yangyang Hou","submitted_at":"2025-09-23T12:35:32Z","abstract_excerpt":"The pretraining-finetuning paradigm is a crucial strategy in metallic surface defect detection for mitigating the challenges posed by data scarcity. However, its implementation presents a critical dilemma. Pretraining on natural image datasets such as ImageNet, faces a significant domain gap. Meanwhile, naive self-supervised pretraining on in-domain industrial data is often ineffective due to the inability of existing learning objectives to distinguish subtle defect patterns from complex background noise and textures. To resolve this, we introduce Anomaly-Guided Self-Supervised Pretraining (AG"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.18919","kind":"arxiv","version":2},"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/2509.18919/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":"2026-05-27T01:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7D5VbMvKFrhdbQdFyGqExPMgwaEnrW0sjp4e7VR9i4ktYS3Yr08rqoWshDDVdn71VOlWjfPVEOmpkQ2AOXUzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:02:00.014507Z"},"content_sha256":"5d72362d5c06cb3a9008ad7527f417779b7e027a76a8345a6250afc9926c2012","schema_version":"1.0","event_id":"sha256:5d72362d5c06cb3a9008ad7527f417779b7e027a76a8345a6250afc9926c2012"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4GX2JJXN5UINHAIHRNDOX2YGOB/bundle.json","state_url":"https://pith.science/pith/4GX2JJXN5UINHAIHRNDOX2YGOB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4GX2JJXN5UINHAIHRNDOX2YGOB/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":"2026-05-31T09:02:00Z","links":{"resolver":"https://pith.science/pith/4GX2JJXN5UINHAIHRNDOX2YGOB","bundle":"https://pith.science/pith/4GX2JJXN5UINHAIHRNDOX2YGOB/bundle.json","state":"https://pith.science/pith/4GX2JJXN5UINHAIHRNDOX2YGOB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4GX2JJXN5UINHAIHRNDOX2YGOB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4GX2JJXN5UINHAIHRNDOX2YGOB","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":"23fdee7e9523bed9ee4e681217ba34fc93b41b4d50c3f93b6f5079c2079981ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-23T12:35:32Z","title_canon_sha256":"ff30ec09f643804382b5c113ed201b8e784a0ce42d61f718b35f8a6de90ddddd"},"schema_version":"1.0","source":{"id":"2509.18919","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.18919","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2509.18919v2","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.18919","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"4GX2JJXN5UIN","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"4GX2JJXN5UINHAIH","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"4GX2JJXN","created_at":"2026-05-27T01:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:5d72362d5c06cb3a9008ad7527f417779b7e027a76a8345a6250afc9926c2012","target":"graph","created_at":"2026-05-27T01:05:38Z","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/2509.18919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pretraining-finetuning paradigm is a crucial strategy in metallic surface defect detection for mitigating the challenges posed by data scarcity. However, its implementation presents a critical dilemma. Pretraining on natural image datasets such as ImageNet, faces a significant domain gap. Meanwhile, naive self-supervised pretraining on in-domain industrial data is often ineffective due to the inability of existing learning objectives to distinguish subtle defect patterns from complex background noise and textures. To resolve this, we introduce Anomaly-Guided Self-Supervised Pretraining (AG","authors_text":"Chuni Liu, Hongjie Li, Jiaqi Du, Ke Xu, Lei Jin, Qian Sun, Yangyang Hou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-23T12:35:32Z","title":"Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.18919","kind":"arxiv","version":2},"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":"sha256:99f15f484bd3d78bccd71f28ef0016651262ba9fd41c6a72337271f237a49a93","target":"record","created_at":"2026-05-27T01:05:38Z","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":"23fdee7e9523bed9ee4e681217ba34fc93b41b4d50c3f93b6f5079c2079981ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-23T12:35:32Z","title_canon_sha256":"ff30ec09f643804382b5c113ed201b8e784a0ce42d61f718b35f8a6de90ddddd"},"schema_version":"1.0","source":{"id":"2509.18919","kind":"arxiv","version":2}},"canonical_sha256":"e1afa4a6eded10d381078b46ebeb067045b84564640c11dd6a7b21cb8de4adbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1afa4a6eded10d381078b46ebeb067045b84564640c11dd6a7b21cb8de4adbb","first_computed_at":"2026-05-27T01:05:38.067119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:38.067119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x2lFlfulwMbL2W1p8NXkttBMB8VbmiECm6hiOqp/2pS0QUaD8Y65fKxdFg2Lo1JsVtZT4Lx1wDprJUcH7r+HAg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:38.067879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.18919","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99f15f484bd3d78bccd71f28ef0016651262ba9fd41c6a72337271f237a49a93","sha256:5d72362d5c06cb3a9008ad7527f417779b7e027a76a8345a6250afc9926c2012"],"state_sha256":"27d667a75ad08e66793ddb8aacc4a0b6f7f7d09eb68d9d9890c73a35de2a0552"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wLeCF/gFRQcq+yYzEoOZeFt9pW2ITqaevIjvOwCXHUBxryP7UfT6yKm90P/yoN733k3p2v6MEInkloSwq6GqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T09:02:00.018883Z","bundle_sha256":"f0ad4c6e37bfa7fa5ac0dbf2f42e70721dc3a0772487ed19f53ae3f93d30f33d"}}