{"as_of":"2026-08-13T14:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1efd8d98e36fe44e145c25794cedc6743ab03e101e8e94a9c02db21cffb5640b","coverage":[{"denominator":67,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":67,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:40:20.188081Z","state":"measured"},{"denominator":67,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":67,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2507.10355/citation-record","integrity":"/paper/2507.10355/integrity","json":"/paper/2507.10355/citation-record.json","paper":"/paper/2507.10355"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:21.026982Z","title":"What does a platypus look like? generating customized prompts for zero-shot image classification,","venue":null,"work_id":"f440cb9f-da64-4bec-b86a-0d8b74819d7d","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.912047Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:6235f66814e8e62906ad5afc1c21c392f07a48d1d7f0cfe60f2eda07afaf02b6","observation_id":"de57b22c-8c5d-4ce1-ae76-c300043be162","resolution":{"observed_at":"2026-08-06T17:40:21.030960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:21.013720Z","title":"Graphadapter: Tuning vision-language models with dual knowledge graph,","venue":null,"work_id":"b890a9d4-7a36-4cce-ab9b-e523aab2d5fc","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.916768Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:f4418ed7f9066a536334445fcfeab7cf9582a7a5528b14265e44ed47c59b5fa3","observation_id":"b5e08e7f-3eba-46f1-9b5d-f3e3be85d263","resolution":{"observed_at":"2026-08-06T17:40:21.018321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T17:40:19.921219Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.921219Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:03ad6a3c4754a951196806ef8e698cb74850beb83944d6a6192ee5e1ad7f298c","observation_id":"74d72df5-7c83-4d29-8944-be26b673665b","resolution":{"observed_at":"2026-08-06T17:40:19.921219Z","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":"2026-08-06T17:40:19.926230Z","title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.926230Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:b0a33c29b5fc7c07b1d2b8826e48106b01d3f575df518e7d02dfde0b12c48a1e","observation_id":"62d82a11-d9fd-4603-aba5-0264de000694","resolution":{"observed_at":"2026-08-06T17:40:19.926230Z","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":"2026-08-06T17:40:19.931254Z","title":"Blip-2: Bootstrapping language- image pre-training with frozen image encoders and large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.931254Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:441c919c3ef081bd15ed771bde661e6631fb87a85f09b28937319d87dc62b7bd","observation_id":"78e83ebf-037e-4b73-9a10-98e7a9e10f75","resolution":{"observed_at":"2026-08-06T17:40:19.931254Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.976466Z","title":"Calip: Zero-shot enhancement of clip with parameter-free attention,","venue":null,"work_id":"2b189301-4921-41b9-bc0f-c2ce16ac6e05","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.935319Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:93fc6306e1660166541f417cb0236d9f0dbc3e312c11677de1cdb55d3fd8559d","observation_id":"72d697b9-8cc2-437f-8fb1-546eabb3a106","resolution":{"observed_at":"2026-08-06T17:40:20.981291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.963403Z","title":"SuS-X: Training-free name- only transfer of vision-language models,","venue":null,"work_id":"bd024e99-10b0-48ef-a1a9-bc1dc2d6b852","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.939824Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:2442402486e9ba63041e8a8e856c03f5b1c125486e0eb4b5c81f86fe16da7108","observation_id":"9cff2d18-22bc-4981-a1e6-bda52d3e1969","resolution":{"observed_at":"2026-08-06T17:40:20.968107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T17:40:19.944342Z","title":"Learning to prompt for vision- language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.944342Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:2ed82993a853110df105325ca03fe762b39dc37b4e6cc019a28014cf908283e3","observation_id":"eb5ae94e-4d6b-4a5b-a12e-7180630be493","resolution":{"observed_at":"2026-08-06T17:40:19.944342Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.940657Z","title":"How does fine-tuning impact out-of-distribution de- tection for vision-language models?","venue":null,"work_id":"8ebaac48-bd44-4196-b7db-64f7559ed45b","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.948289Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:20310024ecd3ddefdaf5bdf5d7c2a6babdd185858fb1ba13ee5179876d590063","observation_id":"4208fa22-5514-4f0e-92d7-e6d278b42f62","resolution":{"observed_at":"2026-08-06T17:40:20.945716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.928815Z","title":"Ifseg: Image-free se- mantic segmentation via vision-language model,","venue":null,"work_id":"6e763fcd-f312-444a-b032-8f04358ccae5","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.951977Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:a5fa9835f6c123010fa0eda4e665697ef0c6091b945639f293d399a974dfd7ad","observation_id":"d0e263c2-3ae8-4625-b36a-39159159e592","resolution":{"observed_at":"2026-08-06T17:40:20.932912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.916313Z","title":"Robust fine-tuning of zero-shot models,","venue":null,"work_id":"574fcd4c-d34a-4ecf-9985-06fa10f7eea7","year":2022},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.955664Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:ad4315e5823d3db014008943e20db33738ea3337881ab510d09ba05630818b9e","observation_id":"fbd45ba8-3991-45f8-a6bf-0005b08040d8","resolution":{"observed_at":"2026-08-06T17:40:20.920473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.902935Z","title":"Fd-align: feature discrimination alignment for fine-tuning pre-trained models in few-shot learning,","venue":null,"work_id":"ff4dbd0e-c7f9-4aca-a27d-63e90a3e2686","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.959570Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:33ea2d164bca559ba71e369c8fca896822a43173aeaa5488dbb026dcc9b2ee9b","observation_id":"2763ae62-1eda-4fbc-97c6-8985e0517100","resolution":{"observed_at":"2026-08-06T17:40:20.907630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.890371Z","title":"Conditional prompt learning for vision-language models,","venue":null,"work_id":"a8d96b90-365a-48c1-8525-fc604140bb3a","year":2022},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.963233Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:dc254cbe7537c098bfc9e331779ef3753d12bf76080c996b9ebdc95f0f490878","observation_id":"bc8d34c3-d22d-4dc5-b6c7-696aaf6888fb","resolution":{"observed_at":"2026-08-06T17:40:20.894572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.876772Z","title":"Prompt distribution learning,","venue":null,"work_id":"86ecd449-70c7-4824-af70-1e6f4d7107e6","year":2022},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.967026Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:4a39a1b98f278f222584d38e8766d05f400169a7bd9a797cd2667ac452e405a5","observation_id":"c763bd71-9463-46b4-9014-ed41b54fc979","resolution":{"observed_at":"2026-08-06T17:40:20.881569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.862408Z","title":"Bi-modality individual- aware prompt tuning for visual-language model,","venue":null,"work_id":"752c41db-1613-4b77-ac1a-d7fcc5ebd718","year":2025},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.970906Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:58296b7c40e58a8ef2d3ea51dce81d4950d29b91301d148f03b41fb9226f94c0","observation_id":"2fe3295f-5c99-4107-bf27-394bc184faea","resolution":{"observed_at":"2026-08-06T17:40:20.867194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.847682Z","title":"CLIP-Adapter: Better vision-language models with feature adapters,","venue":null,"work_id":"3f5d4c3f-4e3d-4d91-ba62-2f73d4fc5bb3","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.975117Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:ad288ac1a5e0e9442dd612add466a9a3f61cab322a4b3c3805ab0f9b32ae9904","observation_id":"f0a59908-75b1-4453-af3e-e31531fef912","resolution":{"observed_at":"2026-08-06T17:40:20.852801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.833275Z","title":"Tip-Adapter: Training-free adaption of clip for few-shot classification,","venue":null,"work_id":"a78fd21b-860d-4217-8363-c89b18aa0c91","year":2022},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.979790Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:33a225c27f36a73a5e7873a28f23e7832e30ca3dec6b54956a951912b8024516","observation_id":"621dcda8-7c8e-43b0-b1a5-b98227ca29b1","resolution":{"observed_at":"2026-08-06T17:40:20.838281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.819591Z","title":"Task residual for tuning vision-language models,","venue":null,"work_id":"fb3233e9-50dd-4394-9c81-51082c4094fe","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.984156Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:8103e98cb39bbf98fdf46f554741d9c24045cb4b4db220d1b5af9426f8f2ecdc","observation_id":"a1bc1388-fb2d-4e51-b599-c740d65bb528","resolution":{"observed_at":"2026-08-06T17:40:20.824331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.806825Z","title":"Tun- ing vision-language models with multiple prototypes clustering,","venue":null,"work_id":"859e5a1c-38e1-40a7-8adf-d572999face5","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.988796Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:d8d7e37c9c25eaa559defc549a9f6387d1e4eddf45d3627b71c59ce6686fafec","observation_id":"b9861b66-adeb-44f0-85b4-dfcd3d4b40d3","resolution":{"observed_at":"2026-08-06T17:40:20.811154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.793830Z","title":"Mma: Multi-modal adapter for vision-language models,","venue":null,"work_id":"1446a978-fc0f-4c31-81cd-ec9d3082d337","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.992374Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:00ad3df331241eda29034c18d419ab43222af00c7d4e2053b2cf0d66a9a547b7","observation_id":"a0abee12-5fb7-48c1-a618-e54d1662dd74","resolution":{"observed_at":"2026-08-06T17:40:20.798368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T17:40:19.996569Z","title":"Maple: Multi-modal prompt learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:19.996569Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:a34f4558e5207c200a5ba79fb378574036bb565bb94c987ae361df6768c573d9","observation_id":"7ae46e8a-a692-4ad9-b72a-24c1835d4e3a","resolution":{"observed_at":"2026-08-06T17:40:19.996569Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.773794Z","title":"Bayesian prompt learn- ing for image-language model generalization,","venue":null,"work_id":"89aa8714-5af3-44e9-a8ce-d12863b72dcf","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.000820Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:9bf40cfbf3358325fe97719f23afb7867166004d355689dcb1b79696e5a16c2b","observation_id":"7a2c8570-ec0b-4971-8052-fac50d36a179","resolution":{"observed_at":"2026-08-06T17:40:20.777985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.762259Z","title":"Promp- tkd: Unsupervised prompt distillation for vision-language models,","venue":null,"work_id":"63aaec5e-170d-4c93-ba72-cfc5e9d3f12e","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.004565Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:42e2ffce3a82c88223085a69f5ca73012cefec747a2647c30ad48dba63d909a4","observation_id":"17fcd0a4-19d9-4ce1-aa73-15cc0844ee7f","resolution":{"observed_at":"2026-08-06T17:40:20.765899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.749839Z","title":"Prompt, generate, then cache: Cascade of foundation models makes strong few-shot learners,","venue":null,"work_id":"1dd6678b-0f0e-4a07-9ed1-2dffad4f8a9d","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.008701Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:e04088f750cbd7eed8207bfbbaefe367c9cff770e38218894e240c6f8a566257","observation_id":"d91e5c7e-a01f-47eb-84e2-b61694f19b01","resolution":{"observed_at":"2026-08-06T17:40:20.753742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.737025Z","title":"Textrefiner: Internal visual feature as efficient refiner for vision-language models prompt tun- ing,","venue":null,"work_id":"80104cf0-82f1-45ae-b656-e5a860742002","year":2025},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.012959Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:61b8eb1a6af6297cbcf114fceafbd6fd097385e83c5cfce7de4b0ffbeb2a3062","observation_id":"19b64a73-6e9b-4cdc-b36f-13b7b390dae2","resolution":{"observed_at":"2026-08-06T17:40:20.741459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.724611Z","title":"Learning with enriched inductive biases for vision-language models,","venue":null,"work_id":"305506a0-2e5b-4fd2-8552-c58f41149b2d","year":2025},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.016704Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:f37a13795e677753f3b82f133a80695bc897e4e41e2f2ad51269a5163dfc1ec1","observation_id":"65f12372-ebec-4c7d-82ed-b3aa8b8175fa","resolution":{"observed_at":"2026-08-06T17:40:20.729067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.07854","last_updated":"2024-10-10T12:20:58Z","snapshot_observed_at":"2026-08-12T22:26:23.632286Z","submitted_at":"2024-10-10T12:20:58Z","title":"HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adapter","version":1},"cited_work":{"arxiv_id":"2410.07854","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.07854","snapshot_observed_at":"2026-08-06T17:40:20.257052Z","title":"HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adapter","venue":"cs.CV","work_id":"79aff30e-8b5b-44ab-a72a-914765b0402d","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.020566Z"},"links":{"cited_paper":"/paper/2410.07854","citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:c870f7c5536ebb1d9440d14788bb4fe87b283c07f8621a4a0e43c1f11606ad55","observation_id":"d881c119-adbc-45fe-869e-a1fc71f54473","resolution":{"observed_at":"2026-08-06T17:40:20.264296Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.712703Z","title":"Language models are few-shot learners,","venue":null,"work_id":"7faa0d29-0fc4-4cde-b2ff-2358fe42a531","year":2020},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.025331Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:3e1ea476185060af65937d64b51843bafc93118d4d2bc9e4f5f241bc34554d0f","observation_id":"9bdf151f-4e73-4bc4-9f78-7f7775487183","resolution":{"observed_at":"2026-08-06T17:40:20.716765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.700438Z","title":"Amu-tuning: Effective logit bias for clip-based few-shot learning,","venue":null,"work_id":"af681d95-65b7-476e-8a27-ffd1ad4a747a","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.030098Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:923ce275850204e0fcd71917bd39e180cbcaf12b2f5c440ef5f81550da4668ad","observation_id":"ac44985e-ee15-4ba4-9d0c-8c88891deb45","resolution":{"observed_at":"2026-08-06T17:40:20.704870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.688941Z","title":"Bayesian exploration of pre- trained models for low-shot image classification,","venue":null,"work_id":"6e2a675c-59a9-4f1e-969e-9511fb3638fa","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.034478Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:5a8101fa8628c30341641bacd59de6b55719e7ccdf10b9d2e532408dee6f6940","observation_id":"99ecb6fa-9f42-4b1e-ae9c-dcb7d915cf17","resolution":{"observed_at":"2026-08-06T17:40:20.692807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.675531Z","title":"An empirical study of training self- supervised vision transformers,","venue":null,"work_id":"642cf1ab-ee83-4cfd-becf-fd904201e028","year":2021},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.038412Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:f80f2d50d452cf98bd85c879ca9f2c350673f5e7b8f9fef131ebc3dfa14df78b","observation_id":"c0b3f15c-e064-4935-b285-7d8f60ec83b9","resolution":{"observed_at":"2026-08-06T17:40:20.679790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.662631Z","title":"Emerging properties in self-supervised vision transformers,","venue":null,"work_id":"ab43d3a7-bdc7-4ebc-9a5c-609068ed71c1","year":2021},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.043192Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:05298f1122a4d0b746c06a37db9cbc0a7f962427b6851278748f79dd951d2b8a","observation_id":"dead694a-1752-4f15-87dc-85c93540e45f","resolution":{"observed_at":"2026-08-06T17:40:20.667234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07745","last_updated":"2022-10-18T07:20:28Z","snapshot_observed_at":"2026-08-13T14:05:08.486071Z","submitted_at":"2022-10-14T12:32:50Z","title":"Confidence estimation of classification based on the distribution of the neural network output layer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.07745","snapshot_observed_at":"2026-08-06T17:40:20.047024Z","title":"Confidence estimation of classification based on the distribution of the neural network output layer,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.047024Z"},"links":{"cited_paper":"/paper/2210.07745","citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:3e5252083b94bc040ea024faeba076926156f5ad8ea9b5f3c2d15115a75bae17","observation_id":"cfca35aa-fc47-4649-b931-9b8e6f41b300","resolution":{"observed_at":"2026-08-06T17:40:20.047024Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.649817Z","title":"Zero-shot text-to-image generation,","venue":null,"work_id":"4639dc55-da5f-411d-900e-01535068e817","year":2021},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.050922Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:897abbab244ea884bd3fe5f080dce14118d5b1b3c798f136938d0b05a5dd3368","observation_id":"a0fe5ce4-2127-426d-ae79-9ca282f58bf2","resolution":{"observed_at":"2026-08-06T17:40:20.654069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.636785Z","title":"Distribution-aware prompt tuning for vision-language models,","venue":null,"work_id":"7e970942-1f32-4f9e-9dc5-daca4f1b1a9e","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.054779Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:bf05ed01e60bc53315f387102770054d940eeabfcb4133edbc0657fc393003a7","observation_id":"e024f651-a261-4238-a268-e29f5023a4af","resolution":{"observed_at":"2026-08-06T17:40:20.641102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.622828Z","title":"Make prompts adaptable: Bayesian modeling for vision-language prompt learning with data-dependent prior,","venue":null,"work_id":"7378c27f-2a0b-4234-9888-e85063ffb947","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.059170Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:658edd9fbfd8b4778b72e0c9cf039935b1a95bac73d73e871d3c06ac02701b36","observation_id":"626481ba-2516-4635-8149-4665a3e7d232","resolution":{"observed_at":"2026-08-06T17:40:20.627428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.609096Z","title":"Any- shift prompting for generalization over distributions,","venue":null,"work_id":"b5bb9954-8448-4999-b27c-a9e9bc7960b3","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.062775Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:197b1e7d338677037e29d969979a861b1cc686b1b6ee87a395e45b9e16200162","observation_id":"f1acd2aa-6bac-4df7-82e7-c83a06151fec","resolution":{"observed_at":"2026-08-06T17:40:20.614098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T17:40:20.067433Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.067433Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:5e1c4f65a5c54922598fc2206004eea14be093d472af022cfb81c1ae9b09067f","observation_id":"07151d1e-b922-4dce-803b-e3022a1ab53c","resolution":{"observed_at":"2026-08-06T17:40:20.067433Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.588779Z","title":"Graph attention networks,","venue":null,"work_id":"53efd952-4a45-492e-b20d-c3c6932cba62","year":2018},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.071362Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:f411ca5000072a4f3d99998be039bc82d75373c0ae74f1bd34612334ef5c22d3","observation_id":"a40d6f41-efc9-4134-bd70-ad82099e0ffc","resolution":{"observed_at":"2026-08-06T17:40:20.592710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.575444Z","title":"Label propagation for zero-shot classifi- cation with vision-language models,","venue":null,"work_id":"a74e47df-21e9-43d6-8187-ccd1bf7ad7f7","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.075095Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:05df724bac7f0772f032e597d42b101f591ae4aed02774f3a669005d8e5fa780","observation_id":"f6c04757-e4db-49ea-be4c-048743ae0e4c","resolution":{"observed_at":"2026-08-06T17:40:20.580088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.562655Z","title":"Efficient and context- aware label propagation for zero-/few-shot training-free adaptation of vision-language model,","venue":null,"work_id":"c9aab4e4-a1c5-48d6-b69e-35d0ffe63483","year":2025},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.079073Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:2e1b4d1e831a4502af40e23129a552837e5dc6335e80dc3e4884503ec530c328","observation_id":"6c46f470-ba1a-4b70-a198-0cfa90c299d1","resolution":{"observed_at":"2026-08-06T17:40:20.566841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.550487Z","title":"On vertex, edge, and vertex-edge random graphs,","venue":null,"work_id":"542c9cef-7171-422d-9be4-2f12f771f36d","year":2011},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.082907Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:49c0a45ad9cc9b8c60b3ae8470d96446d66fe99be5731b14e859d2d118ad893e","observation_id":"94c27a01-7823-4b9c-a30a-4ad5e7ff8b0f","resolution":{"observed_at":"2026-08-06T17:40:20.554720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.537554Z","title":"Awt: Transferring vision- language models via augmentation, weighting, and transportation,","venue":null,"work_id":"eb628c32-f0fb-4ca7-b3d7-6a69ebfb895b","year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.086790Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:cb682c671162a8ffdac105f34ed90fa5223d7301193f483a7bcd10c445b4037c","observation_id":"5145878c-1b27-4794-9089-e7f25853b195","resolution":{"observed_at":"2026-08-06T17:40:20.542028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.524505Z","title":"Robust graph convolutional networks against adversarial attacks,","venue":null,"work_id":"63d7aeee-2f10-489b-b8f6-aba8e688bbab","year":2019},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.090979Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:db799852206c726399b774c8a652de54ef375fb9ccf05c3704a331fe648a456a","observation_id":"e08ca986-1356-4d83-9d48-6758526b53ed","resolution":{"observed_at":"2026-08-06T17:40:20.529188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.510616Z","title":"Auto-encoding variational bayes,","venue":null,"work_id":"a8d4b19f-d080-4aa4-a6a1-cdff935b0460","year":2014},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.094835Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:7c24fd5e33cf72fdecfaaacb300e64d786932545b3961060b90f5ba89c91b6c0","observation_id":"1dcbb162-ce93-49d3-8c85-43774820ed12","resolution":{"observed_at":"2026-08-06T17:40:20.515562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.497829Z","title":"ImageNet: A large-scale hierarchical image database,","venue":null,"work_id":"30b26ef3-5c4b-476a-a1bc-e034aceaf4c5","year":2009},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.098615Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:787c3d8b05ffaecddcae0653fcf1059ed381c3f344ff5cf12cf3be7da87047cc","observation_id":"b9d979d3-05d2-428a-aa2a-46163a9db8ca","resolution":{"observed_at":"2026-08-06T17:40:20.501871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.484679Z","title":"3D object representations for fine-grained categorization,","venue":null,"work_id":"310511a7-fa17-4658-8d3a-02662b55394e","year":2013},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.102928Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:9220b8c5fd48564793b43e2320395a029f4ead9893e8e4dea66701c6c1b45773","observation_id":"72d3fb14-5ade-43ae-9545-5e6bb452a3de","resolution":{"observed_at":"2026-08-06T17:40:20.489414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.471497Z","title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories,","venue":null,"work_id":"28904ed6-aeec-4514-a607-50e2acae3adc","year":2004},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.107253Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:c66efa2852ffd0fd40376a7f754203c509edc691bf5ceb0ab286be44718be598","observation_id":"4659af24-202c-4b8b-a348-e08f06da3468","resolution":{"observed_at":"2026-08-06T17:40:20.475953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-08-12T17:34:19.526460Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-08-06T17:40:20.111340Z","title":"UCF101: A dataset of 101 human actions classes from videos in the wild,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.111340Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:37d9b5ac5876345ad2c81fd73bc30de51da0bfb6009ecacea68253e1a91ee2e6","observation_id":"afb68314-928b-44ca-a59d-7183acb62f16","resolution":{"observed_at":"2026-08-06T17:40:20.111340Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.458399Z","title":"Automated flower classification over a large number of classes,","venue":null,"work_id":"82763da3-a26c-4b7b-9ae3-ff38761963cb","year":2008},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.115592Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:22a2f787c3ef9c8e2421708b140b586e1ce80ac3466cba3e562ebbd87fcb19de","observation_id":"37e50d15-cf39-4f83-a511-038e23146e03","resolution":{"observed_at":"2026-08-06T17:40:20.463296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.445966Z","title":"Food-101–Mining discriminative components with random forests,","venue":null,"work_id":"3007020f-7751-4566-9cbc-45c2dab47353","year":2014},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.119558Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:566357c224f8318b45411d137380d4166d3d83c1a57777bd17e5afd87d1f7e2e","observation_id":"d03c106e-142c-4aef-9d9e-53cbd0dbbc04","resolution":{"observed_at":"2026-08-06T17:40:20.450374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.431262Z","title":"Describing textures in the wild,","venue":null,"work_id":"f88012b1-dcad-431c-ad99-c82ba8741eb7","year":2014},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.123963Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:a48884b3978931fecc250ac6585109bcbcf2103f9854687c63fc336240a2b11c","observation_id":"3247b07b-9a99-49fa-b3a1-4a5f47ccdc93","resolution":{"observed_at":"2026-08-06T17:40:20.436414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.418447Z","title":"EuroSAT: A novel dataset and deep learning benchmark for land use and land cover classi- fication,","venue":null,"work_id":"9f2921a0-aa5a-4cc3-b3a5-e4d466d1767b","year":2019},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.129073Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:6f3e3396ef3ae762516064577ff65d25f7b3d8aa4174f7585f18a3106b657008","observation_id":"d122b2e1-e46f-4327-8293-1482adc8fd2b","resolution":{"observed_at":"2026-08-06T17:40:20.422467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1306.5151","last_updated":"2013-06-21T14:31:57Z","snapshot_observed_at":"2026-08-12T17:35:23.022229Z","submitted_at":"2013-06-21T14:31:57Z","title":"Fine-Grained Visual Classification of Aircraft","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1306.5151","snapshot_observed_at":"2026-08-06T17:40:20.133393Z","title":"Fine- grained visual classification of aircraft,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.133393Z"},"links":{"cited_paper":"/paper/1306.5151","citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:fce7f6adb38b0b7c09522efbece172eed57733c4b065bbf748c52152421efb24","observation_id":"ec090b06-3f27-4a74-bf04-9ed5282e7c15","resolution":{"observed_at":"2026-08-06T17:40:20.133393Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.406055Z","title":"Cats and dogs,","venue":null,"work_id":"d3852689-7cb0-4438-adc2-995b40981cd6","year":2012},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.138636Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:0f1d78f5e9ab964f32b856f21c6567c7d79a1c15463bd6c4b3b9d3bdce7dd99e","observation_id":"81ae35f3-0ff4-4cf1-9456-d3c961d4e951","resolution":{"observed_at":"2026-08-06T17:40:20.410115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.392741Z","title":"SUN database: Large-scale scene recognition from abbey to zoo,","venue":null,"work_id":"4cb73621-27d6-45c5-977e-e794dd4b5c95","year":2010},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.143036Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:de07fcb54de7e62a1e8beda39728b367f6cdeaa5e88ed47ef141026f47781984","observation_id":"22f56489-b073-46cd-8ea3-a26b2dc95e2f","resolution":{"observed_at":"2026-08-06T17:40:20.397530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.379684Z","title":"Do ImageNet classifiers generalize to ImageNet?","venue":null,"work_id":"b5ecaa36-5fff-473c-8bf9-2e973a690030","year":2019},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.147173Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:4f7b163f5f5d3987a9b6da83c1ab32c48ab23f717fbc596f49ea86e1e1084ef4","observation_id":"cca564c6-c9bb-46d0-bd36-6ebba2a5625f","resolution":{"observed_at":"2026-08-06T17:40:20.384108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.365541Z","title":"Learning robust global representations by penalizing local predictive power,","venue":null,"work_id":"35912f16-c3f7-4ffa-b2df-ea9725db86aa","year":2019},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.151718Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:2b35d03d3565525db10a6eff95cfa1447cfddebb0815ea7825ec0287a153bcfc","observation_id":"e1315614-e63f-47ff-a76f-9ada628e834f","resolution":{"observed_at":"2026-08-06T17:40:20.370319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T17:40:20.155515Z","title":"Decoupled weight decay regularization,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.155515Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:4a9d4189ed9bd53b0cf53244a93cfc48e1091eb2e79f7a9c728550429eb8922c","observation_id":"bb70465c-65f0-4722-9434-23ba0b5855a4","resolution":{"observed_at":"2026-08-06T17:40:20.155515Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.345543Z","title":"Fast and accurate deep network learning by exponential linear units (elus),","venue":null,"work_id":"09acd498-f632-4f80-9c49-d5ba9b0a522d","year":2016},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.159644Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:3bf079265a9239cd055a8352fa2a2116298bf2c5d6b4ae59d7c9bd671447e961","observation_id":"f34211da-cd94-427d-9ac5-7cde4029e13b","resolution":{"observed_at":"2026-08-06T17:40:20.349481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.332228Z","title":"Deep sparse rectifier neural networks,","venue":null,"work_id":"90e1bdc2-264e-41fe-b442-03d0f00b0f2d","year":2011},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.164215Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:67a139d943689e5c3c0437cc4bc44d57e473fd4a59c6b8e60ef0148a72787039","observation_id":"2daa355c-8c49-41a4-b238-72345483e0d3","resolution":{"observed_at":"2026-08-06T17:40:20.336877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T17:40:20.167898Z","title":"Dual memory networks: A versatile adaptation approach for vision-language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.167898Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:bdc4b946ffbae1356d10406883f99003dfd32611936e210dda25496f62337e89","observation_id":"5c3ada0e-c6a9-4576-9016-7a20791c7194","resolution":{"observed_at":"2026-08-06T17:40:20.167898Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.310914Z","title":"Self-regulating prompts: Foundational model adaptation without forgetting,","venue":null,"work_id":"fec2df3a-84a0-4ea8-ae06-f515997cd1de","year":2023},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.172352Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:6b85bf79abd94016ab94a2c10ba3e0b42accc859e67b7a61de4f232b6de107f2","observation_id":"67ccdd2a-3835-41dd-a1a0-0a25b6aa03be","resolution":{"observed_at":"2026-08-06T17:40:20.316158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:40:20.297817Z","title":"Mmrl: Multi-modal representation learning for vision-language models,","venue":null,"work_id":"d6a20f1d-62ef-4e96-a30d-aeae7b8e0f0b","year":2025},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.176025Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:d505e64974948c4c75bc7ef4143205cd908b199bb58b8e45f7734acb503ac370","observation_id":"6be451df-fd56-4d00-9d65-6e7e9d3a64a1","resolution":{"observed_at":"2026-08-06T17:40:20.302423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T17:40:20.179874Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.179874Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:aa6eb64cc96a992d0634170327dd2045507a497c8a54b79cd722be13f46a0d6d","observation_id":"23c56b72-9680-43c8-ac15-4be9e45861b3","resolution":{"observed_at":"2026-08-06T17:40:20.179874Z","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":"2026-08-06T17:40:20.183643Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.183643Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:51377d9a73ee0995136a8f70f74dc80172af10d9a9ee1bca33ad9c6b058608cc","observation_id":"d7c59d34-b84d-405e-a456-c842f5eba013","resolution":{"observed_at":"2026-08-06T17:40:20.183643Z","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":"2026-08-06T17:40:20.188081Z","title":"Visualizing data using t-sne","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T17:40:20.188081Z"},"links":{"citing_paper":"/paper/2507.10355"},"observation_digest":"sha256:f0d7690a6f1ef04bd8f964452c9934658d85f09c647b6b08575f757dd6e2de49","observation_id":"3a0cf025-8fdd-4c61-9bcc-f14d3d026119","resolution":{"observed_at":"2026-08-06T17:40:20.188081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.10355","last_updated":"2025-07-14T14:56:49Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T13:14:19.473042Z","submitted_at":"2025-07-14T14:56:49Z","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter"},"reference_resolution":{"displayed":67,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":1,"verified_fuzzy":52},"total_outbound_references":67},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 0 inbound Pith citation observations for arXiv:2507.10355."}