{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YRS56DTCI44HPLFJDMEVDGZIM6","short_pith_number":"pith:YRS56DTC","canonical_record":{"source":{"id":"1708.02668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-08T22:41:43Z","cross_cats_sorted":[],"title_canon_sha256":"bc2eab6c8f9a6086dd0453f6dc5fa260820ce24f03c78f7cb05953e31331aa54","abstract_canon_sha256":"4706ed008b8d85e50d22b6fb7c7a1e567ccd1b4245b5193976f5114c54f72370"},"schema_version":"1.0"},"canonical_sha256":"c465df0e62473877aca91b09519b286791bb9ded8225f706f78b8282ecd7970b","source":{"kind":"arxiv","id":"1708.02668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.02668","created_at":"2026-05-18T00:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"1708.02668v1","created_at":"2026-05-18T00:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02668","created_at":"2026-05-18T00:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"YRS56DTCI44H","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YRS56DTCI44HPLFJ","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YRS56DTC","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YRS56DTCI44HPLFJDMEVDGZIM6","target":"record","payload":{"canonical_record":{"source":{"id":"1708.02668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-08T22:41:43Z","cross_cats_sorted":[],"title_canon_sha256":"bc2eab6c8f9a6086dd0453f6dc5fa260820ce24f03c78f7cb05953e31331aa54","abstract_canon_sha256":"4706ed008b8d85e50d22b6fb7c7a1e567ccd1b4245b5193976f5114c54f72370"},"schema_version":"1.0"},"canonical_sha256":"c465df0e62473877aca91b09519b286791bb9ded8225f706f78b8282ecd7970b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:19.973586Z","signature_b64":"AqwnJyLcmxw6QRCi0TiQ94dz0VczwSW1GwEGukyG6X2Kw42iB0TaQ6M/KhH0Q+VIT9s++4C8XyDTNA/fQBBbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c465df0e62473877aca91b09519b286791bb9ded8225f706f78b8282ecd7970b","last_reissued_at":"2026-05-18T00:38:19.972941Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:19.972941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.02668","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":"2026-05-18T00:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1hulHstFt3IkDjTEBYIbpXlzRxVXzFB9aVssDT4Q/6nqfwRWgNnfmDq9HuRFH44iDaVls08WTgl3oWfPUvj9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:18:07.485421Z"},"content_sha256":"007d53278750f3350ecfd81aa3ac841afc3b6baeec02ae11d6531af3188bb989","schema_version":"1.0","event_id":"sha256:007d53278750f3350ecfd81aa3ac841afc3b6baeec02ae11d6531af3188bb989"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YRS56DTCI44HPLFJDMEVDGZIM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A discriminative view of MRF pre-processing algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charles Herrmann, Chen Wang, Ramin Zabih","submitted_at":"2017-08-08T22:41:43Z","abstract_excerpt":"While Markov Random Fields (MRFs) are widely used in computer vision, they present a quite challenging inference problem. MRF inference can be accelerated by pre-processing techniques like Dead End Elimination (DEE) or QPBO-based approaches which compute the optimal labeling of a subset of variables. These techniques are guaranteed to never wrongly label a variable but they often leave a large number of variables unlabeled. We address this shortcoming by interpreting pre-processing as a classification problem, which allows us to trade off false positives (i.e., giving a variable an incorrect l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02668","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":"2026-05-18T00:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F2lLDYsaS/HqvzZoMplbUOuedea7KSNe+M2xamxIN8K5eplmsCUxri+HSaIJ+fSeGvvfZ66vIit2s2DYiQk8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:18:07.486052Z"},"content_sha256":"4393e1bb645000412348c1746e85a511b974f95cf5fafe5ad42c189877f575cb","schema_version":"1.0","event_id":"sha256:4393e1bb645000412348c1746e85a511b974f95cf5fafe5ad42c189877f575cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YRS56DTCI44HPLFJDMEVDGZIM6/bundle.json","state_url":"https://pith.science/pith/YRS56DTCI44HPLFJDMEVDGZIM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YRS56DTCI44HPLFJDMEVDGZIM6/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":"2026-06-04T06:18:07Z","links":{"resolver":"https://pith.science/pith/YRS56DTCI44HPLFJDMEVDGZIM6","bundle":"https://pith.science/pith/YRS56DTCI44HPLFJDMEVDGZIM6/bundle.json","state":"https://pith.science/pith/YRS56DTCI44HPLFJDMEVDGZIM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YRS56DTCI44HPLFJDMEVDGZIM6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YRS56DTCI44HPLFJDMEVDGZIM6","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":"4706ed008b8d85e50d22b6fb7c7a1e567ccd1b4245b5193976f5114c54f72370","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-08T22:41:43Z","title_canon_sha256":"bc2eab6c8f9a6086dd0453f6dc5fa260820ce24f03c78f7cb05953e31331aa54"},"schema_version":"1.0","source":{"id":"1708.02668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.02668","created_at":"2026-05-18T00:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"1708.02668v1","created_at":"2026-05-18T00:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02668","created_at":"2026-05-18T00:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"YRS56DTCI44H","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YRS56DTCI44HPLFJ","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YRS56DTC","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:4393e1bb645000412348c1746e85a511b974f95cf5fafe5ad42c189877f575cb","target":"graph","created_at":"2026-05-18T00:38:19Z","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":"While Markov Random Fields (MRFs) are widely used in computer vision, they present a quite challenging inference problem. MRF inference can be accelerated by pre-processing techniques like Dead End Elimination (DEE) or QPBO-based approaches which compute the optimal labeling of a subset of variables. These techniques are guaranteed to never wrongly label a variable but they often leave a large number of variables unlabeled. We address this shortcoming by interpreting pre-processing as a classification problem, which allows us to trade off false positives (i.e., giving a variable an incorrect l","authors_text":"Charles Herrmann, Chen Wang, Ramin Zabih","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-08T22:41:43Z","title":"A discriminative view of MRF pre-processing algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02668","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":"sha256:007d53278750f3350ecfd81aa3ac841afc3b6baeec02ae11d6531af3188bb989","target":"record","created_at":"2026-05-18T00:38:19Z","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":"4706ed008b8d85e50d22b6fb7c7a1e567ccd1b4245b5193976f5114c54f72370","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-08T22:41:43Z","title_canon_sha256":"bc2eab6c8f9a6086dd0453f6dc5fa260820ce24f03c78f7cb05953e31331aa54"},"schema_version":"1.0","source":{"id":"1708.02668","kind":"arxiv","version":1}},"canonical_sha256":"c465df0e62473877aca91b09519b286791bb9ded8225f706f78b8282ecd7970b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c465df0e62473877aca91b09519b286791bb9ded8225f706f78b8282ecd7970b","first_computed_at":"2026-05-18T00:38:19.972941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:19.972941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AqwnJyLcmxw6QRCi0TiQ94dz0VczwSW1GwEGukyG6X2Kw42iB0TaQ6M/KhH0Q+VIT9s++4C8XyDTNA/fQBBbDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:19.973586Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.02668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:007d53278750f3350ecfd81aa3ac841afc3b6baeec02ae11d6531af3188bb989","sha256:4393e1bb645000412348c1746e85a511b974f95cf5fafe5ad42c189877f575cb"],"state_sha256":"75138dfba2824727199e230e50f3c194a2a2114273827abf9e1bfdf06cb07737"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r4BoF4MHRkXbA7jRMatz91FEV9rt6bFfr+R8cf5KDBTp7DBbLGT1JFJmVOE+BkCgoN8cPG6XfYGOvYyAmiTXAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T06:18:07.489589Z","bundle_sha256":"4770f240b5bd6a7a9d0d468895d754a721d5e277abe83db30867b681276ef3ee"}}