{"as_of":"2026-08-20T01:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e1a06b1bc853d866e97eb88bb0ebc790f12dc0fc864cda3d7cc4885be0cd2991","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T02:37:26.640826Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2603.06828/citation-record","integrity":"/paper/2603.06828/integrity","json":"/paper/2603.06828/citation-record.json","paper":"/paper/2603.06828"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:19.736348Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:19.736348Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:ae33f0bff9cd9ba65208fdc24d0d7474812fb951be2e4dcd418c28820a983246","observation_id":"61de1ccb-bf3c-47e0-8477-a634265dffd0","resolution":{"observed_at":"2026-08-03T02:37:19.736348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:19.835019Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:19.835019Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:fe0c9fe307678b3ebb630f3109c8250c4b883a46307679cf167d3676ed67343c","observation_id":"74a6071d-ec1e-47cc-89f7-344fa726e26b","resolution":{"observed_at":"2026-08-03T02:37:19.835019Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:20.006991Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.006991Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:d4287253e5eae712041676ab26c821e61442a0c68d8a0d5516de7ed5280b545d","observation_id":"62d655c9-7c45-427a-8c35-db3ad8aa10a5","resolution":{"observed_at":"2026-08-03T02:37:20.006991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.13171","last_updated":"2020-08-30T04:28:13Z","snapshot_observed_at":"2026-08-18T16:20:55.129945Z","submitted_at":"2020-06-23T17:18:54Z","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.13171","snapshot_observed_at":"2026-08-03T02:37:20.146322Z","title":"arXiv preprint arXiv:2006.13171 (2020) 2","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.146322Z"},"links":{"cited_paper":"/paper/2006.13171","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:382c22d6ec5b47bc9989902539d6c8a63531a21a645777001da8264b45dfa0df","observation_id":"a02c91fd-b528-4cc6-92a4-41ebc81bbdbf","resolution":{"observed_at":"2026-08-03T02:37:20.146322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:20.243728Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.243728Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:7b42ad5a205ef622cd73644f62ab0da7efe206e38940d23a59e360087d26b56c","observation_id":"37ca9be5-f58d-416e-8fd1-abe826157a94","resolution":{"observed_at":"2026-08-03T02:37:20.243728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:20.377804Z","title":"In: IEEE Winter Conf","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.377804Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:0afaac0eeadc7b00be119902f796e48f509972fa556fcfef1aae3f932507ecc9","observation_id":"5d56f11e-eaa2-4295-8548-9c18bfd4abfc","resolution":{"observed_at":"2026-08-03T02:37:20.377804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:20.499145Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.499145Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:257f66a824db3c9d8e8e4810cf6d933e169f00981d75b077e0407ea606f06c24","observation_id":"32675c1e-23fa-4f30-8f74-dd708d74b4cf","resolution":{"observed_at":"2026-08-03T02:37:20.499145Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14238","last_updated":"2024-01-15T15:23:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-21T18:59:31Z","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.14238","snapshot_observed_at":"2026-08-03T02:37:20.615302Z","title":"arXiv preprint arXiv:2312.14238 (2024) 7","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.615302Z"},"links":{"cited_paper":"/paper/2312.14238","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:c99e0876d042519d3190e5340afa4fbd05146ff90cf7e88beb3c10af895e6c83","observation_id":"d5685eca-c809-4673-a7b7-7c685349eafd","resolution":{"observed_at":"2026-08-03T02:37:20.615302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07689","last_updated":"2024-06-11T20:10:31Z","snapshot_observed_at":"2026-08-19T22:50:03.085191Z","submitted_at":"2024-06-11T20:10:31Z","title":"Evidence for Non-zero Turbulence in the Protoplanetary disc around IM Lup","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07689","snapshot_observed_at":"2026-08-03T02:37:20.740250Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.740250Z"},"links":{"cited_paper":"/paper/2406.07689","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:e6fb27e382d55176e42fdcba62f8bcbfc7e4b3fedd327865ece9ea3d3e70f7e9","observation_id":"f69a2ea6-b676-4959-9e58-c72a020a44b2","resolution":{"observed_at":"2026-08-03T02:37:20.740250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:20.813889Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.813889Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:523c6cdf35f3a22ec43c529dc766feb7c723ede434f0a3a9df6b60bc53eeaa65","observation_id":"9bf8646c-b430-4922-be4d-21f7be9b2551","resolution":{"observed_at":"2026-08-03T02:37:20.813889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14515","last_updated":"2024-10-30T13:38:10Z","snapshot_observed_at":"2026-08-17T20:22:23.176057Z","submitted_at":"2024-06-20T17:26:01Z","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14515","snapshot_observed_at":"2026-08-03T02:37:20.820402Z","title":"arXiv preprint arXiv:2406.14515 (2024) 3","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.820402Z"},"links":{"cited_paper":"/paper/2406.14515","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:4fbe630a0819b8b942b1575b7d978e04bcec704f10996029e67ef4704e216868","observation_id":"7943e501-1c3d-4caa-adb1-bb1002222058","resolution":{"observed_at":"2026-08-03T02:37:20.820402Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:20.888127Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.888127Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:443dfa2006f10e30a2a5111d18f17d73f5cbbd82bbc963ba14404605941c295d","observation_id":"a92e50b6-7fcd-4a37-b7de-dbd82c0e0c99","resolution":{"observed_at":"2026-08-03T02:37:20.888127Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:20.962545Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:20.962545Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:1c44eae0c1a1673bb4d68b73962a916ddcf24943926f7e882d94d7555e353a69","observation_id":"94781632-99ad-4144-a517-5a8417f01a6f","resolution":{"observed_at":"2026-08-03T02:37:20.962545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:21.041291Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:21.041291Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:2bcd7d653a8a45fe2fe29f2833709896ad24f89a7fad20942507a2c1d0160425","observation_id":"f1ab22c9-403f-4741-9e9d-6f3829eeadd2","resolution":{"observed_at":"2026-08-03T02:37:21.041291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:21.139110Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:21.139110Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:941030cbee86e799a82d6be91701435049560b43cc9d410668a03de34e1f1466","observation_id":"90058a5e-ecce-477f-9a60-aeef7dbff735","resolution":{"observed_at":"2026-08-03T02:37:21.139110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:21.271625Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:21.271625Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:6e89f6246f2dea07d3d4e154af878239d12ff657d11bea528ed2e5137ee3562d","observation_id":"b9028ddf-af93-429f-be5c-40706ab9476a","resolution":{"observed_at":"2026-08-03T02:37:21.271625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:21.349759Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:21.349759Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:01e6b3d5c6b84cf915aa59f3925ea9f0ca2f5f419bae210caa80fa9bf0b5003e","observation_id":"53f4d7b6-4a8b-4dbf-a365-2249da8724cb","resolution":{"observed_at":"2026-08-03T02:37:21.349759Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:21.452141Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:21.452141Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:1786ef535424733555437576211b0330994de07b26574562f5c74ed5b14e98ad","observation_id":"c37ff485-8f97-42b8-b4a5-5ee9a3edc3d6","resolution":{"observed_at":"2026-08-03T02:37:21.452141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:21.543890Z","title":"Frontiers in Artificial Intelligence2, 28 (2019) 2","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:21.543890Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:679c7df4c63b96888caa6b2a0cb156db0a195e0389f2fb8a611e0639f51c1131","observation_id":"abebb1ff-a2ef-44bc-9f7f-1e728d7f19b2","resolution":{"observed_at":"2026-08-03T02:37:21.543890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:21.648673Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:21.648673Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:807fbc7bcdce1c178480f7c3e405390754b9e4efd8075b7854d15e700360035d","observation_id":"94535c59-9b7f-4a0f-b672-cda36553cf09","resolution":{"observed_at":"2026-08-03T02:37:21.648673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:21.762243Z","title":"In: IJCAI","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:21.762243Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:0b9215f46d94348906b38146d230783317c8bb33963bf57b3aa2f4604defd0cd","observation_id":"66b7f574-1c26-4d46-8832-3b6b22b53ca3","resolution":{"observed_at":"2026-08-03T02:37:21.762243Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:21.882573Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:21.882573Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:199f3621665915fe56012afd764c4b88ef6faeb1853af5255f49aea2c53d7be0","observation_id":"10a96a36-c6b6-49c9-b33b-37e95496b212","resolution":{"observed_at":"2026-08-03T02:37:21.882573Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:22.019882Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.019882Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:c56aab487efb95908969f766d6e27735f776b71a88167018612f27987f023c88","observation_id":"87d128b9-9e52-4af9-9124-87d00bb78597","resolution":{"observed_at":"2026-08-03T02:37:22.019882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13702","last_updated":"2023-07-17T01:08:39Z","snapshot_observed_at":"2026-08-13T18:02:27.155379Z","submitted_at":"2023-07-17T01:08:39Z","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13702","snapshot_observed_at":"2026-08-03T02:37:22.113901Z","title":"arXiv preprint arXiv:2307.13702 (2023) 3","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.113901Z"},"links":{"cited_paper":"/paper/2307.13702","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:4b5016c2dc425bcdd5d1f2e8b97745e2d2bf60a7239257292f5c6455117de9be","observation_id":"ee62f9f7-d2eb-4501-8a43-e682dfc30f75","resolution":{"observed_at":"2026-08-03T02:37:22.113901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:22.220900Z","title":"In: Proc","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.220900Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:2e14c1f836c81419431ada6e88969ecffb8555cc6359d2978390dedf75ed1ae7","observation_id":"c5a759ec-92f3-4a57-ba0d-cb2cee7e4027","resolution":{"observed_at":"2026-08-03T02:37:22.220900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:22.300528Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.300528Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:731e612210e20528e92eefea59533295b5797f00fee6b94dcc6114a72824aa55","observation_id":"09071d8f-9296-445e-ad02-ea022f57b337","resolution":{"observed_at":"2026-08-03T02:37:22.300528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.06355","last_updated":"2024-01-04T02:06:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-10T17:59:04Z","title":"VideoChat: Chat-Centric Video Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.06355","snapshot_observed_at":"2026-08-03T02:37:22.390087Z","title":"arXiv preprint arXiv:2305.06355 (2023) 7","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.390087Z"},"links":{"cited_paper":"/paper/2305.06355","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:6ba4434a98b735f6a1c01e4db09c2b420e527ad43f7273e42b7eb3c01b24151e","observation_id":"e5bda715-03e4-4ce3-ad6c-3d538140538d","resolution":{"observed_at":"2026-08-03T02:37:22.390087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.17005","last_updated":"2024-05-23T14:49:29Z","snapshot_observed_at":"2026-08-14T11:10:08.135537Z","submitted_at":"2023-11-28T17:59:04Z","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17005","snapshot_observed_at":"2026-08-03T02:37:22.472754Z","title":"arXiv preprint arXiv:2311.17005 (2023) 3","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.472754Z"},"links":{"cited_paper":"/paper/2311.17005","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:bdfe217550e92cb544817e9a97dd836659034573b3422df473df8d9573cef995","observation_id":"30f66e08-de3e-44e7-a9d2-d0ad4ff761ee","resolution":{"observed_at":"2026-08-03T02:37:22.472754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:22.582006Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.582006Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:9fc0fd0604d908c56104993ffdc106fcaf28f4dd29cf0e2167d863213555e8af","observation_id":"3ff2a9a4-8e93-4804-b9ec-dc067f9bc2e8","resolution":{"observed_at":"2026-08-03T02:37:22.582006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.20050","last_updated":"2023-05-31T17:24:00Z","snapshot_observed_at":"2026-08-17T09:42:34.746112Z","submitted_at":"2023-05-31T17:24:00Z","title":"Let's Verify Step by Step","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.20050","snapshot_observed_at":"2026-08-03T02:37:22.688571Z","title":"arXiv preprint arXiv:2305.20050 (2023) 3","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.688571Z"},"links":{"cited_paper":"/paper/2305.20050","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:36fa7d322df5caf1e9f6548af0e68c3e9b03f4f2819bc39dd84789c8dc578f0b","observation_id":"a66e45e6-5f9c-409c-8106-f5c8c5b5e16b","resolution":{"observed_at":"2026-08-03T02:37:22.688571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:22.826015Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.826015Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:c1f722a84f15372d83fa026c8b40b20d3a9dd187b6888b19739055d2bfa1b293","observation_id":"e1cca0e9-76f2-45c9-a5c5-caa64e346fb6","resolution":{"observed_at":"2026-08-03T02:37:22.826015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14566","last_updated":"2024-03-25T06:05:24Z","snapshot_observed_at":"2026-08-19T10:24:15.607193Z","submitted_at":"2023-10-23T04:49:09Z","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14566","snapshot_observed_at":"2026-08-03T02:37:22.957720Z","title":"arXiv preprint arXiv:2310.14566 (2023) 3","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:22.957720Z"},"links":{"cited_paper":"/paper/2310.14566","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:95feb8905a3dce92512e24d61d3eabb6b9421cd617199767d3900006327ef70e","observation_id":"c2b15949-3f60-431a-9e8c-a6f91fc1668c","resolution":{"observed_at":"2026-08-03T02:37:22.957720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:23.022324Z","title":"(2021) 2","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:23.022324Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:076813ae31bc312452cbafff161f0d9bbaf1ee6d50776f1e5e421f9e12ee5fee","observation_id":"74c32b8c-ba4b-4069-ae4c-d0a9d0757461","resolution":{"observed_at":"2026-08-03T02:37:23.022324Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:23.099966Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:23.099966Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:b58b823ef8c5a2e401b1e875f39e12f5c11140438301dae71f3aa2529e11f79f","observation_id":"2fbf4258-cf6e-4846-b3d6-0389029ce2d8","resolution":{"observed_at":"2026-08-03T02:37:23.099966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:23.159663Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:23.159663Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:6a49f1239ddce7c268c7590e44fcbe71603c3999e657d90ec8817bb20eb7d02b","observation_id":"93f03e77-765d-4616-a6f3-ba8123f83228","resolution":{"observed_at":"2026-08-03T02:37:23.159663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:23.280133Z","title":"In: AAAI","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:23.280133Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:15a2c40f280d8dacebcdca0ca1d6fe56c6e98af27c9b0a4cfe4ee672d877d4fa","observation_id":"133adae4-59f4-4dbe-9eff-8e72eb57b9f9","resolution":{"observed_at":"2026-08-03T02:37:23.280133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:23.438425Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:23.438425Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:eaf659595af2e9935368fdc5dc15ff5643f785a8f5a3a20180daab67364b000b","observation_id":"610d2eeb-32e5-41c0-b56e-e5f3b16e7b26","resolution":{"observed_at":"2026-08-03T02:37:23.438425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:23.623206Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:23.623206Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:e4edd265b3ac505ab8f1b293fd56badf7c47ab4bf0a70c02d5f777614b896729","observation_id":"6b2e8e5b-478c-4825-bc85-18572306a142","resolution":{"observed_at":"2026-08-03T02:37:23.623206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:23.762178Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:23.762178Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:146658c67283e978e7009f5fb7faba98b0925b99f96a38525e9b03419a7098dc","observation_id":"f93f82fe-d10f-4736-b31d-b8f9b66c6269","resolution":{"observed_at":"2026-08-03T02:37:23.762178Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:23.928786Z","title":"In: Proc","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:23.928786Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:fe45658ebf141a49a8756c089bb43a9b1f672d47693240f8a91b913c4c1e4c28","observation_id":"e2bba617-1fba-47b0-ab68-9c19d19dbc64","resolution":{"observed_at":"2026-08-03T02:37:23.928786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.030068Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.030068Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:ecbfed86951df5f93f857a0b6843e694d143d9b92e843d9bce69e7ef4869f513","observation_id":"c4945284-f875-4f6f-8c0b-66377a7736a0","resolution":{"observed_at":"2026-08-03T02:37:24.030068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.125338Z","title":"In: Proc","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.125338Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:3ffb6673d4ed70960a526a65b27d151063b79ad494a7501dd44bd86d94f82ce5","observation_id":"c9f2c7bf-d71a-41a9-872b-2ae31496f101","resolution":{"observed_at":"2026-08-03T02:37:24.125338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.217193Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.217193Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:6d293ce46144c9dc555c34bd49059d8523621239713c790fd9d9893d30384ee1","observation_id":"cd9b8f21-e620-40e0-a152-0707ecc55018","resolution":{"observed_at":"2026-08-03T02:37:24.217193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.343025Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.343025Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:4bfd75cd24fda1ed4d99ee578bd56672785a88beb82432d867ca889dd9057513","observation_id":"ab226b7c-990c-42e4-9ad4-4ea32ad88316","resolution":{"observed_at":"2026-08-03T02:37:24.343025Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.443889Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.443889Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:1964fb1ccc1357a7fe7cb8b428d7454ea5669cf839eaaa9b8838ecc5c8656226","observation_id":"71f96719-5cab-4864-be8d-c57b1429dc17","resolution":{"observed_at":"2026-08-03T02:37:24.443889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.528235Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.528235Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:7e46550094e51a2c991cba7001565fa58f5ada9643f066c0dd24a8a590434ed6","observation_id":"a3a37de2-bf22-48de-a999-b6587ee4676c","resolution":{"observed_at":"2026-08-03T02:37:24.528235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.637590Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.637590Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:1f3bc2b831e9c552f71f5d90bca0d6e3384c32f524b18f4df6b5458076908917","observation_id":"5daebc95-c4b1-4f0a-b1fa-a1bd14cf0a52","resolution":{"observed_at":"2026-08-03T02:37:24.637590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.709936Z","title":"In: Proc","venue":null,"work_id":null,"year":2072},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.709936Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:15738e7d180ac86227d42ccdad875473a1f489879bb673612175f9b53234b39e","observation_id":"9cebbcf6-4468-43fe-b017-dbe26b21a4af","resolution":{"observed_at":"2026-08-03T02:37:24.709936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.835482Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.835482Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:cdcee0b1b2ea861df9ebe19eb43472194b91aa6c647a60fd63dade392a38f3b5","observation_id":"2c745576-36cf-4e88-857c-0e554418cf6d","resolution":{"observed_at":"2026-08-03T02:37:24.835482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:24.926648Z","title":"In: Conf","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:24.926648Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:9c18b25b2d3509d2dd8f301c89678d1b1ec538d452affcb9d918c4e1f78bb2d7","observation_id":"c02a08e2-b6fb-4db1-b49c-2196de1de1c5","resolution":{"observed_at":"2026-08-03T02:37:24.926648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:25.055708Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:25.055708Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:e03fd21369d460f7d83b6d148c52993a77b7a5e31cd907787962b3189a3e5d56","observation_id":"7a2fc1e8-51dd-44f4-a2b9-d7478089b7c9","resolution":{"observed_at":"2026-08-03T02:37:25.055708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.17225","last_updated":"2024-12-04T06:11:50Z","snapshot_observed_at":"2026-08-19T15:22:00.036487Z","submitted_at":"2023-12-28T18:53:39Z","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.17225","snapshot_observed_at":"2026-08-03T02:37:25.216533Z","title":"arXiv preprint arXiv:2312.17225 (2024) 3 18 M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:25.216533Z"},"links":{"cited_paper":"/paper/2312.17225","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:d9bbea9c89582ddb3aeae99abec27d57583ff24ea5b5a2d300a8d73707cd01ac","observation_id":"b9cb1764-6e10-4e9f-852c-c8c205ee658e","resolution":{"observed_at":"2026-08-03T02:37:25.216533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:25.363585Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:25.363585Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:d8c56894b0f284f076ebf9278be678720179d20ae3b8fa12f9cf793ba8e8b8e3","observation_id":"9b2f9669-a7b7-4acf-85e1-9c4c8f27bca7","resolution":{"observed_at":"2026-08-03T02:37:25.363585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:25.507482Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:25.507482Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:b5f84f6d77fe3975579c67e9bfccab137fe68a997880a81d0aa1c2140065a33b","observation_id":"3a5f6993-48b2-486f-8891-a463f107acee","resolution":{"observed_at":"2026-08-03T02:37:25.507482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:25.654791Z","title":"In: IEEE Int","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:25.654791Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:a2f71e67c49bee4ca662e7f31d812263df2e642e9df4e5f82abf148532053b27","observation_id":"1dcffc07-98a1-4a6a-84da-687e2f4f722b","resolution":{"observed_at":"2026-08-03T02:37:25.654791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:25.759970Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:25.759970Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:a0f8985ab5f18e5280e621bcb4df025d62bdd8ddfad40d924e9da65e4536f5e6","observation_id":"beb06363-880a-4e94-8620-7f50deab17c5","resolution":{"observed_at":"2026-08-03T02:37:25.759970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08958","last_updated":"2023-08-28T14:58:05Z","snapshot_observed_at":"2026-08-17T03:52:34.752440Z","submitted_at":"2023-04-18T12:49:39Z","title":"Prediction of equivalent sand-grain size and identification of drag-relevant scales of roughness -- a data driven approach","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.08958","snapshot_observed_at":"2026-08-03T02:37:25.837308Z","title":"arXiv preprint arXiv:2304.08958 (2023) 2","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:25.837308Z"},"links":{"cited_paper":"/paper/2304.08958","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:276f885ddf1be741caff17a1eb8b2ab97ee80fec616c807d660ba0f3ef972cca","observation_id":"92a8930c-58dd-4c5b-883c-c5c01ed2546e","resolution":{"observed_at":"2026-08-03T02:37:25.837308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:25.939415Z","title":"In: IEEE Conf","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:25.939415Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:40db7e7e2a255526791cd470cdffa5073c0660ebdfc036cdff421b20bec615c5","observation_id":"ef1fa466-450d-40f3-ab40-4ca4f2ffee75","resolution":{"observed_at":"2026-08-03T02:37:25.939415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:26.108372Z","title":"In: ACM Int","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:26.108372Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:23083c8d2124930dc8e254bb3bdbab59af92617f5e64a62083083dde58cb8165","observation_id":"b9eb8b63-361d-4a13-b9fc-8caa1a7772fc","resolution":{"observed_at":"2026-08-03T02:37:26.108372Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:26.194533Z","title":null,"venue":null,"work_id":null,"year":2048},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:26.194533Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:ef05f4735aebc16a12aa842be130bb3a9c8ef01d8422b4f2af12eeacf78c60f5","observation_id":"c93abc4e-d4c2-49ab-bdaf-768342758cb2","resolution":{"observed_at":"2026-08-03T02:37:26.194533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:37:26.327887Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:26.327887Z"},"links":{"citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:ecc51c94ea7fbb0938b685577d70208ce291966a2a20e788a128386fc7ffdd8b","observation_id":"3ab01772-4db7-4392-8999-11bf53a630bd","resolution":{"observed_at":"2026-08-03T02:37:26.327887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.10122","last_updated":"2024-10-01T12:07:31Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-11-16T10:59:44Z","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.10122","snapshot_observed_at":"2026-08-03T02:37:26.487212Z","title":"arXiv preprint arXiv:2311.10122 (2023) 7","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:26.487212Z"},"links":{"cited_paper":"/paper/2311.10122","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:f6fbb9d7ca7ea0232d950aa6b4b53326e89e3b4261b9ec078395d8d74751edef","observation_id":"1c1ae80c-5acb-4458-b449-1e364f332cc0","resolution":{"observed_at":"2026-08-03T02:37:26.487212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02858","last_updated":"2023-10-25T06:23:31Z","snapshot_observed_at":"2026-08-13T15:50:38.254753Z","submitted_at":"2023-06-05T13:17:27Z","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02858","snapshot_observed_at":"2026-08-03T02:37:26.640826Z","title":"arXiv preprint arXiv:2306.02858 (2023) 7","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-03T02:37:26.640826Z"},"links":{"cited_paper":"/paper/2306.02858","citing_paper":"/paper/2603.06828"},"observation_digest":"sha256:307d545d0fe029a84b082e26a2620a368323f0d95fbaac92573246d78696f38d","observation_id":"97085c3e-b09b-476f-8824-f627f74dfda8","resolution":{"observed_at":"2026-08-03T02:37:26.640826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.06828","last_updated":"2026-07-31T11:30:44Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T18:44:13.661870Z","submitted_at":"2026-03-06T19:43:26Z","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":63,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":63},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2603.06828."}