{"as_of":"2026-08-13T15:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9746ffdd3df1894ae305e45ffd5c6486b659089205c1290f6f95f18284579fe4","coverage":[{"denominator":76,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":76,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:12:36.191422Z","state":"measured"},{"denominator":76,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":76,"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/2506.19312/citation-record","integrity":"/paper/2506.19312/integrity","json":"/paper/2506.19312/citation-record.json","paper":"/paper/2506.19312"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:12:38.872563Z","title":"A4T: Hi- erarchical Affordance Detection for Transparent Ob- jects Depth Reconstruction and Manipulation,","venue":null,"work_id":"4026ab20-7d34-41af-9e75-15ea5339484a","year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:32.873889Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:ed58d098ea87617dda704316d9e9663a2026191df28aff57fad29c6109b874e8","observation_id":"0e00b700-2aba-4d11-b894-6736bb655ab2","resolution":{"observed_at":"2026-08-06T23:12:38.881383Z","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":"2026-08-06T23:12:38.849209Z","title":"Deep Affordance-Grounded Sensorimotor Ob- ject Recognition,","venue":null,"work_id":"8063e1b7-5c6b-42f0-aa81-132a2f573e4d","year":2017},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:32.977765Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:ff97ddc7dff05211f1b43c248591e3c8a44acae8f08f6b605e59641436d2050c","observation_id":"f5be5950-39e1-4bc5-8fd1-8155ba865d07","resolution":{"observed_at":"2026-08-06T23:12:38.858502Z","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":"2026-08-06T23:12:38.814744Z","title":"Af- fordance Transfer Learning for Human-Object Inter- action Detection,","venue":null,"work_id":"fb3c8c61-3437-47c8-ac6b-54fa74880f7b","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.059689Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:56d8ff1b2481dfe5f9973dd921d3f5e0c88c629d4960c22f66727285f06a9fb6","observation_id":"2dd4be0a-71ee-4226-aafe-e5e76fa50244","resolution":{"observed_at":"2026-08-06T23:12:38.823763Z","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":"2026-08-06T23:12:38.782329Z","title":"Pre- dicting 3D Human Dynamics From Video,","venue":null,"work_id":"63625dbd-2a16-45e4-bea7-260e2c619040","year":2019},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.137280Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:46badaa8ee63fd604c397e70f52c145bdb352b2665e44e68fdd35b178dc0efbe","observation_id":"389e5eeb-5ccf-4dd5-8426-db0ddb25339a","resolution":{"observed_at":"2026-08-06T23:12:38.794811Z","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":"2026-08-06T23:12:38.743530Z","title":"Predicting hu- man activities using stochastic grammar,","venue":null,"work_id":"3f6ca576-fc2a-4a02-8817-07b0a3ca7c93","year":2017},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.190698Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:c54c9be88055c5997b8b6c93cb0418d644af53a4e3c10f949b188aed5a4e256e","observation_id":"a05d1ed5-1aa2-40b1-a142-0aa2ba835007","resolution":{"observed_at":"2026-08-06T23:12:38.754420Z","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":"2026-08-06T23:12:38.716096Z","title":"Af- fordance grounding from demonstration video to tar- get image,","venue":null,"work_id":"f3b0e042-f9b4-48bd-ad10-f7097a617007","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.263651Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:e05dd855d486fa6e358566a94726cdf665af275eeb4b2c38525d6cce825f2510","observation_id":"f1576fad-b1d1-4a5e-8ca9-780480961cd8","resolution":{"observed_at":"2026-08-06T23:12:38.724545Z","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":"2026-08-06T23:12:38.688009Z","title":"Affor- dance Research in Developmental Robotics: A Sur- vey,","venue":null,"work_id":"2fa00d50-9771-4180-b429-9cbbfede33d3","year":2016},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.336516Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:81e0650beca7d297437c85fcd798c59d96b84e850611489d94627fde05927d0a","observation_id":"c46d9943-58af-46bd-bde5-b239c2804d45","resolution":{"observed_at":"2026-08-06T23:12:38.698748Z","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":"2026-08-06T23:12:38.657651Z","title":"A survey of visual affordance recognition based on deep learning,","venue":null,"work_id":"aad39c98-d2f9-47fd-b9bb-829a05f70fdb","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.388801Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:f46ad5818107c2c717a602f598b7a90cdc3f51672abc195a30a0c1a3e555e6a7","observation_id":"8bf83273-906d-4e23-8897-13e284478dbc","resolution":{"observed_at":"2026-08-06T23:12:38.665818Z","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":"2026-08-06T23:12:38.633393Z","title":"Visual affor- dance and function understanding: A survey,","venue":null,"work_id":"f61cda5e-2b9b-4b0c-bc64-9b8f94ee6252","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.479794Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:d2881208f4d04e06247275426e0e787ed42bc2320df4189976228c46122c156f","observation_id":"f6eca6ea-bb28-45c9-8b7f-3f60cd28631e","resolution":{"observed_at":"2026-08-06T23:12:38.641003Z","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":"2026-08-06T23:12:38.610196Z","title":"3d af- fordancenet: A benchmark for visual object affordance understanding,","venue":null,"work_id":"e23158f3-b736-4fcf-bc9d-1514023b6cbf","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.583208Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:5a706e0734e39444dcaf10c0ce1bd88588b35f4b93af8f3b917ab720fc43556c","observation_id":"813784fa-daec-491c-a1f9-f6578c10face","resolution":{"observed_at":"2026-08-06T23:12:38.616376Z","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":"2026-08-06T23:12:38.584935Z","title":"Open-vocabulary affordance detection in 3d point clouds,","venue":null,"work_id":"ac26a6e3-c8ce-4d18-8ddd-2753738c78ee","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.663850Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:90c9741b36d1c9d2860acff3b95f1ee86729fa02efe2b98b2d4cfd29e58cd2cc","observation_id":"98d5ca03-0004-47ee-9350-8570c1c539e8","resolution":{"observed_at":"2026-08-06T23:12:38.592290Z","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":"2026-08-06T23:12:38.558334Z","title":"3D ShapeNets: A Deep Representation for Volumetric Shapes,","venue":null,"work_id":"c5aa7deb-6839-471f-b857-0f461ce7fe2e","year":2015},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.739172Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:1242c85f979a523bd924b4260c2be58a1a1dc176ccc7fba3cacaf7ad7539efa2","observation_id":"b2c4ffa2-6fe9-4573-9326-8e627c69de51","resolution":{"observed_at":"2026-08-06T23:12:38.566059Z","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":"2026-08-06T23:12:38.530672Z","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data,","venue":null,"work_id":"94badc39-2e08-44bd-aa40-c70ea10b14d9","year":2019},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.808268Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:9660fb624a80da4351546622accde6ba2ac372ecbfc29c0f63b4c4a49ac06a90","observation_id":"3ea55269-ad29-4b67-90e8-00083640a5cb","resolution":{"observed_at":"2026-08-06T23:12:38.537935Z","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":"2026-08-06T23:12:38.493256Z","title":"Open-vocabulary affordance detection using knowledge distillation and text-point correlation,","venue":null,"work_id":"2cdc20c3-05ca-4b4f-9403-16dac1807ebb","year":2024},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.855478Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:e98052331f29c5b1e5a61c91a45e1b4f88f3b77f579288c22a3bc35e52fa169f","observation_id":"bf95c1f5-366f-4885-bb6a-63e5bcd915b8","resolution":{"observed_at":"2026-08-06T23:12:38.505981Z","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":"2026-08-06T23:12:38.462143Z","title":"Transductive zero-shot learning for 3d point cloud classification,","venue":null,"work_id":"adf7350a-4214-4cbf-9e72-568b7cd7788a","year":2020},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:33.937675Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:eb3ea7df206906f2c2d038f23b32133b1f8f150ba73775dbe3f4c0f05ce04902","observation_id":"e9dd02c6-a436-4616-bbbd-4f4f551fab21","resolution":{"observed_at":"2026-08-06T23:12:38.471404Z","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":"2026-08-06T23:12:38.427383Z","title":"Generative zero-shot learning for semantic seg- mentation of 3d point clouds,","venue":null,"work_id":"00d6e29a-5596-4830-baef-35e4a26d7874","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.005562Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:02cbe6f023eae94d853cd2213fa75b61fd96ed587fde5df9b27517244c8f84f6","observation_id":"80fc2dce-bb5f-49ff-85b9-25d0b9176321","resolution":{"observed_at":"2026-08-06T23:12:38.443595Z","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":"2026-08-06T23:12:38.219667Z","title":"Zero- shot learning of 3d point cloud objects,","venue":null,"work_id":"d622db9c-4164-49a8-8eee-e1d4f9a01ad0","year":2019},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.128479Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:22e4a947ac1f1eb406d09d30e56a67d9482dd5fb9eeb78e01edae1cc6a601dd4","observation_id":"d5f1b7c3-1438-46c2-8e2e-274e41e8e0f3","resolution":{"observed_at":"2026-08-06T23:12:38.226904Z","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":"2026-08-06T23:12:38.195014Z","title":"InstructBLIP 2: Extending Vision- Language Models with Fine-Grained Instruction Tun- ing,","venue":null,"work_id":"21bfbef9-6442-41cb-a57e-7c433b3e3b24","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.304562Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:38964bb9e47181c997d43fa9a4d0c8836311d7eea35347bb20a69a84540e81a3","observation_id":"8b689183-96d4-4da2-9204-4a9e5dacf1cc","resolution":{"observed_at":"2026-08-06T23:12:38.202062Z","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":"2026-08-06T23:12:38.165685Z","title":"Flamingo: A Visual Language Model for Few-Shot Learning,","venue":null,"work_id":"5d50f0ae-92d2-4596-96c6-4062ccfc2d8d","year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.442982Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:c19900f37d6daa3b5f0eb8f90853a37a1943a715764e449b0c27cb232dcf65f8","observation_id":"11b3a8ef-fa14-4743-b86d-63adb9ee50d6","resolution":{"observed_at":"2026-08-06T23:12:38.174695Z","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":"2026-08-06T23:12:38.143233Z","title":"Attention Is All You Need","venue":null,"work_id":"08df68c9-98a3-43e7-be83-ee37a4397343","year":null},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.573833Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:dd36b23a1e909f77fcc4c0f19ede040495479efcdb19dbc46db3ae4fb9a2cb5e","observation_id":"ebd797fc-6114-4351-ac9f-8f36949bda24","resolution":{"observed_at":"2026-08-06T23:12:38.149453Z","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":"2026-08-06T23:12:38.123504Z","title":"BERT: Pre-training of Deep Bidirectional Transform- ers for Language Understanding,","venue":null,"work_id":"d44b351d-447c-446c-8450-e9eb83440c23","year":2019},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.781753Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:64bd0ee8e26341b7203ad5584191138bc4345263ccc9f5478f89b6e66a18c160","observation_id":"3b9763ef-807e-4840-a6a8-7c0f2621be4b","resolution":{"observed_at":"2026-08-06T23:12:38.129739Z","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":"2203.15556","last_updated":"2022-03-29T13:38:03Z","snapshot_observed_at":"2026-08-09T19:52:33.533277Z","submitted_at":"2022-03-29T13:38:03Z","title":"Training Compute-Optimal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.15556","snapshot_observed_at":"2026-08-06T23:12:34.809052Z","title":"Training compute-optimal large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.809052Z"},"links":{"cited_paper":"/paper/2203.15556","citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:8c0041511729cdb7f8d785f77ef4921ffedaabccfdd02c40f24d826463259f0e","observation_id":"9fbd1cba-b91e-40cc-97ab-a764ad9fda82","resolution":{"observed_at":"2026-08-06T23:12:34.809052Z","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":"2026-08-06T23:12:38.093913Z","title":"Detecting object affordances with Convo- lutional Neural Networks,","venue":null,"work_id":"bf8a6365-826a-4655-bd6e-1d161f22c0fb","year":2016},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.876316Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:fb925bcf7bccb3fead7485b6f9152e574c586d3ef660b68b29d962eb4816a56e","observation_id":"c7af728e-d662-4ec5-8b10-a56cc6d4d560","resolution":{"observed_at":"2026-08-06T23:12:38.101474Z","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":"2026-08-06T23:12:38.067338Z","title":"Affordancenet: An end-to-end deep learning approach for object af- fordance detection,","venue":null,"work_id":"e490b6f6-b086-4457-bf89-7f2e4c446b57","year":2018},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.939060Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:839671acaa03eb7703c7cd95f850e5c88ba096a1070950930aae3ffe299d2de9","observation_id":"b456abc3-a3e0-484a-892e-1a8a1067aac0","resolution":{"observed_at":"2026-08-06T23:12:38.073919Z","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":"2026-08-06T23:12:38.031615Z","title":"Object-based affordances detection with Convolutional Neural Networks and dense Conditional Random Fields,","venue":null,"work_id":"a08cb2e0-db7c-4bef-8b04-f516c32da345","year":2017},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:34.954446Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:ae65dac8ee2e145529242872498a87b894a2da1425b221a19c5a0d964402c509","observation_id":"574333d8-32eb-43e7-949a-fd05802d09ea","resolution":{"observed_at":"2026-08-06T23:12:38.044353Z","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":"2026-08-06T23:12:37.990923Z","title":"A multi-scale cnn for af- fordance segmentation in rgb images,","venue":null,"work_id":"0c5d57b6-c32a-4572-b61f-f24c19af75ba","year":2016},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.004794Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:6a7191ab6b10e648fb57158147b8257535c520245e09d41a6cf273b95a7d855d","observation_id":"f65f59b2-e2e0-4dc8-b1ac-aab9b5560997","resolution":{"observed_at":"2026-08-06T23:12:37.997854Z","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":"2026-08-06T23:12:37.944636Z","title":"A deep learning approach to object affordance segmentation,","venue":null,"work_id":"ba7ff3ea-c756-4524-9f44-9c27aa73f67a","year":2020},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.062177Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:0a4ea43486520d949768fe6325c8d331a696d1450ac151b05754bcd533964444","observation_id":"a4fd111a-31f1-42ec-ba25-3ebf611e32ad","resolution":{"observed_at":"2026-08-06T23:12:37.951998Z","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":"2026-08-06T23:12:37.918415Z","title":"Cerberus transformer: Joint semantic, affordance and attribute parsing,","venue":null,"work_id":"4cf26499-032f-4da0-949e-97b9b0a9f6f5","year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.114698Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:a7c8e70e3245ecaf8f69d37020e1afd2e0fcaba7b24a0baa80834f2be6499ab2","observation_id":"e3ce8c61-2827-49d2-8c25-042c3b2444ed","resolution":{"observed_at":"2026-08-06T23:12:37.928066Z","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":"2026-08-06T23:12:37.883243Z","title":"Learning affordance grounding from exocentric im- ages,","venue":null,"work_id":"fe34e76c-89a4-4ae7-becf-ae7fe1e6663a","year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.141954Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:20cbd2d418a9e6901fd6d88ef416114f9c39d02c8ebe76401095574b5bb6df21","observation_id":"c237df84-8db4-4e9c-b5d6-76e8649a4621","resolution":{"observed_at":"2026-08-06T23:12:37.890230Z","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":"2026-08-06T23:12:37.852292Z","title":"Affordancellm: Grounding affordance from vision language models,","venue":null,"work_id":"1a8ba3cf-9da7-41ce-b54e-cf70ff34f9e7","year":2024},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.184090Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:6b86ccea292227709c5d155c22247cf30b3fc0ec8898ec1801fe61411a6d663f","observation_id":"555c8fcb-3714-4496-aca1-bce57ca6553b","resolution":{"observed_at":"2026-08-06T23:12:37.863300Z","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":"2026-08-06T23:12:37.822188Z","title":"Visual instruc- tion tuning,","venue":null,"work_id":"c8a15e06-6493-4b27-987b-e490667eba87","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.240572Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:e9e4e1b7b0301497128508c1a5dee44a119e7f89e3ee7a32687c15d0513192f6","observation_id":"57a26f55-b690-41d0-a2f0-cac02ca36296","resolution":{"observed_at":"2026-08-06T23:12:37.832914Z","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":"2026-08-06T23:12:37.785871Z","title":"Semantic labeling of 3d point clouds with object affordance for robot ma- nipulation,","venue":null,"work_id":"565cd728-0fae-4697-bfdb-75231d438a09","year":2014},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.314593Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:e86b151ba1e9b8bcb7cd11376723647027ce992178c2fb787382f81bb3dee12e","observation_id":"aa93a09e-f258-441b-acf0-e8579292e685","resolution":{"observed_at":"2026-08-06T23:12:37.799409Z","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":"2026-08-06T23:12:37.763045Z","title":"Affordance detection for task-specific grasping using deep learning,","venue":null,"work_id":"96b59a88-f67a-4e3a-95fa-adc2182b7bb7","year":2017},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.425631Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:1fd1bef4a6f00e0d68e72e0ad2405111fc4191df188bf5e0db2add1ce2c8f9b5","observation_id":"0168a083-cef6-4539-8210-02e6dc873a08","resolution":{"observed_at":"2026-08-06T23:12:37.769920Z","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":"2026-08-06T23:12:35.561425Z","title":"Pointnet: Deep learning on point sets for 3d classification and segmentation,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.561425Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:cd027dd1f563f7d695943aa441a97169c5fc4cd45bb069353a86e1f0257dcb24","observation_id":"1651265b-0e6c-475d-ae4c-30729755eb74","resolution":{"observed_at":"2026-08-06T23:12:35.561425Z","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":"2026-08-06T23:12:37.720522Z","title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space,","venue":null,"work_id":"67afd5dc-0e7d-4717-a7f4-05f9a207acad","year":2017},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.616387Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:f1f9c2b6b58370bbc2151f517f9c7f5e2b65d8112f22daeea79ef7dcbafd951d","observation_id":"516cb30f-7334-41db-857a-bd2b992c2ef1","resolution":{"observed_at":"2026-08-06T23:12:37.728084Z","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":"2026-08-06T23:12:37.680379Z","title":"Dynamic graph cnn for learning on point clouds,","venue":null,"work_id":"e9a966fb-e2bb-41c6-a2f3-79b5bdce95d4","year":2019},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.663629Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:e0bec3c9c6206baa59b53779fa3191c12d7b75b3dcacea6c7abcdea43cc2db74","observation_id":"766f8039-1870-4082-a716-d7c42a4add5a","resolution":{"observed_at":"2026-08-06T23:12:37.697043Z","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":"2026-08-06T23:12:37.654571Z","title":"Point Transformer,","venue":null,"work_id":"33445939-1c72-4018-9b23-85c4a38f5bb2","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.705034Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:a77b765e411dd76250333f0419498e194c7fc6cc62ca86d55bf1b0590d12d26f","observation_id":"83a9fd46-cc76-46f8-aca4-c5ed4b202c08","resolution":{"observed_at":"2026-08-06T23:12:37.661790Z","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":"2026-08-06T23:12:37.611882Z","title":"A robustly opti- mized BERT pre-training approach with post-training,","venue":null,"work_id":"ec078fe3-3292-41fe-8f04-2ce053ba2dcc","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.795822Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:869478653ea73acb9fdc088eff8462021f065426347cf8c90dcf20cc56962c67","observation_id":"15eb2b83-ffed-40b1-ac27-ff97060dfe9c","resolution":{"observed_at":"2026-08-06T23:12:37.632212Z","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":"2006.03654","last_updated":"2021-10-06T21:02:00Z","snapshot_observed_at":"2026-07-06T09:26:29.068023Z","submitted_at":"2020-06-05T19:54:34Z","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.03654","snapshot_observed_at":"2026-08-06T23:12:35.825141Z","title":"Deberta: Decoding- enhanced bert with disentangled attention,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.825141Z"},"links":{"cited_paper":"/paper/2006.03654","citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:28247b1b7d64b37ac889ba7af20eef5fa4b8a3d79c2300221584102736eee923","observation_id":"9fd8db11-7c57-4f99-b177-d96c9eaca4d9","resolution":{"observed_at":"2026-08-06T23:12:35.825141Z","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":"2026-08-06T23:12:37.567701Z","title":"Learning Transferable Visual Models From Natural Language Supervision,","venue":null,"work_id":"ddbb9385-3a17-4bcb-9f63-e30e73b75e89","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.834750Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:052185d80159b819875043ae6ca8797a4ae2add272b93ee2816ba0913743f8f0","observation_id":"d61bb13a-e619-42f1-8d77-3d175699ebe5","resolution":{"observed_at":"2026-08-06T23:12:37.577061Z","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":"2026-08-06T23:12:35.844233Z","title":"Multimodal Alignment and Fu- sion: A Survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.844233Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:d9736a0f30cd3606711a0d9c7865461498e3b519cd7a4dcd37dfd43cdf37cbde","observation_id":"5fc8a9c9-4af4-40b8-9928-48fcb5cdbfe2","resolution":{"observed_at":"2026-08-06T23:12:35.844233Z","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":"2026-08-06T23:12:37.535901Z","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision,","venue":null,"work_id":"dfbd3fa7-9bc9-45d6-80b5-4d4e858b5455","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.855900Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:dad79748d90001ccae1dcc6a7a2e8bc4f2712ac113f4de2861d1e6791babf26f","observation_id":"b9941c22-7afd-418d-89d8-94ef2d5624a4","resolution":{"observed_at":"2026-08-06T23:12:37.543973Z","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":"2026-08-06T23:12:37.510044Z","title":"Multimodal repre- sentation learning for tourism recommendation with two-tower architecture,","venue":null,"work_id":"7fea6241-2f4a-4bd4-9553-6d930227158e","year":2024},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.869115Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:b68a596465b91aa5a64d9b8529f5e887fba55f8e8533c984b7db0e82ea9ac2d2","observation_id":"43524f2e-ecd0-45db-a5d3-72770bf4a452","resolution":{"observed_at":"2026-08-06T23:12:37.518422Z","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":"2026-08-06T23:12:37.479122Z","title":"I can listen but cannot read: An evaluation of two-tower multi- modal systems for instrument recognition,","venue":null,"work_id":"4b3f826b-59f6-4fb5-beef-5c2d637015e0","year":2024},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.879077Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:fb1edd067dbb33f85ca3ad0806ae74f18fe52bf0d0b4571fa6401066fa8ee1a5","observation_id":"c235b6ce-2702-42f1-accc-0afeebd19d8c","resolution":{"observed_at":"2026-08-06T23:12:37.490452Z","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":"2026-08-06T23:12:37.448132Z","title":"Bridgetower: Building bridges between encoders in vision-language representation learning,","venue":null,"work_id":"de9984bc-6b71-4b0c-bcb5-8a89f52c1881","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.888509Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:180016eaa0f87a818715e25025b2ba90f487816bc544c7d68a4dc98707d3c77e","observation_id":"f4c84bb9-a486-4f6b-a409-01c105a86a95","resolution":{"observed_at":"2026-08-06T23:12:37.457987Z","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":"2026-08-06T23:12:37.398482Z","title":"Be- yond Two-Tower Matching: Learning Sparse Retriev- able Cross-Interactions for Recommendation,","venue":null,"work_id":"87a0949d-f7e2-48b8-9223-43425c8b7f6d","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.902333Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:13900c04c580a624b7b903488405f1779c614ef73b3487d63a1f667dd36b2a82","observation_id":"dc048dec-31b1-42fc-84b4-c01cc30053b1","resolution":{"observed_at":"2026-08-06T23:12:37.406626Z","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":"2026-08-06T23:12:37.363301Z","title":"Touchformer: A Transformer-based two-tower architecture for tactile temporal signal classification,","venue":null,"work_id":"f2823b82-1818-46d4-89c0-100842e0aef1","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.910303Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:98d245a897ec70210a7c81c8341422ff8592d2618fcb7225b2c6ccf7ba5af913","observation_id":"157ccc69-635e-4627-afa0-b5ea6c0fa0ac","resolution":{"observed_at":"2026-08-06T23:12:37.381193Z","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":"2026-08-06T23:12:37.335092Z","title":"Mix-tower: Light visual question answering framework based on exclusive self-attention mechanism,","venue":null,"work_id":"ebf16484-8ded-43d6-93f8-7d4b52c5f973","year":2024},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.923476Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:06c4aa6e911b70f932510d5b922b22eb6ccc3ec4282cc0011394458cdb83c767","observation_id":"b6eaa045-dd91-4faa-842f-cd125dd15eb1","resolution":{"observed_at":"2026-08-06T23:12:37.342148Z","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":"2026-08-06T23:12:37.294974Z","title":"Towards artificial general intelligence via a multimodal foundation model,","venue":null,"work_id":"14daed89-dd3a-48b6-8e1e-22dbd7221f8e","year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.930934Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:3a480501495094909e576b844d734cb576ac0dc1ae31aa4e06eac663e546bd18","observation_id":"07ca6b59-85eb-4a07-960e-de66f3983f2a","resolution":{"observed_at":"2026-08-06T23:12:37.304468Z","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":"2026-08-06T23:12:37.252803Z","title":"Multimodal Reranking for Knowledge- Intensive Visual Question Answering,","venue":null,"work_id":"da9a3651-74a6-43c4-bce3-2ca16d20e42c","year":2024},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.936731Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:104068df06ad563cd865fb90b557b2bfa9d21d87abb54c82e72a330891479095","observation_id":"48e2d963-7456-4ab0-b662-7c5d1bb7a49f","resolution":{"observed_at":"2026-08-06T23:12:37.261409Z","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":"2026-08-06T23:12:37.228392Z","title":"Dif- ferentiable cross-modal hashing via multimodal trans- formers,","venue":null,"work_id":"3619303d-e5af-4b8f-8d42-70c42eb88a5b","year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.945708Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:5abaf27cf2c9c1f9b697271e9552d5394a4cf15c6e7124543e8be7a3ba19f23f","observation_id":"b1d06ad8-da76-4b7d-9b99-c413003e4547","resolution":{"observed_at":"2026-08-06T23:12:37.235788Z","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":"2026-08-06T23:12:37.201943Z","title":"Towards User Friendly Medication Mapping Using Entity-Boosted Two-Tower Neural Network,","venue":null,"work_id":"9521ffcc-9b35-489e-8083-c7e85a44d74b","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.953730Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:a50cafe5df5464cb03375dade603057c64776264e66009bd9cefa37dbd88c593","observation_id":"02b33984-3811-4660-94ce-67e37b5ee21b","resolution":{"observed_at":"2026-08-06T23:12:37.210564Z","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":"2026-08-06T23:12:37.176710Z","title":"Fusing information from multifidelity computer models of physical sys- tems,","venue":null,"work_id":"4a4a2c89-b870-45be-8e39-f1d1336c684e","year":2012},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.964177Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:90de98f1f53c42d6cab23d06a2696f6976bc31620d152af905d5d051ed5e76d9","observation_id":"d26529e8-d484-4d4d-a4db-cc281b5b394c","resolution":{"observed_at":"2026-08-06T23:12:37.182231Z","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":"2026-08-06T23:12:37.151369Z","title":"Seg- Net: A Deep Convolutional Encoder-Decoder Archi- tecture for Image Segmentation,","venue":null,"work_id":"24bf84f8-a336-4d87-ac01-4a9c2ca89acd","year":2015},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.970766Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:8d389c1c8d3cc4f728b9d8598def202f3b90cde2e835794ee60f67072ff6266c","observation_id":"b32b9c27-effe-46f9-af17-f4e6248fedc5","resolution":{"observed_at":"2026-08-06T23:12:37.162429Z","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":"2026-08-06T23:12:37.119095Z","title":"Sensor fusion of camera and LiDAR raw data for vehicle detection,","venue":null,"work_id":"4541987c-5bbd-4a9e-8296-0151940bd296","year":2020},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.987196Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:dd2bf2c0110fe7dbb14cd6a0c74705cc14ee1ee6987640984b2e1b5096a7e953","observation_id":"e012b1a5-e8a9-4247-8f5a-72a14c7e5d12","resolution":{"observed_at":"2026-08-06T23:12:37.126389Z","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":"2026-08-06T23:12:37.093802Z","title":"A Model-Level Fusion-Based Multi-Modal Object Detection and Recognition Method,","venue":null,"work_id":"f19e3fd7-8d40-4201-b17f-b95deccbb7b4","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:35.996534Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:92355dfb598937880262801d26663d61d72a6f9857004900cc96dddbc9dffb56","observation_id":"c9687933-4d52-49dc-9f47-974d117e2d0d","resolution":{"observed_at":"2026-08-06T23:12:37.099882Z","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":"2026-08-06T23:12:37.065201Z","title":"Learning to combine local models for facial Action Unit detec- tion,","venue":null,"work_id":"f23bfd3b-74bc-4839-8076-828a71d7eac7","year":2015},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.004071Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:aa1f8b711d4e794f82eea2c9f460ae01bfd0b25a81c46150cf07b2296b1df4f6","observation_id":"7e9ba028-cc50-43d3-b1f1-f1584326c9cd","resolution":{"observed_at":"2026-08-06T23:12:37.072641Z","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":"2026-08-06T23:12:37.043835Z","title":"Polos: Multimodal Metric Learning from Human Feedback for Image Captioning,","venue":null,"work_id":"a3b4ae6a-64c6-4a36-a58d-1667064e3612","year":2024},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.014908Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:6f1700ef73b780bb89c69f9b8cac4062321693a2491fc8e3282cce4478152841","observation_id":"dbf5b439-85ca-4f2c-a295-a8ae18ba4a09","resolution":{"observed_at":"2026-08-06T23:12:37.050351Z","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":"2026-08-06T23:12:37.014753Z","title":"Hierarchical Feature Fusion Network for Salient Object Detection,","venue":null,"work_id":"db3c56d3-17a1-4e5d-b4cd-cd48e41351ae","year":2020},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.021868Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:222a56398bb9ed45ce19d81608f987afb3b48121b49925097e036544fc800680","observation_id":"22993178-5dff-44a7-8985-b81a889f91d7","resolution":{"observed_at":"2026-08-06T23:12:37.025923Z","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":"2026-08-06T23:12:36.978353Z","title":"DenseFuse: A Fusion Approach to Infrared and Visible Images,","venue":null,"work_id":"451106a0-d01d-4ed9-8e4c-a35be7d4e8d9","year":2018},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.031814Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:c0199188bd18cb04f489ac2776a2577f9bd475560a42d5528c69b6aa398ddb26","observation_id":"10013bb5-63eb-4188-ad44-ba7fcd2643af","resolution":{"observed_at":"2026-08-06T23:12:36.984794Z","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":"2026-08-06T23:12:36.950483Z","title":"Divide, Conquer and Combine: Hierarchical Feature Fusion Network with Local and Global Perspectives for Multimodal Affec- tive Computing,","venue":null,"work_id":"0287df48-9d78-4bed-b9e6-1ee78680c27a","year":2019},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.041247Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:36a253e7165ce3173dbf18cf8190213932498e63ab586dc0bc3d7b4a4289b9f3","observation_id":"be9b7e67-cfc0-46b4-bcc9-e05af9636ae7","resolution":{"observed_at":"2026-08-06T23:12:36.959099Z","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":"2026-08-06T23:12:36.922839Z","title":"A hierarchical feature fusion frame- work for adaptive visual tracking,","venue":null,"work_id":"707816a0-7e0c-47d4-91a4-ccbc7489a48a","year":2011},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.051098Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:ba6f6dbf76dc701837befd91b9551dbdb70ccb6785f5ad30b2962363a336b7c4","observation_id":"9b254963-3447-4e66-9925-d6ae53e63000","resolution":{"observed_at":"2026-08-06T23:12:36.930252Z","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":"2026-08-06T23:12:36.898390Z","title":"Model level fusion of edge histogram descriptors and gabor wavelets for landmine detection with ground penetrating radar,","venue":null,"work_id":"4066b32f-27f1-4a24-8122-be2eece444b7","year":2010},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.069077Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:922257c8d08548f8c1ff98155c8ee7c49ad24d077c69a4475fbe512e31c0d963","observation_id":"77063f44-bda1-4c2e-808f-bc107ca93ecb","resolution":{"observed_at":"2026-08-06T23:12:36.904553Z","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":"2026-08-06T23:12:36.847209Z","title":"Towards Raw Sensor Fu- sion in 3D Object Detection,","venue":null,"work_id":"044f6665-336b-461c-8ba4-963d72b06243","year":2019},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.076577Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:2305f307a2694fc8f3a2ab3c00eff4b3f579da14b82d1cd8732f48c8ff24c590","observation_id":"1f525350-1fb3-4d28-b752-7ac2163de450","resolution":{"observed_at":"2026-08-06T23:12:36.856881Z","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":"2026-08-06T23:12:36.784380Z","title":"Design of a Low-Level Radar and Time-of-Flight Sen- sor Fusion Framework,","venue":null,"work_id":"d1d2ea4b-bee6-40e5-9ea9-22596acf57ad","year":2018},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.090290Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:d2535bce2d9c3b75bbb6c670a60b001a594faedb2d327d08021f60338905e6dc","observation_id":"ba86160e-f83c-4622-828b-09d8074bf7c5","resolution":{"observed_at":"2026-08-06T23:12:36.795207Z","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":"2026-08-06T23:12:36.746731Z","title":"Guided Deep Decoder: Unsupervised Image Pair Fusion,","venue":null,"work_id":"dc6fccb1-40b4-43c2-869b-2c852641cbac","year":2020},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.098060Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:2c22779d1814ed35d208c2f1b22b297db47de93e3bf2858325fc603b607c8784","observation_id":"dc5beebc-298c-4d71-b5b3-24df6548d886","resolution":{"observed_at":"2026-08-06T23:12:36.757432Z","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":"2026-08-06T23:12:36.714753Z","title":"Decision-Level Data Fusion in Quality Control and Predictive Main- tenance,","venue":null,"work_id":"4fb60a7e-2ce0-4a53-ab24-8032a3634865","year":2021},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.106624Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:f4cd5540d7ad6c3c4bc0e31ffa43ae87ba7dcd5cfc75c360640f4f40baf24492","observation_id":"80e4baf2-6a32-4c30-b854-cb9b8c0287c4","resolution":{"observed_at":"2026-08-06T23:12:36.723183Z","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":"2026-08-06T23:12:36.687788Z","title":"ViLT: Vision and lan- guage transformer without convolution or region su- pervision","venue":null,"work_id":"fa8cb296-108c-456c-ac85-dc7117b067a4","year":null},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.117534Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:bb6f9a18cd9023f56065816c24ddc3726775916ed8a51f7caf1928e9544a6d43","observation_id":"614807a0-1fed-4010-80e1-e513f8a1eb69","resolution":{"observed_at":"2026-08-06T23:12:36.695855Z","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":"2026-08-06T23:12:36.651660Z","title":"VLMo: Unified Vision-Language Pre-Training with Mixture of Modal- ity Experts,","venue":null,"work_id":"53611406-2727-4709-bcb8-65d51d1a4a43","year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.129200Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:62f1681d3960f60d406c40586c3db83be8f4e30a0e19136d7c65c6b5616aaea1","observation_id":"7993308d-6174-441e-8c9a-a8737c1bbdf2","resolution":{"observed_at":"2026-08-06T23:12:36.669490Z","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":"2026-08-06T23:12:36.624100Z","title":"BLIP: Boot- strapping language image pre-training for unified vi- sion language understanding and generation,","venue":null,"work_id":"e572ddc1-dcb7-409e-a5dc-41afa0e1f8a8","year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.141635Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:3c7d30b43fc89fcaa5a77ce83b5d95ebe5ba3a8b87ba1155427cc102ba151230","observation_id":"e54610a1-e00f-45ac-a0c4-335956a45cd6","resolution":{"observed_at":"2026-08-06T23:12:36.632313Z","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":"2026-08-06T23:12:36.595139Z","title":"BLIP-2: Boot- strapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models,","venue":null,"work_id":"e8da0513-7e99-45bb-8607-74f895fd4a13","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.150789Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:f0e8dd7384a32cd6ad552d37b276694f4369cb464d414b020aaee363b2fac6c8","observation_id":"af77ee36-574d-4085-8e86-2fd793af470c","resolution":{"observed_at":"2026-08-06T23:12:36.603527Z","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":"2026-08-06T23:12:36.567918Z","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruc- tion Tuning,","venue":null,"work_id":"bb22c5ec-50a5-40e5-aec7-22e8947d623b","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.158359Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:1aa0561a7f132ab5dec743a04a2b07d56aabf5ab062a465121d3cf4d9c745550","observation_id":"11ba52d7-f35b-4b16-a130-2f0773829cf2","resolution":{"observed_at":"2026-08-06T23:12:36.574066Z","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":"2304.10592","last_updated":"2023-10-02T16:38:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-20T18:25:35Z","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.10592","snapshot_observed_at":"2026-08-06T23:12:36.165953Z","title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.165953Z"},"links":{"cited_paper":"/paper/2304.10592","citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:f7b841cadf3a4c4c339e0e5d9b4ca295b4f2e02719f7ade324d72b9fff493c07","observation_id":"33e1aecd-4a67-4505-8116-3782aeeef652","resolution":{"observed_at":"2026-08-06T23:12:36.165953Z","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":"2026-08-06T23:12:36.542185Z","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision,","venue":null,"work_id":"1accf784-2d45-449e-8665-41329f8b3fe9","year":2022},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.175329Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:a0fabb1311a064fd5af48f8fa384ed70dcefff44614a3d245a5de365f3f013cc","observation_id":"83aca980-d79e-4313-8b3e-6acea65d873c","resolution":{"observed_at":"2026-08-06T23:12:36.549214Z","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":"2026-08-06T23:12:36.517413Z","title":"Qwen2-VL: Enhancing Vision-Language Model’s Perception of the World at Any Resolution,","venue":null,"work_id":"0a623ae8-0cc6-49df-88bf-2c6c79d60238","year":2024},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.182881Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:f7d5c6a5f80e414796b828246fec2f50158ce4cd2f8b1398b38aa16b7e4cc488","observation_id":"7bd85ec4-9da9-4ef3-b60e-e43e24af7da1","resolution":{"observed_at":"2026-08-06T23:12:36.524421Z","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":"2026-08-06T23:12:36.487825Z","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localiza- tion, Text Reading, and Beyond,","venue":null,"work_id":"bbcde35b-21de-43b3-afe0-5a5f2a72a261","year":2023},"citing_paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:36.191422Z"},"links":{"citing_paper":"/paper/2506.19312"},"observation_digest":"sha256:1ab712c711dae1e4c1b9009b7c3cd8f75c277670da3dc9cab4dd89ed963b9909","observation_id":"2edbe88f-c577-4590-b57b-850640eb8234","resolution":{"observed_at":"2026-08-06T23:12:36.497986Z","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"}}],"paper":{"arxiv_id":"2506.19312","last_updated":"2025-06-24T04:58:55Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T13:57:42.210892Z","submitted_at":"2025-06-24T04:58:55Z","title":"Capturing Fine-Grained Alignments Improves 3D Affordance Detection"},"reference_resolution":{"displayed":76,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":71},"total_outbound_references":76},"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 76 of 76 outbound references and 0 inbound Pith citation observations for arXiv:2506.19312."}