{"as_of":"2026-08-06T18:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ba5b420dc2e72676e5cd5910c2c19596bbe4cb618cb42bf6be8a932d6df96f53","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":15,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T10:17:59.198656Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-04T16:29:57.224762Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2507.06448","last_updated":"2026-04-14T16:31:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-08T23:22:34Z","title":"Perception-Aware Policy Optimization for Multimodal Reasoning","version":5},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-19T05:11:54.685897Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2507.06448"},"observation_digest":"sha256:b8b95cf0ea380b72a7cff5a4be32ae122f228d59c346328cc580464c9a591a1d","observation_id":"abdc0de2-7310-428f-85bd-6b68a72e6217","resolution":{"observed_at":"2026-06-09T03:07:59.867366Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-08-05T10:17:59.198656Z","title":"arXiv preprint arXiv:2505.21457","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.04243","last_updated":"2025-09-04T14:17:01Z","snapshot_observed_at":"2026-08-06T03:24:32.093755Z","submitted_at":"2025-09-04T14:17:01Z","title":"Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T10:17:59.198656Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2509.04243"},"observation_digest":"sha256:6c4d49ca23736060d6ab5dd6d649f0ba1076c718e3b8c3884353b6d2b327a518","observation_id":"ca9b32fc-55d6-44e6-a355-b616183806ab","resolution":{"observed_at":"2026-08-05T10:17:59.198656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2509.07969","last_updated":"2025-09-09T17:54:21Z","snapshot_observed_at":"2026-07-30T05:21:39.737665Z","submitted_at":"2025-09-09T17:54:21Z","title":"Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-18T01:17:55.500268Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2509.07969"},"observation_digest":"sha256:04bc7450d0a5fb16a8e95dbd6b2aafb7325cb5b9fcca46f0b79b26a41a402557","observation_id":"dce92b3f-4e41-44b5-80c0-70e59af4e30f","resolution":{"observed_at":"2026-06-09T03:07:59.867366Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2511.19972","last_updated":"2026-05-07T02:58:13Z","snapshot_observed_at":"2026-07-06T22:36:53.831174Z","submitted_at":"2025-11-25T06:31:57Z","title":"Boosting Reasoning in Large Multimodal Models via Activation Replay","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-17T05:05:48.682057Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2511.19972"},"observation_digest":"sha256:fc00a1e45480e027c3297bcb7b9f9b6006cc88fe687ae7bd8da6ab37a19f478a","observation_id":"d433e0b6-4e9f-406c-bacc-7f6c33e6e983","resolution":{"observed_at":"2026-06-09T03:07:59.867366Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2604.06777","last_updated":"2026-04-08T07:48:07Z","snapshot_observed_at":"2026-08-06T14:41:06.876472Z","submitted_at":"2026-04-08T07:48:07Z","title":"Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-10T18:20:02.559108Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2604.06777"},"observation_digest":"sha256:f31f1a9dbe07cc6d5a49449510acaff0251754edd103fa7ace7fae9f5457fae3","observation_id":"a3849417-c099-4ddc-a179-1b1a96fbc4f9","resolution":{"observed_at":"2026-06-09T03:07:59.867366Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2605.15542","last_updated":"2026-05-15T02:27:41Z","snapshot_observed_at":"2026-08-01T22:59:27.797060Z","submitted_at":"2026-05-15T02:27:41Z","title":"DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-19T14:24:48.938948Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2605.15542"},"observation_digest":"sha256:63ab2b9a3b6b1e81ed73c1ad68be16d3f2d04c984b301522769308b2d7ccddba","observation_id":"1a4d7a1a-775e-41bf-a88a-2db475b2cb96","resolution":{"observed_at":"2026-06-09T03:07:59.867366Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2605.19538","last_updated":"2026-05-19T08:38:44Z","snapshot_observed_at":"2026-07-06T23:30:16.094579Z","submitted_at":"2026-05-19T08:38:44Z","title":"CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-05-20T06:14:43.288597Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2605.19538"},"observation_digest":"sha256:94904af9210f664eb157aa2517016807353cae1f812eec809944a05a32e91aa1","observation_id":"ed2156ba-c96d-4735-bba7-3f3756ec9e4f","resolution":{"observed_at":"2026-06-09T03:07:59.867366Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2605.30639","last_updated":"2026-05-28T22:42:38Z","snapshot_observed_at":"2026-07-06T23:39:53.132531Z","submitted_at":"2026-05-28T22:42:38Z","title":"PInVerify: An Offline Embodied Benchmark for Active Instance Verification","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-29T07:30:59.306097Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2605.30639"},"observation_digest":"sha256:d09f3960de01105d6f208adf1fa6d671bd5f2320ad60d899973abe1f8c898988","observation_id":"67fcc637-bd7d-4b09-b37a-3cfe4cbc4c42","resolution":{"observed_at":"2026-06-29T07:33:13.558464Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2606.00096","last_updated":"2026-06-02T05:03:53Z","snapshot_observed_at":"2026-08-03T08:51:35.059162Z","submitted_at":"2026-05-25T13:06:59Z","title":"Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-06-29T23:11:14.114211Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2606.00096"},"observation_digest":"sha256:382aab16e1e5a0dcff34a7cd1de076750d6526b60c0bb4316643454ef45c76b6","observation_id":"1142b0b9-1dc7-44ff-8226-cda08adc69b1","resolution":{"observed_at":"2026-06-29T23:14:01.391342Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2606.01247","last_updated":"2026-05-31T14:00:10Z","snapshot_observed_at":"2026-07-06T23:41:48.357871Z","submitted_at":"2026-05-31T14:00:10Z","title":"Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-06-28T17:08:59.111306Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2606.01247"},"observation_digest":"sha256:f442a8b2bf17533ae3fc0a07cdac66518e99b0143ea695be1dbb53764ef93895","observation_id":"d4295b6b-f1c7-43e9-be18-c776224f4745","resolution":{"observed_at":"2026-06-28T17:12:24.813141Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2606.03577","last_updated":"2026-06-02T12:46:34Z","snapshot_observed_at":"2026-07-06T23:43:50.943530Z","submitted_at":"2026-06-02T12:46:34Z","title":"Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-06-28T10:48:24.523702Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2606.03577"},"observation_digest":"sha256:7064d91689fe29254ba7393acb6479f2ebc2a48655b65e202ae68f4acdeacabb","observation_id":"16f9fb93-a9d2-48ee-a297-28f0690b62cd","resolution":{"observed_at":"2026-07-02T02:36:27.100708Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2606.24233","last_updated":"2026-06-23T07:22:22Z","snapshot_observed_at":"2026-08-02T14:20:11.599861Z","submitted_at":"2026-06-23T07:22:22Z","title":"Latent Visual States for Efficient Multimodal Reasoning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-06-26T00:38:11.619574Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2606.24233"},"observation_digest":"sha256:359b9592f0987b6abb8bbb2811f18e294e3ab24e9cc554e792db64c6c64e67ab","observation_id":"ffebcac5-9d91-4928-b2bf-093d0989263a","resolution":{"observed_at":"2026-07-04T16:29:57.225996Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2606.26196","last_updated":"2026-06-24T15:20:32Z","snapshot_observed_at":"2026-07-07T00:00:31.981360Z","submitted_at":"2026-06-24T15:20:32Z","title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","version":1},"reference_index":207,"source":"pdf_text","source_observed_at":"2026-06-26T01:50:54.242508Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2606.26196"},"observation_digest":"sha256:a5ea420e18d03f8178a9075f1804e9b694dc4e03a2b9cd3800fc7efe76273bfa","observation_id":"2e088860-9e60-4a6a-9a2e-106b5e867db8","resolution":{"observed_at":"2026-07-04T15:09:55.084285Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.21457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-04T16:29:57.224762Z","title":"arXiv preprint arXiv:2505.21457 , year =","venue":"cs.CV","work_id":"2f6b9068-7d97-4dae-b9fb-d9c4acb49d40","year":2025},"citing_paper":{"arxiv_id":"2607.02479","last_updated":"2026-07-02T17:47:27Z","snapshot_observed_at":"2026-07-07T00:07:56.573640Z","submitted_at":"2026-07-02T17:47:27Z","title":"EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\\circ$","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-03T14:50:31.645497Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2607.02479"},"observation_digest":"sha256:bd39d30f43a5fc7f4b6f726ab8e9d4c02b2f38a4c674f45cff2baa62c6073041","observation_id":"0b107f68-6b02-486c-bd54-79b76793a9cc","resolution":{"observed_at":"2026-07-03T14:58:32.479035Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.21457","snapshot_observed_at":"2026-07-12T04:17:40.198357Z","title":"arXiv preprint arXiv:2505.21457 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03184","last_updated":"2026-07-03T10:42:34Z","snapshot_observed_at":"2026-08-05T15:07:18.952856Z","submitted_at":"2026-07-03T10:42:34Z","title":"BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception","version":1},"reference_index":156,"source":"arxiv_source","source_observed_at":"2026-07-12T04:17:40.198357Z"},"links":{"cited_paper":"/paper/2505.21457","citing_paper":"/paper/2607.03184"},"observation_digest":"sha256:5146da5e50f2874231618b8be0ec789b8a2451729d058cccb0b975c28a66039c","observation_id":"db53e269-69ca-4d5e-b9e2-7322ba542447","resolution":{"observed_at":"2026-07-12T04:17:40.198357Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.21457/citation-record","integrity":"/paper/2505.21457/integrity","json":"/paper/2505.21457/citation-record.json","paper":"/paper/2505.21457"},"outbound":[],"paper":{"arxiv_id":"2505.21457","last_updated":"2026-06-08T14:20:16Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T21:31:35.572708Z","submitted_at":"2025-05-27T17:29:31Z","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 15 inbound Pith citation observations for arXiv:2505.21457."}