{"as_of":"2026-08-08T18:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a160b711d2135f4d5ebe9e144765e5c65a75751f3652eaa5e9cde630a85cf1e8","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":12,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:30:18.365807Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-13T20:53:15.699075Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":"2204.03044","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fusing finetuned models for better pretraining","venue":null,"work_id":"28f3736c-8f57-47c1-8b13-23c608cec53c","year":2022},"citing_paper":{"arxiv_id":"2212.04089","last_updated":"2023-03-31T15:27:01Z","snapshot_observed_at":"2026-08-03T22:12:27.993418Z","submitted_at":"2022-12-08T05:50:53Z","title":"Editing Models with Task Arithmetic","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-13T08:09:12.716163Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2212.04089"},"observation_digest":"sha256:54f587690f4a9bd0762c556b6caaeec813dab0dab6fd132bd22f612b22e77f3d","observation_id":"eea2cf8c-7dcc-4e6a-abbf-11038c2a9dd9","resolution":{"observed_at":"2026-05-13T08:09:12.846324Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-07T14:30:18.365807Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18713","last_updated":"2025-05-24T14:27:20Z","snapshot_observed_at":"2026-08-08T03:28:31.402278Z","submitted_at":"2025-05-24T14:27:20Z","title":"Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T14:30:18.365807Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2505.18713"},"observation_digest":"sha256:af7dc221c4a561d1b65afb0ad281c3a776bb37896cdf4d8d2bd0ba4cfd554755","observation_id":"2f91bafc-df7e-4cf9-b960-3d7f5acbbf03","resolution":{"observed_at":"2026-08-07T14:30:18.365807Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-07T13:17:47.661698Z","title":"Fusing finetuned models for better pretraining","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22697","last_updated":"2025-05-28T13:55:12Z","snapshot_observed_at":"2026-08-07T13:06:24.584318Z","submitted_at":"2025-05-28T13:55:12Z","title":"Update Your Transformer to the Latest Release: Re-Basin of Task Vectors","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T13:17:47.661698Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2505.22697"},"observation_digest":"sha256:37537b120037fef77574f6f5ef9151283f5b5b682d2ed0bd98d838a136381153","observation_id":"df4e6500-3478-4593-b8fa-874e4a67e7e5","resolution":{"observed_at":"2026-08-07T13:17:47.661698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-07T12:13:42.124288Z","title":"Choshen, E","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.03189","last_updated":"2025-05-30T20:52:21Z","snapshot_observed_at":"2026-08-08T12:29:06.915460Z","submitted_at":"2025-05-30T20:52:21Z","title":"Continual Learning in Vision-Language Models via Aligned Model Merging","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:42.124288Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2506.03189"},"observation_digest":"sha256:902868bd11117c3792c2586d3b852fc70c8306b7ec57856c89c35f4df08a4a49","observation_id":"d49cf55c-dda8-4fe0-b900-f4b74541a716","resolution":{"observed_at":"2026-08-07T12:13:42.124288Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-07T11:12:18.728444Z","title":"Preprint, arXiv:2204.03044","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.03489","last_updated":"2025-06-04T02:11:54Z","snapshot_observed_at":"2026-08-07T10:59:30.930729Z","submitted_at":"2025-06-04T02:11:54Z","title":"EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T11:12:18.728444Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2506.03489"},"observation_digest":"sha256:520fecdf10508a5a0927f50a20faa697da30150ddc056b5db81e44376bf3ac0e","observation_id":"d8000de7-f1b4-4d29-be6c-215df84ba17c","resolution":{"observed_at":"2026-08-07T11:12:18.728444Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-06T22:41:50.072985Z","title":"Fusing finetuned models for better pretraining","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20989","last_updated":"2025-06-26T04:06:20Z","snapshot_observed_at":"2026-08-08T09:37:17.501553Z","submitted_at":"2025-06-26T04:06:20Z","title":"Can Gradient Descent Simulate Prompting?","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T22:41:50.072985Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2506.20989"},"observation_digest":"sha256:d0934adb0ebb27b2544e3311c480c57579c31a4291120f63a94a97d481232cbd","observation_id":"a52abf27-fc54-4ed7-9a75-32d122743ea3","resolution":{"observed_at":"2026-08-06T22:41:50.072985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-06T19:44:51.637129Z","title":"Fusing finetuned models for better pretraining","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04790","last_updated":"2025-07-25T06:46:34Z","snapshot_observed_at":"2026-08-07T01:04:12.654339Z","submitted_at":"2025-07-07T09:11:45Z","title":"Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T19:44:51.637129Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2507.04790"},"observation_digest":"sha256:c65ad64b8951002794d645cfd7ed9eeb41cfe5b7b9c3cc123584cd2f8c1ad807","observation_id":"65c13c57-c054-49a5-96e5-bbb535b3b57c","resolution":{"observed_at":"2026-08-06T19:44:51.637129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-05T17:34:47.375954Z","title":"Fusing finetuned models for better pretraining.ArXiv preprint, abs/2204.03044, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16084","last_updated":"2025-08-22T04:20:58Z","snapshot_observed_at":"2026-08-05T17:34:46.481598Z","submitted_at":"2025-08-22T04:20:58Z","title":"Intrinsic Strain-Driven Topological Evolution in SrRuO3 via Flexural Strain Engineering","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T17:34:47.375954Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2508.16084"},"observation_digest":"sha256:6facc92b2a1a142368964e1bb5b0789c4cf61774898a00ca47f704ed77e5a497","observation_id":"295b61a0-2880-470d-940d-42cf7fcf8e39","resolution":{"observed_at":"2026-08-05T17:34:47.375954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-02T23:56:45.528223Z","title":"Antypas, D., Ushio, A., Camacho-Collados, J., Neves, L., Silva, V ., and Barbieri, F","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.12323","last_updated":"2026-07-08T02:28:44Z","snapshot_observed_at":"2026-08-07T11:55:49.583707Z","submitted_at":"2026-02-12T18:59:20Z","title":"The Appeal and Reality of Recycling LoRAs with Adaptive Merging","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T23:56:45.528223Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2602.12323"},"observation_digest":"sha256:5d722ffe89a33eb19f41fd7939bc363e0e3a895bbe9f674b9794dcbf887ded7b","observation_id":"5e3cbcc5-074e-484f-b140-49689d8f5f3c","resolution":{"observed_at":"2026-08-02T23:56:45.528223Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":"2204.03044","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fusing finetuned models for better pretraining","venue":null,"work_id":"28f3736c-8f57-47c1-8b13-23c608cec53c","year":2022},"citing_paper":{"arxiv_id":"2604.02633","last_updated":"2026-04-03T01:58:11Z","snapshot_observed_at":"2026-08-03T20:03:31.464232Z","submitted_at":"2026-04-03T01:58:11Z","title":"Analytic Drift Resister for Non-Exemplar Continual Graph Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-13T20:51:47.676754Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2604.02633"},"observation_digest":"sha256:9e489d7a8bc6c5d2e97c2bd8d737b85fb534294e78cb39ebb6013a76b2832391","observation_id":"64880164-db46-4d59-b83f-ea3b4fb50de0","resolution":{"observed_at":"2026-05-13T20:53:15.700447Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":"2204.03044","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fusing finetuned models for better pretraining","venue":null,"work_id":"28f3736c-8f57-47c1-8b13-23c608cec53c","year":2022},"citing_paper":{"arxiv_id":"2604.22823","last_updated":"2026-07-13T15:11:18Z","snapshot_observed_at":"2026-08-07T22:24:37.598492Z","submitted_at":"2026-04-18T09:38:03Z","title":"PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T07:04:54.909073Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2604.22823"},"observation_digest":"sha256:f837ba6a1546f5efccf3c6b7d2d3468fb83059f93e076ea9a6d409acbc6e80b0","observation_id":"adaf1cd7-fd64-433d-83b6-9e20613a9944","resolution":{"observed_at":"2026-05-10T07:06:52.909218Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-01T17:56:04.574109Z","title":"arXiv preprint arXiv:2204.03044 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17467","last_updated":"2026-07-20T01:45:37Z","snapshot_observed_at":"2026-08-07T01:33:41.602612Z","submitted_at":"2026-07-20T01:45:37Z","title":"DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T17:56:04.574109Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2607.17467"},"observation_digest":"sha256:68fb785ac7ad8d4908623bd532ad829d98733bdecad36a025c9eb653d2135f6d","observation_id":"c386dfe4-c99a-433e-a536-ba517763283d","resolution":{"observed_at":"2026-08-01T17:56:04.574109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2204.03044/citation-record","integrity":"/paper/2204.03044/integrity","json":"/paper/2204.03044/citation-record.json","paper":"/paper/2204.03044"},"outbound":[],"paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T18:37:24.892453Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 12 inbound Pith citation observations for arXiv:2204.03044."}