{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:B4PHWPLUPWK2WC5HKU4QBJMWFG","short_pith_number":"pith:B4PHWPLU","canonical_record":{"source":{"id":"1702.03690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-13T09:49:35Z","cross_cats_sorted":[],"title_canon_sha256":"d2c92ab7abf4f6fb22ca624539cb902131afab65e0f5b0d9b2da534bc1f61162","abstract_canon_sha256":"2bde043d60da34ebbdf70d6a62ca4186b518b6b2b362d683753accf386a66a02"},"schema_version":"1.0"},"canonical_sha256":"0f1e7b3d747d95ab0ba7553900a59629a4f986d64dd9a51ab3217dd517451cf1","source":{"kind":"arxiv","id":"1702.03690","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.03690","created_at":"2026-05-18T00:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"1702.03690v1","created_at":"2026-05-18T00:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03690","created_at":"2026-05-18T00:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"B4PHWPLUPWK2","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"B4PHWPLUPWK2WC5H","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"B4PHWPLU","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:B4PHWPLUPWK2WC5HKU4QBJMWFG","target":"record","payload":{"canonical_record":{"source":{"id":"1702.03690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-13T09:49:35Z","cross_cats_sorted":[],"title_canon_sha256":"d2c92ab7abf4f6fb22ca624539cb902131afab65e0f5b0d9b2da534bc1f61162","abstract_canon_sha256":"2bde043d60da34ebbdf70d6a62ca4186b518b6b2b362d683753accf386a66a02"},"schema_version":"1.0"},"canonical_sha256":"0f1e7b3d747d95ab0ba7553900a59629a4f986d64dd9a51ab3217dd517451cf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:53.231659Z","signature_b64":"4ANkPGGy7QIp10QS3Kdu3LcKy/vQ4V4YjqO0FqMUd9LDlGEz4p3l1t6SEb5Zq40Bw52DiAlLxS93pO8aDzi6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f1e7b3d747d95ab0ba7553900a59629a4f986d64dd9a51ab3217dd517451cf1","last_reissued_at":"2026-05-18T00:50:53.231105Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:53.231105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.03690","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":"2026-05-18T00:50:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4CrAb6aR+cpmaXqyyeyaK6+l/RkYBwUP5BPeNx4mvHz6Tr06c0LzKH3W3JGC2/0nhByGDLlh3MBUDWT0fb2VAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T20:44:15.130034Z"},"content_sha256":"a1f0d89e917759ca5160bbbd23e9893825880e02132e7ab8b24ca89bd7207a7c","schema_version":"1.0","event_id":"sha256:a1f0d89e917759ca5160bbbd23e9893825880e02132e7ab8b24ca89bd7207a7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:B4PHWPLUPWK2WC5HKU4QBJMWFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Efficient Decomposition Framework for Discriminative Segmentation with Supermodular Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqian Yu, Matthew B. Blaschko","submitted_at":"2017-02-13T09:49:35Z","abstract_excerpt":"Several supermodular losses have been shown to improve the perceptual quality of image segmentation in a discriminative framework such as a structured output support vector machine (SVM). These loss functions do not necessarily have the same structure as the one used by the segmentation inference algorithm, and in general, we may have to resort to generic submodular minimization algorithms for loss augmented inference. Although these come with polynomial time guarantees, they are not practical to apply to image scale data. Many supermodular losses come with strong optimization guarantees, but "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03690","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":"2026-05-18T00:50:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4mrCO/hosVieCaf2A77pFTpXQK3jqwSXoJ9b+U7Yqrpx4vGfzLlYwUhNq7P/hy02Iju/0EUxeFlB+dTFB5OrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T20:44:15.130744Z"},"content_sha256":"2a36f8c160e1259ced9a9969af21c8d4988b5fed9be3659774aaeda884d2e4d6","schema_version":"1.0","event_id":"sha256:2a36f8c160e1259ced9a9969af21c8d4988b5fed9be3659774aaeda884d2e4d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B4PHWPLUPWK2WC5HKU4QBJMWFG/bundle.json","state_url":"https://pith.science/pith/B4PHWPLUPWK2WC5HKU4QBJMWFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B4PHWPLUPWK2WC5HKU4QBJMWFG/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":"2026-06-07T20:44:15Z","links":{"resolver":"https://pith.science/pith/B4PHWPLUPWK2WC5HKU4QBJMWFG","bundle":"https://pith.science/pith/B4PHWPLUPWK2WC5HKU4QBJMWFG/bundle.json","state":"https://pith.science/pith/B4PHWPLUPWK2WC5HKU4QBJMWFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B4PHWPLUPWK2WC5HKU4QBJMWFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:B4PHWPLUPWK2WC5HKU4QBJMWFG","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":"2bde043d60da34ebbdf70d6a62ca4186b518b6b2b362d683753accf386a66a02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-13T09:49:35Z","title_canon_sha256":"d2c92ab7abf4f6fb22ca624539cb902131afab65e0f5b0d9b2da534bc1f61162"},"schema_version":"1.0","source":{"id":"1702.03690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.03690","created_at":"2026-05-18T00:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"1702.03690v1","created_at":"2026-05-18T00:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03690","created_at":"2026-05-18T00:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"B4PHWPLUPWK2","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"B4PHWPLUPWK2WC5H","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"B4PHWPLU","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:2a36f8c160e1259ced9a9969af21c8d4988b5fed9be3659774aaeda884d2e4d6","target":"graph","created_at":"2026-05-18T00:50:53Z","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":"Several supermodular losses have been shown to improve the perceptual quality of image segmentation in a discriminative framework such as a structured output support vector machine (SVM). These loss functions do not necessarily have the same structure as the one used by the segmentation inference algorithm, and in general, we may have to resort to generic submodular minimization algorithms for loss augmented inference. Although these come with polynomial time guarantees, they are not practical to apply to image scale data. Many supermodular losses come with strong optimization guarantees, but ","authors_text":"Jiaqian Yu, Matthew B. Blaschko","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-13T09:49:35Z","title":"An Efficient Decomposition Framework for Discriminative Segmentation with Supermodular Losses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03690","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:a1f0d89e917759ca5160bbbd23e9893825880e02132e7ab8b24ca89bd7207a7c","target":"record","created_at":"2026-05-18T00:50:53Z","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":"2bde043d60da34ebbdf70d6a62ca4186b518b6b2b362d683753accf386a66a02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-13T09:49:35Z","title_canon_sha256":"d2c92ab7abf4f6fb22ca624539cb902131afab65e0f5b0d9b2da534bc1f61162"},"schema_version":"1.0","source":{"id":"1702.03690","kind":"arxiv","version":1}},"canonical_sha256":"0f1e7b3d747d95ab0ba7553900a59629a4f986d64dd9a51ab3217dd517451cf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f1e7b3d747d95ab0ba7553900a59629a4f986d64dd9a51ab3217dd517451cf1","first_computed_at":"2026-05-18T00:50:53.231105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:53.231105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ANkPGGy7QIp10QS3Kdu3LcKy/vQ4V4YjqO0FqMUd9LDlGEz4p3l1t6SEb5Zq40Bw52DiAlLxS93pO8aDzi6AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:53.231659Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.03690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1f0d89e917759ca5160bbbd23e9893825880e02132e7ab8b24ca89bd7207a7c","sha256:2a36f8c160e1259ced9a9969af21c8d4988b5fed9be3659774aaeda884d2e4d6"],"state_sha256":"b5be1294bbacc1c462a1843aec40e8665168c2f9f9101b6f1bf91c59403d7ec6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eorDOtauOr5yQsRXZkS3peFsTMSh5peFi2M3RyelANbq3QNOwXZYhvI9dob6HR1joCzVAr6wyjiBOdHxmym/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T20:44:15.134188Z","bundle_sha256":"db3760491a66170f62970a46d0718fe9e60c1bb750a2f2e6f07aaddd865f2bde"}}