{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:IOF7CU5BT7VQJTK6LIYE2XOZWR","short_pith_number":"pith:IOF7CU5B","canonical_record":{"source":{"id":"1401.4107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-01-16T17:58:21Z","cross_cats_sorted":[],"title_canon_sha256":"cdd1a43c21fefb86901d8ab948bfa48ffbf3c2bd8d9bc3fb335a566ab8cfc34d","abstract_canon_sha256":"adb6e34840e189cfe6f51fc9aa29e87f27892f42b86d66bb4a0ea66ef0059607"},"schema_version":"1.0"},"canonical_sha256":"438bf153a19feb04cd5e5a304d5dd9b44b46f8e3bdb05515f6ef9ec07ecf3d76","source":{"kind":"arxiv","id":"1401.4107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.4107","created_at":"2026-05-18T03:01:57Z"},{"alias_kind":"arxiv_version","alias_value":"1401.4107v1","created_at":"2026-05-18T03:01:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.4107","created_at":"2026-05-18T03:01:57Z"},{"alias_kind":"pith_short_12","alias_value":"IOF7CU5BT7VQ","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"IOF7CU5BT7VQJTK6","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"IOF7CU5B","created_at":"2026-05-18T12:28:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:IOF7CU5BT7VQJTK6LIYE2XOZWR","target":"record","payload":{"canonical_record":{"source":{"id":"1401.4107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-01-16T17:58:21Z","cross_cats_sorted":[],"title_canon_sha256":"cdd1a43c21fefb86901d8ab948bfa48ffbf3c2bd8d9bc3fb335a566ab8cfc34d","abstract_canon_sha256":"adb6e34840e189cfe6f51fc9aa29e87f27892f42b86d66bb4a0ea66ef0059607"},"schema_version":"1.0"},"canonical_sha256":"438bf153a19feb04cd5e5a304d5dd9b44b46f8e3bdb05515f6ef9ec07ecf3d76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:01:57.182450Z","signature_b64":"zG1YhIa2eOW8sz7E53Crk3CtXue0PcApoWra2x8lthc872iMP5HbLsw4+b7fAfDGBUEpv4SPQhaBabh2x1P+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"438bf153a19feb04cd5e5a304d5dd9b44b46f8e3bdb05515f6ef9ec07ecf3d76","last_reissued_at":"2026-05-18T03:01:57.181905Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:01:57.181905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1401.4107","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":"2026-05-18T03:01:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"drM70dJT92eqxfA6oiLd0r9Jvez52aFQeqeE5LWu4IENQwgpdwKmmMP0fDQmRU2Wz92GRvSEsQBEcEqDW0cCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T22:53:37.007697Z"},"content_sha256":"ba31b8bd1018fe3a44a7e8f86be7d4000647847e54e62f511795fc793003cc11","schema_version":"1.0","event_id":"sha256:ba31b8bd1018fe3a44a7e8f86be7d4000647847e54e62f511795fc793003cc11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:IOF7CU5BT7VQJTK6LIYE2XOZWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting loss-specific training of filter-based MRFs for image restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Horst Bischof, Ren\\'e Ranftl, Thomas Pock, Yunjin Chen","submitted_at":"2014-01-16T17:58:21Z","abstract_excerpt":"It is now well known that Markov random fields (MRFs) are particularly effective for modeling image priors in low-level vision. Recent years have seen the emergence of two main approaches for learning the parameters in MRFs: (1) probabilistic learning using sampling-based algorithms and (2) loss-specific training based on MAP estimate. After investigating existing training approaches, it turns out that the performance of the loss-specific training has been significantly underestimated in existing work. In this paper, we revisit this approach and use techniques from bi-level optimization to sol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.4107","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":""},"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":"2026-05-18T03:01:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bwMNufePoAqA+vMXV18hIpPS8vXZwDOT69EGHoLGOR3q02nrtmbXaHBfyH+VBofJVw9A4utK8uLQj9pIYXh6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T22:53:37.008115Z"},"content_sha256":"ef468c429b3c267b92cc44b61f636b95a651401616bb2358eca8e83af86c291d","schema_version":"1.0","event_id":"sha256:ef468c429b3c267b92cc44b61f636b95a651401616bb2358eca8e83af86c291d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IOF7CU5BT7VQJTK6LIYE2XOZWR/bundle.json","state_url":"https://pith.science/pith/IOF7CU5BT7VQJTK6LIYE2XOZWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IOF7CU5BT7VQJTK6LIYE2XOZWR/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":"2026-06-25T22:53:37Z","links":{"resolver":"https://pith.science/pith/IOF7CU5BT7VQJTK6LIYE2XOZWR","bundle":"https://pith.science/pith/IOF7CU5BT7VQJTK6LIYE2XOZWR/bundle.json","state":"https://pith.science/pith/IOF7CU5BT7VQJTK6LIYE2XOZWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IOF7CU5BT7VQJTK6LIYE2XOZWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:IOF7CU5BT7VQJTK6LIYE2XOZWR","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":"adb6e34840e189cfe6f51fc9aa29e87f27892f42b86d66bb4a0ea66ef0059607","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-01-16T17:58:21Z","title_canon_sha256":"cdd1a43c21fefb86901d8ab948bfa48ffbf3c2bd8d9bc3fb335a566ab8cfc34d"},"schema_version":"1.0","source":{"id":"1401.4107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.4107","created_at":"2026-05-18T03:01:57Z"},{"alias_kind":"arxiv_version","alias_value":"1401.4107v1","created_at":"2026-05-18T03:01:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.4107","created_at":"2026-05-18T03:01:57Z"},{"alias_kind":"pith_short_12","alias_value":"IOF7CU5BT7VQ","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"IOF7CU5BT7VQJTK6","created_at":"2026-05-18T12:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"IOF7CU5B","created_at":"2026-05-18T12:28:33Z"}],"graph_snapshots":[{"event_id":"sha256:ef468c429b3c267b92cc44b61f636b95a651401616bb2358eca8e83af86c291d","target":"graph","created_at":"2026-05-18T03:01:57Z","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"},"paper":{"abstract_excerpt":"It is now well known that Markov random fields (MRFs) are particularly effective for modeling image priors in low-level vision. Recent years have seen the emergence of two main approaches for learning the parameters in MRFs: (1) probabilistic learning using sampling-based algorithms and (2) loss-specific training based on MAP estimate. After investigating existing training approaches, it turns out that the performance of the loss-specific training has been significantly underestimated in existing work. In this paper, we revisit this approach and use techniques from bi-level optimization to sol","authors_text":"Horst Bischof, Ren\\'e Ranftl, Thomas Pock, Yunjin Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-01-16T17:58:21Z","title":"Revisiting loss-specific training of filter-based MRFs for image restoration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.4107","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:ba31b8bd1018fe3a44a7e8f86be7d4000647847e54e62f511795fc793003cc11","target":"record","created_at":"2026-05-18T03:01:57Z","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":"adb6e34840e189cfe6f51fc9aa29e87f27892f42b86d66bb4a0ea66ef0059607","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-01-16T17:58:21Z","title_canon_sha256":"cdd1a43c21fefb86901d8ab948bfa48ffbf3c2bd8d9bc3fb335a566ab8cfc34d"},"schema_version":"1.0","source":{"id":"1401.4107","kind":"arxiv","version":1}},"canonical_sha256":"438bf153a19feb04cd5e5a304d5dd9b44b46f8e3bdb05515f6ef9ec07ecf3d76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"438bf153a19feb04cd5e5a304d5dd9b44b46f8e3bdb05515f6ef9ec07ecf3d76","first_computed_at":"2026-05-18T03:01:57.181905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:01:57.181905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zG1YhIa2eOW8sz7E53Crk3CtXue0PcApoWra2x8lthc872iMP5HbLsw4+b7fAfDGBUEpv4SPQhaBabh2x1P+AA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:01:57.182450Z","signed_message":"canonical_sha256_bytes"},"source_id":"1401.4107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba31b8bd1018fe3a44a7e8f86be7d4000647847e54e62f511795fc793003cc11","sha256:ef468c429b3c267b92cc44b61f636b95a651401616bb2358eca8e83af86c291d"],"state_sha256":"deb1fcc9fd941f0315af78a4300913201004b1c9007af2dfc8200e7b6a07ad03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wTWrM7UilwSJ9DJwtzZEbN+w55MuLhn2grilxAUYR3ujZ0jOWMOBrfb6I9vw6XQnp2LC7REAaynfRyw5W9hpAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T22:53:37.010742Z","bundle_sha256":"82f88fb05bd0e84961f8d2abdb25cf407abc5b7f6df439a2ec6c5f30b987c418"}}