{"as_of":"2026-08-11T09:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:203547eff057ec70be522a97b3c404ece26a382130101493dcd3ec87ff3aed81","coverage":[{"denominator":18,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T08:44:38.977180Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.30452/citation-record","integrity":"/paper/2605.30452/integrity","json":"/paper/2605.30452/citation-record.json","paper":"/paper/2605.30452"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"Condi- tional gradient method for multiobjective optimization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:4fed80e732a11070e0e714446d30bd3018a5e664210c9250a1c3eecdd3a4f2e3","observation_id":"16624400-aad7-4c47-8872-42b898674a67","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"Fair Resource Allocation in Multi-Task Learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:675e04bbad142c7e56b17e33e266a18fa90c26ce46451b4d92bf55ed2d5c2734","observation_id":"f9609300-7fc4-4c25-bf1a-3c6bc49711c3","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16232","last_updated":"2025-02-03T12:29:44Z","snapshot_observed_at":"2026-08-11T00:32:02.213987Z","submitted_at":"2024-06-23T22:06:25Z","title":"Jacobian Descent for Multi-Objective Optimization","version":3},"cited_work":{"arxiv_id":"2406.16232","doi":"10.48550/arxiv.2406.16232","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.16232","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Jacobian descent for multi-objective optimization.arXiv preprint arXiv:2406.16232","venue":"arXiv (Cornell University)","work_id":"4711764f-d344-4191-acbd-4f2e75a07b53","year":2024},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"cited_paper":"/paper/2406.16232","citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:fd0d23aed8724059e53bb3c9dd600aa7265d0c10bcfdb3faeacc0030a511dbf7","observation_id":"931ec840-348a-4774-abd0-6884d2461a75","resolution":{"observed_at":"2026-06-29T08:53:16.420337Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"Multi-Task Learning as Multi- Objective Optimization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:1be47366821d27027a403590693e47c1281c4ccebd1b0a33538982295fc02faa","observation_id":"441ba2f5-ae0f-4510-b3bf-99b66afb7b81","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"Convergence guarantees of linear scalarization.The aggregation rule in (23) corresponds precisely to performing gradient descent on the scalarized objective F= P i fi","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:d4eed357dc65482203da2c0e2f07c4b3738e7ebcb55b3211c2b5ca90c04376c4","observation_id":"85af59dd-3684-47ab-9838-36dc28f85198","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":null,"venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:46cf1e409699e1716117f94ed10b74ca034f56b777408f00f89d2dadfc08f1a3","observation_id":"2eb0aeab-8472-4f38-a3b1-878dd825be4b","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:cd503737a768266d94dcc36a4d62b9808589dfbec53176a8f4f9842404a4b828","observation_id":"56cf3bba-61d6-4bd8-be3b-a0afae5019b4","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"(2019) for both non-convex and convex settings","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:9551b5f2d2bbf0590e702a567e858d14ffef729fd1cfce703bfdb2191d4d7c3c","observation_id":"af1e40c3-1f48-4a89-93e0-25f745416498","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:36f1a6f89b1ab783947f4cc9961501edf7b72a66a0f4a24b954a509d1b35ab1b","observation_id":"c8088df2-0442-40a6-918c-97cad02b05a3","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"(2022) and our analysis (Theorem","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:d538a02fafda1e60c5fa1e85711d3fca8968d3ff0ddf48a1d59e8a730ef5ef90","observation_id":"a13b82bd-2fb9-4105-ba59-6678055d9b1d","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"While Navon et al","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:ece92b5830f4c7a88ecd3bc2785978e684a8fc9fb562ca9ca2ec4ae857ff461d","observation_id":"2920bb45-3ae7-4cd8-a785-dee076fb568a","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:ffbcb53050b4eb103a3d6ac69e1111b33f02ef05a8586d5eb3f6270015073fb3","observation_id":"cca6f5e5-4276-459f-ae98-97d16b90174f","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"Within our framework, Corollary 2 establishes an O(1/ √ t) convergence rate for DualProj in terms of the Pareto stationarity measure γ(wt) for the non-convex setting","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:c22ee27459903d8bef3d419f170b9bd26fd31fc588eb7a0f8a1ec5ce164dcb99","observation_id":"157d7c41-4311-4024-ad3d-97ef21f26ec3","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:440c0b8034a25e1ffb243ae8ab9e27f7f7db6c4745f54b3c27569a4e87576075","observation_id":"2cdeb452-3894-4f0c-b072-1f820e9ee717","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"Proof.We omit the indextin the following to simplify the notation","venue":null,"work_id":null,"year":1962},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:8139bd333d6cf90d6eec3740c9d166fec8363c94835482f21ad3d239b0e71a6e","observation_id":"fee9caf3-08d2-422a-a33c-be2a8de2261f","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"For Nash-MTL (Navon et al., 2022), we adopt the official implementation’s default, which always clips the aggregated update direction to satisfy∥dt∥= 1","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:f9522d69049b683548389f5fd57419a602dc0759589a6ea9aa0f4793d44588a7","observation_id":"d10402a3-8a6c-4a08-855e-f356e01a929a","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"Specifically, we use the function libmoon.util.mtl.get_dataset(\"adult\") to generate the train, validation, and test splits","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:a55d03e2e92b20edc0166c729c7758d0219c2620c407f36ea324a0e175902e77","observation_id":"1c868516-09b7-401f-98a0-a4a5ec8dd8a2","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:44:38.977180Z","title":"MGDA + coefficient-clipping","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:38.977180Z"},"links":{"citing_paper":"/paper/2605.30452"},"observation_digest":"sha256:4f3c3efcb5fb7747b2c265306444807404294882d10e5ffd729789958e40770d","observation_id":"69ecbd10-49d0-45d1-9cbb-6f6566e332fe","resolution":{"observed_at":"2026-06-29T08:44:38.977180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.30452","last_updated":"2026-05-28T18:21:53Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-03T23:52:04.205374Z","submitted_at":"2026-05-28T18:21:53Z","title":"A Unified Framework for Gradient Aggregation in Multi-Objective Optimization"},"reference_resolution":{"displayed":18,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":18},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2605.30452."}