{"as_of":"2026-08-08T20:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:744ec869f40ad3a974ae95b89a854a4e9d275e77742ee34dfcc6f3fbd2f53446","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T21:16:27.443463Z","state":"measured"},{"denominator":69,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":69,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-15T14:50:58.269817Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-15T14:51:08.148643Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"cited_work":{"arxiv_id":"2508.09262","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.09262","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Harnessing input-adaptive inference for efficient vln","venue":null,"work_id":"2cefd8eb-2cb8-4f3d-a183-9513fc4e58a1","year":2025},"citing_paper":{"arxiv_id":"2603.07080","last_updated":"2026-04-29T05:35:06Z","snapshot_observed_at":"2026-07-06T22:48:13.053749Z","submitted_at":"2026-03-07T07:30:35Z","title":"VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-15T14:50:58.269817Z"},"links":{"cited_paper":"/paper/2508.09262","citing_paper":"/paper/2603.07080"},"observation_digest":"sha256:c4237c26dd6e3f036d29613252dc4a2fd1fc75b4bfc18ac16e7dbb21a5eb2c01","observation_id":"d5f0dd66-a0bf-424d-abca-bb237d1a6dd0","resolution":{"observed_at":"2026-05-15T14:51:08.151302Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.09262/citation-record","integrity":"/paper/2508.09262/integrity","json":"/paper/2508.09262/citation-record.json","paper":"/paper/2508.09262"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:38.557933Z","title":"Vision-and-language navigation: In- terpreting visually-grounded navigation instructions in real environments","venue":null,"work_id":"602bba94-9adc-4394-be27-cdae0158a88d","year":2018},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:20.733081Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:2cc71ae47743f6034eb3d657043411b8d2153387d16bcc909853bed83c85ab8e","observation_id":"b511e49f-8a6a-4dc0-85f7-db97b60daa5d","resolution":{"observed_at":"2026-08-05T21:16:38.653883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:38.308743Z","title":"Sim- to-real transfer for vision-and-language navigation","venue":null,"work_id":"f38836aa-f51f-4ba3-94d6-8ad2f58dba07","year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:20.829736Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:fed2541ddc686d8281fe501c033ec0e3b1aab403bcfcefac9384457abd3ffa58","observation_id":"e8a12b91-793e-4038-bf2a-e8c95e5920e1","resolution":{"observed_at":"2026-08-05T21:16:38.413025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:38.093340Z","title":"Near-optimal hashing algo- rithms for approximate nearest neighbor in high dimensions","venue":null,"work_id":"71059b5b-4181-414b-a5be-112a4abf837c","year":2008},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:20.934984Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:4c3bc3dc524e06aa8554489c846a9cb33e9cb077e0cd93d30e306089edd060ad","observation_id":"c9907dc5-ebdf-409d-a231-d1435efc7e03","resolution":{"observed_at":"2026-08-05T21:16:38.195462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:37.871373Z","title":"Post train- ing 4-bit quantization of convolutional networks for rapid- deployment","venue":null,"work_id":"ebdcb600-683b-4b35-af88-db7d8547fbe1","year":2019},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.038892Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:f944f8bc7b929116c746ecda96157307578ff94aa33c556d37189f6f50ded35a","observation_id":"a99c0956-64b6-4214-9140-ade9c8338cbe","resolution":{"observed_at":"2026-08-05T21:16:37.992286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:37.685729Z","title":"Surf: Speeded up robust features","venue":null,"work_id":"84288355-d5be-4bb1-b64f-f485b1051fb2","year":2006},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.166405Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:6a1e3252835357bd556952f2897a510d8a29618ae5157ca76ed8d21d4a791591","observation_id":"d3be4173-c310-4bb3-879d-fd256e853baf","resolution":{"observed_at":"2026-08-05T21:16:37.787205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:37.500908Z","title":"Lsq+: Improving low-bit quantization through learnable offsets and better initialization","venue":null,"work_id":"bdff9eb3-71a6-4bcf-8095-3a2b71235b9a","year":null},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.294571Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:89d428ba11db2a299e59389a6043155ca927781e38a6b872cad3a81b4580b855","observation_id":"0f3d5646-8387-44d2-9346-5954df171c09","resolution":{"observed_at":"2026-08-05T21:16:37.622777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:37.287568Z","title":"Matterport3d: Learning from rgb-d data in indoor environments","venue":null,"work_id":"2c258d42-670a-4876-a919-e5d14b90a52f","year":2017},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.372606Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:00de0571b80a2376d4f6c5cc5e9f35fe01f6ff45d7d7d970a1ecfe4c99f2fef5","observation_id":"ea44c453-daeb-430e-b8b5-3e09e1462cd4","resolution":{"observed_at":"2026-08-05T21:16:37.397170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:37.025531Z","title":"Similarity estimation techniques from rounding algorithms","venue":null,"work_id":"af446339-3a65-4ae2-9620-4e619971da53","year":2002},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.466769Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:d3577f2219a22ea745c6afe915b8ab85b6bd28476553d6f62d6ca8628f2daa59","observation_id":"7e9a7242-1966-4e87-a187-3fc61aeb124c","resolution":{"observed_at":"2026-08-05T21:16:37.145279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:36.760938Z","title":"Robustnav: Towards benchmark- ing robustness in embodied navigation","venue":null,"work_id":"ca21fcda-272a-465c-8c18-da396a1229bb","year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.572306Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:404c27bb9c3a602c1d8847052b0c398353ef358aa57c336f1d98a2099bcb9c77","observation_id":"ffdb1142-0cee-4ae5-adf5-5e0554e649a3","resolution":{"observed_at":"2026-08-05T21:16:36.860896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:36.509850Z","title":"History aware multimodal transformer for vision- and-language navigation","venue":null,"work_id":"a9434dd0-66df-4b63-9c05-32a4f0b0c0f9","year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.602493Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:e659c9a9a035ce8914840bdb201c89629f2f35a6f850844b6aba6d772b07a56c","observation_id":"75b984ba-07c1-4239-bcda-ddb7979c8298","resolution":{"observed_at":"2026-08-05T21:16:36.632021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:36.409974Z","title":"Think global, act lo- cal: Dual-scale graph transformer for vision-and-language navigation","venue":null,"work_id":"57a79884-876d-4712-9582-56f0166e4c33","year":2022},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.625856Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:3828c44e70fcd46a22c4b7f4a26f7e04b0d9df3d7e842abae370ee9e6729010e","observation_id":"9c8e2339-e081-4280-9b26-834e1dd10beb","resolution":{"observed_at":"2026-08-05T21:16:36.447927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06085","last_updated":"2018-07-17T07:33:19Z","snapshot_observed_at":"2026-07-06T06:39:21.688392Z","submitted_at":"2018-05-16T01:19:43Z","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06085","snapshot_observed_at":"2026-08-05T21:16:21.733414Z","title":"Pact: Parameterized clipping activation for quantized neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.733414Z"},"links":{"cited_paper":"/paper/1805.06085","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:d267e115da4f636acdeaa1abcfa8d9df4be35924c742330015eb7f895e6eebb0","observation_id":"48441fbd-4f96-444d-b89b-6f42e2e53dda","resolution":{"observed_at":"2026-08-05T21:16:21.733414Z","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":"2026-08-05T21:16:36.271795Z","title":"Low-bit quantization of neural networks for efficient infer- ence","venue":null,"work_id":"adafd446-5be3-4c56-a5b7-773f60626242","year":2019},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.847023Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:e56a0aec9fe277520377c2c76eaeeec1545fb6fe9d9e218c47ae95fae5cf8cc1","observation_id":"cba321f5-bdf9-43dc-b5de-699e1433adcb","resolution":{"observed_at":"2026-08-05T21:16:36.340021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:36.059503Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport","venue":null,"work_id":"bc94c499-53e0-4479-84ab-ba69b6fd2b0d","year":2013},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:21.950162Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:100ad3d5e3a046d54a5dae7206571fe4ed9b328cf6a69946d663400809cf79a5","observation_id":"e5610eb6-8336-41fd-840f-fcbd1b775724","resolution":{"observed_at":"2026-08-05T21:16:36.186895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:35.783297Z","title":"BERT: Pre-training of deep bidirectional trans- formers for language understanding","venue":null,"work_id":"606d15f2-28b9-45d9-a048-2ed8be251226","year":2019},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.028110Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:d9e8c0cd538034815f382efc455c30c3bebd43acf5383ac128138b947946a971","observation_id":"a96da192-03e0-40eb-b9a9-24fc0183cadb","resolution":{"observed_at":"2026-08-05T21:16:35.929627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:35.510459Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"1e0c3b22-7052-4ce3-8d5d-9fdbef2e7f39","year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.130767Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:60a02f9e01d64f64f8d7dc5835ebf6b1728de4d5c3faceca75d479b9f50598d5","observation_id":"3958f03d-ef1e-4c83-9970-d31e07f3dc44","resolution":{"observed_at":"2026-08-05T21:16:35.632724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11556","last_updated":"2019-09-25T15:35:03Z","snapshot_observed_at":"2026-08-08T18:02:18.011077Z","submitted_at":"2019-09-25T15:35:03Z","title":"Reducing Transformer Depth on Demand with Structured Dropout","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.11556","snapshot_observed_at":"2026-08-05T21:16:22.237618Z","title":"Reducing transformer depth on demand with structured dropout","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.237618Z"},"links":{"cited_paper":"/paper/1909.11556","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:03b3c4f0fd9360b60a1228ee31244501269d919cc482c67c4a504d347a288cf0","observation_id":"1beebdf1-25db-475a-9bc5-eb1303dad0e5","resolution":{"observed_at":"2026-08-05T21:16:22.237618Z","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":"2026-08-05T21:16:35.159032Z","title":"Depgraph: Towards any structural pruning","venue":null,"work_id":"e2c3179b-91b3-43e2-a9e0-7fbc3485900d","year":2023},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.346939Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:06b9248437ff34926929d04d94c8449a1d129a16d6cdc1174376407e81a5922b","observation_id":"d8312716-778e-4db8-9cb1-ad5c64220db3","resolution":{"observed_at":"2026-08-05T21:16:35.309446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:34.936072Z","title":"Spatially adaptive computation time for residual networks","venue":null,"work_id":"428ddfd1-d569-4095-9187-59c359b0c136","year":2017},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.454930Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:8a3cea613c6d8cf4eb6576b7031f8aabb1d14cf672721c867b82bfab7c79c3a3","observation_id":"fe304698-9c18-4731-853e-00812b98f8bb","resolution":{"observed_at":"2026-08-05T21:16:35.033885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:34.652157Z","title":"Speaker-follower models for vision-and-language navigation","venue":null,"work_id":"4af5b1da-d21b-4f8b-a996-cb136877301a","year":2018},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.556193Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:0195604d9b4aaf1c5815ce1acf29b309f33914319516dc6120de07e1c2b8048c","observation_id":"7f36c452-49b2-4373-b403-f578e6b96620","resolution":{"observed_at":"2026-08-05T21:16:34.778832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:34.464165Z","title":"Airbert: In-domain pretraining for vision-and-language navigation","venue":null,"work_id":"90534654-93db-4740-a981-4b54e009803c","year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.643854Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:12905c337c93219747bf4ab321f614d8819ea8579cb64bc2a9b0e67f117a0ea7","observation_id":"e4d143db-f0ea-46e6-ba18-ad793050eac7","resolution":{"observed_at":"2026-08-05T21:16:34.569487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:34.280018Z","title":"Improving robust- ness of vision transformers by reducing sensitivity to patch corruptions","venue":null,"work_id":"1f5d9581-c79b-446c-a271-c4ee582f789b","year":null},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.689621Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:2fc17e1cd8b896b8ba196c8b7a717e02b02907774b6a650040cefcd8fe59db96","observation_id":"bcfb70cd-cce1-4071-bd82-c7983e108c20","resolution":{"observed_at":"2026-08-05T21:16:34.384139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-05T21:16:22.805505Z","title":"Deep com- pression: Compressing deep neural networks with pruning, trained quantization and huffman coding","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.805505Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:67b99d8b6baaa91ce980c2b2a04b81179f3b1048fdc2f13ed5a262104287e999","observation_id":"59cd03c8-1cca-4158-846c-742f0177a02e","resolution":{"observed_at":"2026-08-05T21:16:22.805505Z","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":"2026-08-05T21:16:34.024471Z","title":"Learning both weights and connections for efficient neural network","venue":null,"work_id":"880d3584-ee52-4767-91b7-f266f60d7d58","year":2015},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:22.936871Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:d10fed8be014ca15b32a0efbb8b938d25c7febd0e8ae750fabab4b3ff2cf477b","observation_id":"677d8c61-6377-4c78-8501-11cec1ad2f0c","resolution":{"observed_at":"2026-08-05T21:16:34.190249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:33.675832Z","title":"Towards learning a generic agent for vision- and-language navigation via pre-training","venue":null,"work_id":"64deb20b-c23b-47f1-8dab-06d7b79a49f4","year":2020},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:23.002639Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:6695a5121e7ec253d6cc7209e742532a031c0109dde7f4d27a2ef7f86b064024","observation_id":"4f99c410-06f1-437c-9874-4ddd69aae620","resolution":{"observed_at":"2026-08-05T21:16:33.814372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:33.431390Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"ac1faf8a-29b2-457f-8fa0-0f393afcd19b","year":2016},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:23.102535Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:5a782621d2d3f4f7923ea7fdfac16226a961c62b6b815c4de9ad598531049085","observation_id":"936ac15a-e28f-4a9e-818c-1566426df53c","resolution":{"observed_at":"2026-08-05T21:16:33.528192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:33.239069Z","title":"Benchmarking neural network robustness to common corruptions and perturbations","venue":null,"work_id":"4376e7f9-65da-47e2-a7f4-d54ef2bdd60e","year":null},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:23.227810Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:4a66d3636a594d86c733729cd592bfbf4128f275bf1c168125241eeda3979a24","observation_id":"62537790-f269-4f02-b3f9-3b7aebf0eb1d","resolution":{"observed_at":"2026-08-05T21:16:33.313024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:33.058606Z","title":"Revisiting pruning at ini- tialization through the lens of ramanujan graph","venue":null,"work_id":"d04ba2a2-968f-49ba-b6f4-8ab7c609e577","year":2023},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:23.361214Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:e4e8d15966539173bb39f26174920e43236c85dc41bb0a4af9753bfd8f0f651c","observation_id":"e0d58cd7-15d9-483e-9092-105bc6a6cd2c","resolution":{"observed_at":"2026-08-05T21:16:33.147918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:32.938888Z","title":"A recurrent vision-and-language bert for navigation","venue":null,"work_id":"a37698fd-6cc9-49fa-ab97-6d2ffaaaeadf","year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:23.461766Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:ec327767b5006ac18d30876b8edf8328d2aa4099d42e4871f2a5db16c7775495","observation_id":"dc8b5c34-199b-4498-bedb-fb81d4f4157e","resolution":{"observed_at":"2026-08-05T21:16:32.994494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:32.767742Z","title":"Bridg- ing the gap between learning in discrete and continuous envi- ronments for vision-and-language navigation","venue":null,"work_id":"b5be2bae-ccb8-4eb1-9763-7732180dce87","year":2022},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:23.545616Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:6a436d38cf2050be51bfcabb9a45d8bc7d6af90bcd5778faf6fac32eb3fe3ec3","observation_id":"221165ec-fe3f-48f5-8d4b-8f719dafafb5","resolution":{"observed_at":"2026-08-05T21:16:32.821399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:32.627341Z","title":"Multi-scale dense networks for resource efficient image classification","venue":null,"work_id":"19ee8f46-eafb-4d93-9187-c1296de88c0b","year":2018},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:23.684011Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:d62a8e5c6e9b7f383cd66943e0414e526e2a936d5610794fb865ae55d7d480a3","observation_id":"5521bd9e-00cf-4f1a-89cb-4382661c850f","resolution":{"observed_at":"2026-08-05T21:16:32.721731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:32.477998Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","venue":null,"work_id":"cedb1f14-cce0-4967-8e3f-a30ad8291e6e","year":2018},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:23.786312Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:1aac380e7b6dbe1ce72da3739e9d558dd80b716387c5efd3d869b8e0d1ddb390","observation_id":"23d54271-c30b-4d3a-865f-9d7d365e4dc7","resolution":{"observed_at":"2026-08-05T21:16:32.545283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:32.280438Z","title":"A new path: Scaling vision-and-language navigation with synthetic instructions and imitation learning,","venue":null,"work_id":"c265ffa5-1162-470e-a159-0cbec7445466","year":null},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:23.942354Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:ef906c21ed2a6ffbc88ae2f23e2b26d4c7f5a22b7d7121385d65c8ad0d21ae4a","observation_id":"857ce5db-368b-44d2-b2e7-83289a60d172","resolution":{"observed_at":"2026-08-05T21:16:32.402035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:32.131588Z","title":"Shallow-deep networks: Understanding and mitigating net- work overthinking","venue":null,"work_id":"39c5ef4c-1e15-46df-88ff-64944ab8ea85","year":2019},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:24.097276Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:78d60a1af48e4956fc083b0f02334f94f5b32dc6f17f58178357fa4d6e3efa59","observation_id":"49019d57-8ca9-464a-a812-f29eda0114d4","resolution":{"observed_at":"2026-08-05T21:16:32.197874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:31.934403Z","title":"Sim-2-sim transfer for vision- and-language navigation in continuous environments","venue":null,"work_id":"98719326-3b3b-40ca-a12a-558b72fe5b46","year":2022},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:24.233687Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:8dd5de93f14bc895ae9dd5c0a51d7983c13c5312472871af31555041e5f25e0d","observation_id":"aaa6b125-039f-4d0a-97e2-337702ce222b","resolution":{"observed_at":"2026-08-05T21:16:32.006393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:31.778708Z","title":"Beyond the nav-graph: Vision and language navigation in continuous environments","venue":null,"work_id":"dea65a40-904b-44ba-b2f1-c5616a10d062","year":2020},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:24.342597Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:0a8c5846182693048b401941b074362f8bc167f085a7c759d1445a08fab2cdff","observation_id":"856735f6-84ef-46e0-a2a5-82241a408bf9","resolution":{"observed_at":"2026-08-05T21:16:31.866878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:31.602928Z","title":"Improving vision-and-language navigation by generating future-view image semantics","venue":null,"work_id":"a0a47db5-6b4b-4540-a119-e3cacc5f2f8b","year":2023},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:24.478664Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:8bf62fec3de59728ada01895f8b79ea0e75d1455a48a87dcf2d1f5e52c7660ef","observation_id":"ce4562bb-de13-424a-8a4f-35afba907193","resolution":{"observed_at":"2026-08-05T21:16:31.687460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05426","last_updated":"2021-07-25T09:34:39Z","snapshot_observed_at":"2026-08-04T09:21:27.169501Z","submitted_at":"2021-02-10T13:46:16Z","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.05426","snapshot_observed_at":"2026-08-05T21:16:24.592967Z","title":"Brecq: Pushing the limit of post-training quantization by block reconstruction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:24.592967Z"},"links":{"cited_paper":"/paper/2102.05426","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:e7a7999741a9277598301c33740169a5d45c4a31c7bfb784fa1288afe96e3ba8","observation_id":"56815087-af10-4b37-a0e9-5da3aef93916","resolution":{"observed_at":"2026-08-05T21:16:24.592967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.02178","last_updated":"2020-04-29T15:46:34Z","snapshot_observed_at":"2026-08-07T23:53:14.045662Z","submitted_at":"2020-04-05T12:29:20Z","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.02178","snapshot_observed_at":"2026-08-05T21:16:24.770092Z","title":"Fastbert: a self-distilling bert with adaptive inference time","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:24.770092Z"},"links":{"cited_paper":"/paper/2004.02178","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:ace01fbcf03d65c4c9bede69087957399c345cba96eaecae9ba5a0c913cb3532","observation_id":"12c67c62-fd60-4b59-b644-14fb097f9a3d","resolution":{"observed_at":"2026-08-05T21:16:24.770092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.01875","last_updated":"2018-10-03T14:17:24Z","snapshot_observed_at":"2026-07-06T07:05:54.800811Z","submitted_at":"2018-10-03T14:17:24Z","title":"Relaxed Quantization for Discretized Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.01875","snapshot_observed_at":"2026-08-05T21:16:24.936792Z","title":"Relaxed quanti- zation for discretized neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:24.936792Z"},"links":{"cited_paper":"/paper/1810.01875","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:c4309fa1da02c3da103cf1bfc26bd8f591f12a253fc93a6c163ccbc59837db2b","observation_id":"ee9dc887-5bf2-48a9-9959-b63426518154","resolution":{"observed_at":"2026-08-05T21:16:24.936792Z","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":"2026-08-05T21:16:31.447581Z","title":"Distinctive image features from scale- invariant keypoints","venue":null,"work_id":"2ffc860e-bbf9-47d3-aaa9-55d8b60f8ec6","year":2004},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:25.115397Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:8987e5274693930dddf73803def3532bf79c6933a880fce364bc6eb232daec7e","observation_id":"c70e60e8-f74b-4bb3-9781-126bf15de658","resolution":{"observed_at":"2026-08-05T21:16:31.516288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.06440","last_updated":"2017-06-08T19:53:26Z","snapshot_observed_at":"2026-08-07T07:29:29.524604Z","submitted_at":"2016-11-19T22:48:30Z","title":"Pruning Convolutional Neural Networks for Resource Efficient Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.06440","snapshot_observed_at":"2026-08-05T21:16:25.292863Z","title":"Pruning convolutional neural networks for resource efficient inference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:25.292863Z"},"links":{"cited_paper":"/paper/1611.06440","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:abfafabe3671f52624f0e7dbbd74a951e7e35fcee4a67e2bb6c89f7cc44f6ba7","observation_id":"89e7fdf7-3075-485d-9bd5-b0f4909225dc","resolution":{"observed_at":"2026-08-05T21:16:25.292863Z","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":"2026-08-05T21:16:31.272582Z","title":"Soat: A scene-and object-aware transformer for vision-and-language navigation","venue":null,"work_id":"72f6f715-8128-456d-9484-3c288fd330fd","year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:25.447804Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:d02f553b2803a7684497f36732f75b8b8e1c6d5ad10cbae13a731d6d3ee58d78","observation_id":"6e762497-5571-46aa-8e41-9b8d4f8603ee","resolution":{"observed_at":"2026-08-05T21:16:31.358741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:25.518136Z","title":"Up or down? adap- tive rounding for post-training quantization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:25.518136Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:168228668bf46f219c5adae479e1c8af071fb6f1b8ac9d0be925798c4c4b4b51","observation_id":"ee3932fc-c7b6-41bc-98d3-69b8faadde68","resolution":{"observed_at":"2026-08-05T21:16:25.518136Z","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":"2026-08-05T21:16:31.120114Z","title":"Gradient- free structured pruning with unlabeled data","venue":null,"work_id":"0d529c5f-6268-48c0-884f-4df046fe8a84","year":2023},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:25.604298Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:fce434dec187827b21d9b7b4ffe4f7f0d82a85709e05341a6dd7225939c93457","observation_id":"10e07c3a-563a-4dc2-a8ad-df76a93e3465","resolution":{"observed_at":"2026-08-05T21:16:31.182875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:30.966343Z","title":"Do vi- sual imaginations improve vision-and-language navigation agents? In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 3846–3855, 2025","venue":null,"work_id":"115ac37b-6d21-4597-b360-9a6fd2fa5eb6","year":2025},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:25.735960Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:8b9bef9a3e2d5d7e2a008b3b6af520ae480efee07ecab83d944ae8216da69862","observation_id":"6805fda0-d190-4980-8c4b-e74c82baa80d","resolution":{"observed_at":"2026-08-05T21:16:31.028732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:30.864814Z","title":"Reverie: Remote embodied visual referring expression in real indoor environments","venue":null,"work_id":"801b2fc8-557a-4904-984f-63c5890866b3","year":2020},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:25.852909Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:93d6290e7bbc71bd3228eaf27eaf122a34dc755979423c10cbb92e60179863a6","observation_id":"fc0c3a03-1271-45e6-8cab-65f71a67a71b","resolution":{"observed_at":"2026-08-05T21:16:30.909191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:25.982342Z","title":"Orb: An efficient alternative to sift or surf","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:25.982342Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:0f2c403b426048b00c6c47bbba2f6ee76457545723a7ee7207a97d6e5a2fa427","observation_id":"3e44a65d-fbc5-4150-9d81-cbf69d181fe6","resolution":{"observed_at":"2026-08-05T21:16:25.982342Z","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":"2026-08-05T21:16:30.709763Z","title":"Habitat: A platform for embodied ai research","venue":null,"work_id":"f6f96310-813d-4398-837c-b3ad0335cbc6","year":2019},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.070327Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:629a7fdb1959b8f8c3e9e34a7aa8d036c0a933ab954c176e3b7fe096cf6310f2","observation_id":"bc81ae3a-7b86-4100-b169-4ac9626d267f","resolution":{"observed_at":"2026-08-05T21:16:30.777281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.17634","last_updated":"2024-09-26T08:31:27Z","snapshot_observed_at":"2026-08-05T23:55:38.892035Z","submitted_at":"2024-09-26T08:31:27Z","title":"P4Q: Learning to Prompt for Quantization in Visual-language Models","version":1},"cited_work":{"arxiv_id":"2409.17634","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.17634","snapshot_observed_at":"2026-08-05T21:16:27.572764Z","title":"P4Q: Learning to Prompt for Quantization in Visual-language Models","venue":"cs.CV","work_id":"4922cc7c-0e48-4090-9a9e-4b81d00e08f9","year":2024},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.143127Z"},"links":{"cited_paper":"/paper/2409.17634","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:19e9ef55441aaf2322256594cc08e633e8da7343922f0147d244e689276bcb92","observation_id":"9aca160b-6137-472f-9e4f-90bc007bd49a","resolution":{"observed_at":"2026-08-05T21:16:27.643236Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:30.526619Z","title":null,"venue":null,"work_id":"cb307303-7d7a-40c7-9275-b38cfcdfc72f","year":2023},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.147183Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:0467670d88d344abd23ba79e258e3e6f008082acdb6bbef55ebcb7a52197088b","observation_id":"6c392954-0e24-4427-b0d4-fd4379c04705","resolution":{"observed_at":"2026-08-05T21:16:30.622602Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:30.320011Z","title":"Branchynet: Fast inference via early exiting from deep neural networks","venue":null,"work_id":"47697399-f312-4772-8eb4-048d33d04597","year":2016},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.181663Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:63fb28321da5b6370cd1719e9836d169384f240bc1a91d8a84aacff30bcd34a5","observation_id":"e6585886-2e71-48ab-a08c-e429b6522992","resolution":{"observed_at":"2026-08-05T21:16:30.419219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:30.113945Z","title":"Vision-and-dialog navigation","venue":null,"work_id":"f6a27c91-d825-4c3e-9b86-2b2686604490","year":2020},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.239274Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:f5080c5057a73eb043228fd9bc772fec9e51264c0c173e7fd0c41c6168704ca9","observation_id":"15b46aa2-1246-4fd4-9cfd-e73b6af9a43a","resolution":{"observed_at":"2026-08-05T21:16:30.241668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11452","last_updated":"2020-05-22T17:02:41Z","snapshot_observed_at":"2026-08-07T13:50:20.069427Z","submitted_at":"2019-05-27T19:03:40Z","title":"Mixed Precision DNNs: All you need is a good parametrization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11452","snapshot_observed_at":"2026-08-05T21:16:26.312095Z","title":"Mixed precision dnns: All you need is a good parametrization","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.312095Z"},"links":{"cited_paper":"/paper/1905.11452","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:d52956cc006c391499b24035665ae421a518335f661c7967d3898f86c15e05b7","observation_id":"d9856914-0fc4-41e5-9e00-f83f46834d5d","resolution":{"observed_at":"2026-08-05T21:16:26.312095Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07795","last_updated":"2022-10-14T13:26:41Z","snapshot_observed_at":"2026-08-03T13:04:29.259108Z","submitted_at":"2022-10-14T13:26:41Z","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.07795","snapshot_observed_at":"2026-08-05T21:16:26.354820Z","title":"Efficientvlm: Fast and accurate vision-language mod- els via knowledge distillation and modal-adaptive pruning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.354820Z"},"links":{"cited_paper":"/paper/2210.07795","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:a7efe26b48f2b4bce1576712f21c7de880f1306648d15d9914fb83720699319f","observation_id":"f383c027-162a-4247-b886-e8043189ed58","resolution":{"observed_at":"2026-08-05T21:16:26.354820Z","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":"2026-08-05T21:16:29.869800Z","title":"Skipnet: Learning dynamic routing in convolu- tional networks","venue":null,"work_id":"9b090406-30b3-43c0-b605-21f80351354e","year":2018},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.431616Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:d5e34910ebf1343184bbf75fb5bd9c311728b811f8e7c1cf02c6daee399cda6a","observation_id":"6824a69f-a019-4722-857d-ea04a0903f87","resolution":{"observed_at":"2026-08-05T21:16:29.969622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:29.659731Z","title":"Image quality assessment: from error visibility to structural similarity","venue":null,"work_id":"54382d96-9109-41bf-b6ed-969102091dde","year":2004},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.519752Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:b0d4cdf5f6f4f7809fbc83b5a096e308bc6a71e30bdcc6eb3abe00c4951e823b","observation_id":"3295c586-93ef-4b21-bb09-52c502e15d7d","resolution":{"observed_at":"2026-08-05T21:16:29.757113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:29.456732Z","title":"Scaling data generation in vision-and-language navigation","venue":null,"work_id":"75333d23-25e5-4993-9953-3d795c0c5287","year":2023},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.605460Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:bc83c1277bf357d525870816fc07ccf51d918558d67aff96b65b0a6298e61e45","observation_id":"a5176f39-20a9-40b2-9d9b-f92a3fa76101","resolution":{"observed_at":"2026-08-05T21:16:29.559449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:29.257993Z","title":"Wang et al","venue":null,"work_id":"c00cfb9b-09ff-472e-8208-519893cf2d2a","year":2024},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.666964Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:0cef4db025d9463bad13735498840429d9e231046fd8e299b441408ed42b40b1","observation_id":"ed2e4ac4-c37a-47cd-907e-c99340ad57cd","resolution":{"observed_at":"2026-08-05T21:16:29.374156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:29.055749Z","title":"Wasserman et al","venue":null,"work_id":"34c3d9bb-7414-41a8-8243-c5fe624566e0","year":2023},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.786338Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:dac5ff6b16997ee840cb6acb8e9578e524408c5b075d6c8c54f82c7ebe908dec","observation_id":"468cb6f1-8414-4714-9ecf-35df5e35247b","resolution":{"observed_at":"2026-08-05T21:16:29.140019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.12993","last_updated":"2020-04-27T17:58:05Z","snapshot_observed_at":"2026-08-06T01:22:26.725556Z","submitted_at":"2020-04-27T17:58:05Z","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.12993","snapshot_observed_at":"2026-08-05T21:16:26.875019Z","title":"Deebert: Dynamic early exiting for accelerating bert inference","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.875019Z"},"links":{"cited_paper":"/paper/2004.12993","citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:06afc62ff65f076789e1976cf8e16c444d63fe021585d0c1b773cbf342b9da16","observation_id":"ae3fcb53-9d36-4050-ba7a-e5247cbe5855","resolution":{"observed_at":"2026-08-05T21:16:26.875019Z","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":"2026-08-05T21:16:28.875615Z","title":"Deer-vla: Dynamic inference of multimodal large language models for efficient robot execution","venue":null,"work_id":"74d9c96e-56d1-476b-aa30-b8c4bfd84b8f","year":2024},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:26.967215Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:7dbe19cea065a3101aa18fc89fc94134f127a1f1f3de545dd294237ab74ce00e","observation_id":"0ba175dd-72bc-4977-bbc4-5c6447629910","resolution":{"observed_at":"2026-08-05T21:16:28.973165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:28.671078Z","title":"Fsim: A feature similarity index for image quality assessment.IEEE transactions on Image Processing, 20(8):2378–2386, 2011","venue":null,"work_id":"92c45601-35a7-4668-bec6-23452b5431f8","year":2011},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:27.047546Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:7510ec708c35460dac7d3f6fcd2ec04eedf33c39b4fd74eef8b343a5c2306fd1","observation_id":"53ca755a-2518-49c0-a196-71e20bd166c0","resolution":{"observed_at":"2026-08-05T21:16:28.763472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:28.503370Z","title":"Zhang et al","venue":null,"work_id":"df59b711-47c4-4b72-8abe-5432d3545187","year":null},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:27.142313Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:e22e0738b10f3401290b102e20c5958c4ac8d2ea2d322ff9c1bd5fa152d689e3","observation_id":"17b60309-bd93-4e2a-bddb-2c9371f208b8","resolution":{"observed_at":"2026-08-05T21:16:28.572046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:28.335171Z","title":"The unreasonable effectiveness of deep features as a perceptual metric","venue":null,"work_id":"cd6ca4c7-6349-4136-a8b9-fce9434e8afc","year":2018},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:27.221282Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:6d849eb7a9069f6a7ecec9d816f646cf5e39d86fa12641d38b3b39c427c189c5","observation_id":"2d96d2e8-4b69-4c40-bf82-7684789e341f","resolution":{"observed_at":"2026-08-05T21:16:28.428640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:28.156308Z","title":"Soon: Scenario oriented object nav- igation with graph-based exploration","venue":null,"work_id":"1f834074-b2a9-4dbe-b283-283c702a2374","year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:27.267954Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:d9f46e4e20786e3a351c911e3cda26648ccc857adc5ec718e6c5053d3236c058","observation_id":"9f9d8f8f-ae3c-4c86-b550-dd3d1bddd16b","resolution":{"observed_at":"2026-08-05T21:16:28.251212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:28.001556Z","title":"Learning unforeseen robustness from out-of-distribution data using equivariant domain translator","venue":null,"work_id":"55e0fafe-21e2-4dac-8ca2-b086136bdbd2","year":2023},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:27.365685Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:fdf8742a077168c2eeb7e3a2e9317b000b732b22b53720adad4543351e99adbd","observation_id":"192547e1-ffc2-4875-bd68-0c5f044612bb","resolution":{"observed_at":"2026-08-05T21:16:28.059247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T21:16:27.834364Z","title":"Zhu et al","venue":null,"work_id":"03bd70ea-9e3f-42a0-80bc-dadda51c52d4","year":2021},"citing_paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T21:16:27.443463Z"},"links":{"citing_paper":"/paper/2508.09262"},"observation_digest":"sha256:f64eb6cf81544857bebdba3784c96d618a7008ab087ab9e3dec523428af8d9f3","observation_id":"a02ee394-4508-4238-aaf4-526719577bb5","resolution":{"observed_at":"2026-08-05T21:16:27.898133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.09262","last_updated":"2025-08-12T18:05:33Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T09:26:18.699272Z","submitted_at":"2025-08-12T18:05:33Z","title":"Harnessing Input-Adaptive Inference for Efficient VLN"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":1,"verified_fuzzy":54},"total_outbound_references":68},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 1 inbound Pith citation observation for arXiv:2508.09262."}