{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OPMPV2JOL57AIYLTXYGDOOCOLQ","short_pith_number":"pith:OPMPV2JO","canonical_record":{"source":{"id":"2411.10649","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T01:13:04Z","cross_cats_sorted":[],"title_canon_sha256":"16128536e965060a65efbfb7449ae550c7705befd4204622bf407116fb55f568","abstract_canon_sha256":"d0068f3b71380862d594fe3173c1b783a93c0430f28a81c1ecdf020dd7d63313"},"schema_version":"1.0"},"canonical_sha256":"73d8fae92e5f7e046173be0c37384e5c035145a6826dc10367a12771b18a59ac","source":{"kind":"arxiv","id":"2411.10649","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10649","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10649v1","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10649","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"pith_short_12","alias_value":"OPMPV2JOL57A","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"pith_short_16","alias_value":"OPMPV2JOL57AIYLT","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"pith_short_8","alias_value":"OPMPV2JO","created_at":"2026-07-05T09:36:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OPMPV2JOL57AIYLTXYGDOOCOLQ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10649","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T01:13:04Z","cross_cats_sorted":[],"title_canon_sha256":"16128536e965060a65efbfb7449ae550c7705befd4204622bf407116fb55f568","abstract_canon_sha256":"d0068f3b71380862d594fe3173c1b783a93c0430f28a81c1ecdf020dd7d63313"},"schema_version":"1.0"},"canonical_sha256":"73d8fae92e5f7e046173be0c37384e5c035145a6826dc10367a12771b18a59ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:51.439454Z","signature_b64":"6q0ZRlCHb/OdQL5M2mrsGvShoYQMIzYH816tBzm9Ty2L5yXk9Ilnd97qWSq+zWDl63XmMwUcM3zmsGPmGxRiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73d8fae92e5f7e046173be0c37384e5c035145a6826dc10367a12771b18a59ac","last_reissued_at":"2026-07-05T09:36:51.438985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:51.438985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10649","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":"2026-07-05T09:36:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bAowJlLL7SA/h6jK9e9ZB0p7ekLyxvixCWA6Aeud2pjiskxpla7NAocyOtjjdK2uR2MLZUkTtj9eHFrvkx6rBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:30:59.537959Z"},"content_sha256":"e0370c5954330d6279be85138e6082bc7674179eb9d9f700a508b1b0057ff103","schema_version":"1.0","event_id":"sha256:e0370c5954330d6279be85138e6082bc7674179eb9d9f700a508b1b0057ff103"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OPMPV2JOL57AIYLTXYGDOOCOLQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Loss Convexification for Learning Iterative Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elke Rundensteiner, Fangzhou Lin, Haichong Zhang, Yiqing Zhang, Yuping Shao, Ziming Zhang","submitted_at":"2024-11-16T01:13:04Z","abstract_excerpt":"Iterative methods such as iterative closest point (ICP) for point cloud registration often suffer from bad local optimality (e.g. saddle points), due to the nature of nonconvex optimization. To address this fundamental challenge, in this paper we propose learning to form the loss landscape of a deep iterative method w.r.t. predictions at test time into a convex-like shape locally around each ground truth given data, namely Deep Loss Convexification (DLC), thanks to the overparametrization in neural networks. To this end, we formulate our learning objective based on adversarial training by mani"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10649","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/2411.10649/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":"2026-07-05T09:36:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xJSlG12WcHMJylSsZY2n/PE9rmtD8v0/F9zcHX1WIyzxFVGeFMfp+C4UPEqTL1RePBgzW9MAyDTHfNrN8lGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:30:59.538285Z"},"content_sha256":"46fd6b654d307eb1f1e37b108d6040550befb2915dc36596ad9675ae1c548c60","schema_version":"1.0","event_id":"sha256:46fd6b654d307eb1f1e37b108d6040550befb2915dc36596ad9675ae1c548c60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPMPV2JOL57AIYLTXYGDOOCOLQ/bundle.json","state_url":"https://pith.science/pith/OPMPV2JOL57AIYLTXYGDOOCOLQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPMPV2JOL57AIYLTXYGDOOCOLQ/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":"2026-08-14T19:30:59Z","links":{"resolver":"https://pith.science/pith/OPMPV2JOL57AIYLTXYGDOOCOLQ","bundle":"https://pith.science/pith/OPMPV2JOL57AIYLTXYGDOOCOLQ/bundle.json","state":"https://pith.science/pith/OPMPV2JOL57AIYLTXYGDOOCOLQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPMPV2JOL57AIYLTXYGDOOCOLQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OPMPV2JOL57AIYLTXYGDOOCOLQ","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":"d0068f3b71380862d594fe3173c1b783a93c0430f28a81c1ecdf020dd7d63313","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T01:13:04Z","title_canon_sha256":"16128536e965060a65efbfb7449ae550c7705befd4204622bf407116fb55f568"},"schema_version":"1.0","source":{"id":"2411.10649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10649","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10649v1","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10649","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"pith_short_12","alias_value":"OPMPV2JOL57A","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"pith_short_16","alias_value":"OPMPV2JOL57AIYLT","created_at":"2026-07-05T09:36:51Z"},{"alias_kind":"pith_short_8","alias_value":"OPMPV2JO","created_at":"2026-07-05T09:36:51Z"}],"graph_snapshots":[{"event_id":"sha256:46fd6b654d307eb1f1e37b108d6040550befb2915dc36596ad9675ae1c548c60","target":"graph","created_at":"2026-07-05T09:36:51Z","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/2411.10649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Iterative methods such as iterative closest point (ICP) for point cloud registration often suffer from bad local optimality (e.g. saddle points), due to the nature of nonconvex optimization. To address this fundamental challenge, in this paper we propose learning to form the loss landscape of a deep iterative method w.r.t. predictions at test time into a convex-like shape locally around each ground truth given data, namely Deep Loss Convexification (DLC), thanks to the overparametrization in neural networks. To this end, we formulate our learning objective based on adversarial training by mani","authors_text":"Elke Rundensteiner, Fangzhou Lin, Haichong Zhang, Yiqing Zhang, Yuping Shao, Ziming Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T01:13:04Z","title":"Deep Loss Convexification for Learning Iterative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10649","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:e0370c5954330d6279be85138e6082bc7674179eb9d9f700a508b1b0057ff103","target":"record","created_at":"2026-07-05T09:36:51Z","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":"d0068f3b71380862d594fe3173c1b783a93c0430f28a81c1ecdf020dd7d63313","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T01:13:04Z","title_canon_sha256":"16128536e965060a65efbfb7449ae550c7705befd4204622bf407116fb55f568"},"schema_version":"1.0","source":{"id":"2411.10649","kind":"arxiv","version":1}},"canonical_sha256":"73d8fae92e5f7e046173be0c37384e5c035145a6826dc10367a12771b18a59ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73d8fae92e5f7e046173be0c37384e5c035145a6826dc10367a12771b18a59ac","first_computed_at":"2026-07-05T09:36:51.438985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:51.438985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6q0ZRlCHb/OdQL5M2mrsGvShoYQMIzYH816tBzm9Ty2L5yXk9Ilnd97qWSq+zWDl63XmMwUcM3zmsGPmGxRiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:51.439454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0370c5954330d6279be85138e6082bc7674179eb9d9f700a508b1b0057ff103","sha256:46fd6b654d307eb1f1e37b108d6040550befb2915dc36596ad9675ae1c548c60"],"state_sha256":"a8a0a9719d6c8acacb3e56084512063f9f54e9bb6e822703664d997450ae0576"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVQtUUoqFZKAyFh2vcOMsMQcyZNk1yCdkVVGvEd3IpawAUoN7e03b/yf8LpkPI1edL6ifAoRXnFNEC/hB3NjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:30:59.542712Z","bundle_sha256":"266df1bd8b293d7f47d07f83ac99191ca4ae912565252109bf52a796a22857c3"}}