{"as_of":"2026-08-02T15:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ef7b5337c8d2be4bb9575ace6c01b4f662cd829c84616acde45c8bb66b7a599d","coverage":[{"denominator":74,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":74,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-23T03:16:10.826692Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-02T06:30:47.504484+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T06:59:14.917904Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.07709","snapshot_observed_at":"2026-07-31T06:59:14.917904Z","title":"Magellan: Metacognitive predictions of learning progress guide autotelic llm agents in large goal spaces.arXiv preprint arXiv:2502.07709,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24720","last_updated":"2026-07-27T17:55:03Z","snapshot_observed_at":"2026-07-31T06:59:09.334749Z","submitted_at":"2026-07-27T17:55:03Z","title":"The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-31T06:59:14.917904Z"},"links":{"cited_paper":"/paper/2502.07709","citing_paper":"/paper/2607.24720"},"observation_digest":"sha256:c8a718b36bf1a44cdc929fa800b2527af8779f7f6acc7ed292208e4363a97ede","observation_id":"9e836083-1e7c-45f3-ad44-e227f2ecd23b","resolution":{"observed_at":"2026-07-31T06:59:14.917904Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.07709/citation-record","integrity":"/paper/2502.07709/integrity","json":"/paper/2502.07709/citation-record.json","paper":"/paper/2502.07709"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T08:36:07.226215Z","title":"write newline","venue":null,"work_id":"8481976a-f196-4822-833d-e487ae5a1e81","year":null},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:7b0f733d893b3a83aa117dfa8a8dff6e12a91aa8dbf4de142ae0ed39fa1b3a0f","observation_id":"5d3a42d8-28db-4437-9119-fc8c115d9694","resolution":{"observed_at":"2026-05-23T03:17:27.892514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b0a91c69-eb25-4455-b0f3-30a3ed294e79","year":2022},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:1555bc163917e2968525129eaeec28cf072ebe332fc58ae1b884ffe3a43def1d","observation_id":"ce5e6c6d-bb83-4ba8-a1ca-d8d5d83910e2","resolution":{"observed_at":"2026-05-23T03:17:27.817594Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Grounding language to autonomously-acquired skills via goal generation","venue":null,"work_id":"eeaec73c-c607-4103-966e-0f7effda0e8b","year":2021},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:63ce044ee6153ee449c1fb2b557e601f23548dc10aa197bead9b03391448577b","observation_id":"0d7fdc57-ac2b-4787-8f83-73059f1e724e","resolution":{"observed_at":"2026-05-23T03:17:27.885288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Mirolli, M","venue":null,"work_id":"777a9c14-8c95-49bd-90fc-7eaf5fdf9274","year":2012},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:32676c6ed7ebbe7b96b4e782ab83d25424b0145f6c42a0fe69a78ab43f8bf9db","observation_id":"26853dc2-a6ca-4a1d-800b-c956049976c6","resolution":{"observed_at":"2026-05-23T03:17:27.820732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2009.203751","doi":"10.1109/tamd.2009.2037513","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"and Oudeyer, P.-Y","venue":null,"work_id":"ede950b0-efaa-4c4b-8507-d98213078638","year":2009},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:7d6c2ad2d46f75eb29a4beaf43900247431fb1fd03d426edaf68dee9df9afdd9","observation_id":"685c748f-cab1-4abe-9f21-ef1b8d19adda","resolution":{"observed_at":"2026-05-23T03:17:27.238743Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.robot.2012.05.008","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Oudeyer, P.-Y","venue":null,"work_id":"c3d1bb68-34c7-4af1-a0ee-c86b71dbda88","year":2013},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:b1f6f65fe86fab423633ec866a0fa2325ad756b286e92b6339bd04a7bec5f0bd","observation_id":"74e792c0-a524-44ae-8506-4a0633287ba8","resolution":{"observed_at":"2026-05-23T03:17:27.274505Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"a0afe251-1e23-4c6a-9aed-902977500a83","year":1954},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:b068a7d6b7f49fc19f22656f024a3f1527d31dbc013365bbd454b211162e0d69","observation_id":"ec3a91bf-41be-48e6-875c-dff75ca9a53d","resolution":{"observed_at":"2026-05-23T03:17:27.910728Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Control what you can: Intrinsically motivated task-planning agent","venue":null,"work_id":"48c14c2c-41d0-4f8b-9bbe-a79aed32805e","year":2019},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:4b27a79761ac596d13c3bd38823b6ae41e0699f3cf733349c98353a8d62265b0","observation_id":"60154f5d-7e6f-4cc1-9312-75752c1e37c4","resolution":{"observed_at":"2026-05-23T03:17:27.729804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Grounding large language models in interactive environments with online reinforcement learning","venue":null,"work_id":"bb4b58cd-27c6-48b8-a89d-b7253ad2f955","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:9de145389a7da234f0a24a4b8812497fa08e343ae4e11a3248ab590a39221164","observation_id":"5fa97a11-9360-41a2-8103-9162ea263cc6","resolution":{"observed_at":"2026-05-23T03:17:27.774970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Stein variational goal generation for adaptive exploration in multi-goal reinforcement learning","venue":null,"work_id":"91a7261d-8f12-427a-a916-8ac4f61a3d52","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:c70b9c547fd883cf20489b1c1b9c0b218be9ab66eee540856121f74652398749","observation_id":"613e9a51-cfa1-4fe2-ae8d-35733e1be166","resolution":{"observed_at":"2026-05-23T03:17:27.767461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"H., and Bengio, Y","venue":null,"work_id":"e7b0c9fa-f01a-4860-810e-9ab5773e1107","year":2019},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:630a24acc29fdd53286d92ebce215f85e3897a2b1d57cc42859215c75b3fe1d9","observation_id":"fd65f983-bb58-474b-8b34-6ea31900dc54","resolution":{"observed_at":"2026-05-23T03:17:27.807062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multi-armed bandits for intelligent tutoring systems","venue":null,"work_id":"057f618e-9a85-42cd-8a3b-8112723c3877","year":2015},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:46ed3bbedd0d2105940184e9f1f36f98bbe5140772d48aea2aca0a812128d3b5","observation_id":"d1c41a7b-5eff-4bc2-9519-f3821faf5999","resolution":{"observed_at":"2026-05-23T03:17:27.813942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"CURIOUS : intrinsically motivated modular multi-goal reinforcement learning","venue":null,"work_id":"4cf9fd51-11d8-4391-aca8-88470520074c","year":2019},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:79a65c4e2bb689c6d239063fd4bcaafa7b393994e16f845f01ade9feac10548a","observation_id":"5242d2ed-d095-477e-b885-bb37af73b9b6","resolution":{"observed_at":"2026-05-23T03:17:27.760048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.09253","last_updated":"2020-10-21T16:48:51Z","snapshot_observed_at":"2026-07-06T08:59:04.711078Z","submitted_at":"2020-02-21T12:59:57Z","title":"Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration","version":4},"cited_work":{"arxiv_id":"2002.09253","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.09253","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"F., and Oudeyer, P.-Y","venue":null,"work_id":"0fe01803-7ad0-4713-88f7-02834321e9c0","year":2002},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"cited_paper":"/paper/2002.09253","citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:f9c7847471c3133b8812deab5e737b5b71efc69bb554730468d2dd80ab9e5d37","observation_id":"440dd6a4-3af2-4281-80bb-9e83b6f654e7","resolution":{"observed_at":"2026-05-23T03:17:27.383111Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Language and culture internalization for human-like autotelic ai","venue":null,"work_id":"1756187c-b335-4da9-ad9c-12ea9ad7adcf","year":2022},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:25c49525b1559eff83e4ea39b14651f241830c2f39426c1684fd5648f495d6c3","observation_id":"bc45bdd9-1fc9-4fa4-8040-4ca132ec98d1","resolution":{"observed_at":"2026-05-23T03:17:27.726046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Autotelic agents with intrinsically motivated goal-conditioned reinforcement learning: a short survey","venue":null,"work_id":"016ecac3-6ec8-4030-9031-e9f277bf2ba1","year":2022},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:af1e3d394b1a3885992d609ca89786e328664fd3e78b26b3c2ceffbf0f226a74","observation_id":"268727f1-0a0f-4bae-91b5-08a1c7d420d4","resolution":{"observed_at":"2026-05-23T03:17:27.756148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emergent complexity and zero-shot transfer via unsupervised environment design","venue":null,"work_id":"59129a95-6033-43b3-8a50-b988ced1b755","year":2020},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:7449953b253a28595eaa69ded5e2c44815b91c4ae05aed90a3bc262af99df1d3","observation_id":"25c67a14-cceb-4f1b-a305-9382423075ac","resolution":{"observed_at":"2026-05-23T03:17:27.771147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"QL o RA : Efficient finetuning of quantized LLM s","venue":null,"work_id":"ba4fa866-806d-4288-bbef-3ebb4967b126","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:a0bf311828d5df83270e327449c9441ef1372c9611cf3939bbd5adaad385a57b","observation_id":"0f030102-8b2a-46ad-bd1d-8588e2a33c3f","resolution":{"observed_at":"2026-05-23T03:17:27.763592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Where’s the reward? a review of reinforcement learning for instructional sequencing","venue":null,"work_id":"542e4601-11b3-4e60-aee1-d5ea01bf9f96","year":2019},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:64cb0af12f504a92627eb8de783dd24bf20e0c2c7c8a1829a508740465cb0e24","observation_id":"f095ae55-fe8e-433e-8b48-74271b7b11b7","resolution":{"observed_at":"2026-05-23T03:17:27.752477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Open r1: A fully open reproduction of deepseek-r1, January 2025","venue":null,"work_id":"ee767992-2ba6-4124-89f6-82fffce755e8","year":2025},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:789e789999f9b5960a64cd829ceff3c206da561a93a4eb0c1af30d82a736f4b3","observation_id":"0aecf5db-3fd2-4c31-a3b3-5f546a48d10c","resolution":{"observed_at":"2026-05-23T03:17:27.744455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Oudeyer, P.-Y","venue":null,"work_id":"c4aac5de-fbf0-4844-8197-0081d8d7d00b","year":2016},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:1f31be06fb694e805afefd57064fde9dfe423f3d8c8b0f31473fc5547390500a","observation_id":"581ef7e1-3a90-45cd-92ba-032bb7f175ed","resolution":{"observed_at":"2026-05-23T03:17:27.843251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Intrinsically motivated goal exploration processes with automatic curriculum learning","venue":null,"work_id":"92a0dddd-cf93-4e46-833c-e76617a68a35","year":2022},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:6918f8e467d27aa88b896f5eeb07e230979c517eea621b42e9df7aa1d508aec0","observation_id":"23da7bae-95d1-485b-a759-cb9ef140e61d","resolution":{"observed_at":"2026-05-23T03:17:27.740769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Accuracy-based curriculum learning in deep reinforcement learning","venue":null,"work_id":"2d09fcae-7939-4c93-aae3-3cb3f57f42d2","year":2018},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:f781e2e8cdc765b1fd66eb93b0385e7206ee999e9557aa1299b8f8b69616ba2d","observation_id":"01f50584-9c8d-4cf4-b078-ce11f8aad955","resolution":{"observed_at":"2026-05-23T03:17:27.718451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sac-glam: Improving online rl for llm agents with soft actor-critic and hindsight relabeling","venue":null,"work_id":"440642da-3b58-4507-844b-47599e03c9e5","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:1bd346a78aad6cffd19994c3e14d35466b4306962dcd1653b0c878ae31027a0f","observation_id":"26c8b16e-6ec6-4158-adce-94a8f719eaad","resolution":{"observed_at":"2026-05-23T03:17:27.722370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Oudeyer, P.-Y","venue":null,"work_id":"733929ba-cf55-467e-9278-7f562834c7a1","year":2018},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:34a2ed6001bb30700798e84d7aae26766298738ea2b731594b4db00a8f747089","observation_id":"2a0e1580-823e-4872-8553-914a5f9a77bc","resolution":{"observed_at":"2026-05-23T03:17:27.849738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Benchmarking the spectrum of agent capabilities","venue":null,"work_id":"701f10c7-7558-40b9-91e6-e827dc3f1f3c","year":2022},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:3647a2097a6315846087cad0b0058186d273c2c8ca71b094be37e8f051c23199","observation_id":"e1146347-c105-4535-86b6-20568be1b321","resolution":{"observed_at":"2026-05-23T03:17:27.748473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.emnlp-main.507","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T22:16:36.284380Z","title":"Reasoning with language model is planning with world model","venue":null,"work_id":"59168056-5ef3-4558-8ed6-3024921b4fb3","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:7a639a87c6d061d36cac8d0fd784a09fed9a75b19dde1c06e1d2d548e778c3fb","observation_id":"69c0f90f-52ac-47c9-832d-8be7015dee00","resolution":{"observed_at":"2026-05-23T03:17:27.249071Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-07-09T10:48:37.824555+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-09T10:48:37.824555+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Automatic goal generation for reinforcement learning agents","venue":null,"work_id":"9243642b-0249-41fb-b7aa-e4de46a21452","year":2017},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:50a18c1241c3d352dfe023dbc859dd08d37ed34976dc7e01a2032a79f66ca092","observation_id":"5fdefbc4-e82f-4451-a2f8-edc15d4d075b","resolution":{"observed_at":"2026-05-23T03:17:27.871724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"J., yelong shen, Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W","venue":null,"work_id":"feb3f42f-a8e6-402c-8c3a-cb16707486d9","year":2022},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:91f2700c01db57cf0120395effab8279a1a5d7d3d66f9eba49f3cfb653b617a8","observation_id":"756e0999-9bdc-4201-8629-f787165f5b22","resolution":{"observed_at":"2026-05-23T03:17:27.733585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","venue":null,"work_id":"be67ae36-02b1-47cb-a385-752256c9d025","year":2022},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:d6fd14fb02b3a45234e4c59c948100cf87b1c3759872a1c83511772669678d86","observation_id":"11e2f3dc-997d-4fc1-89e1-60d0c0c4a859","resolution":{"observed_at":"2026-05-23T03:17:27.824256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Wordcraft: An environment for benchmarking commonsense agents","venue":null,"work_id":"58573764-9d35-48e8-9eba-78f52e6baf79","year":2020},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:f98f30b8e3d05956bd4d3607be87f0c559c611ecc9fa71fe5acb48edddce7d19","observation_id":"a4e68dec-4aaf-4029-931f-29e8f6f918ed","resolution":{"observed_at":"2026-05-23T03:17:27.796394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Replay-guided adversarial environment design","venue":null,"work_id":"396010a3-2c98-4f62-852d-6ff06622a45c","year":2021},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:53b3a37be27391b7f9dc848f8ac515cfb288539be83f44ef2b5895027c0e4e41","observation_id":"98f1ef97-06fc-487d-b21a-6ab534fe1a83","resolution":{"observed_at":"2026-05-23T03:17:27.898614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"General intelligence requires rethinking exploration","venue":null,"work_id":"a5657281-5141-4cac-985c-17e279d3bda3","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:a3d437be60f0eb564561e415f8b6ca43d8c6a53f969755d5c108f86ec698a8d3","observation_id":"706b218c-2811-4643-960d-198b0df3b7b6","resolution":{"observed_at":"2026-05-23T03:17:27.863543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The malmo platform for artificial intelligence experimentation","venue":null,"work_id":"5bed3291-bdca-44a5-8ba7-812d863336b6","year":2016},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:2b77b62b322f003a618242fb59a742f9541103be385a42e955eb64e840ac022c","observation_id":"99d69c60-ade6-40d8-a977-87468dbcbb63","resolution":{"observed_at":"2026-05-23T03:17:27.737159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"H., Houghton, B., Sampedro, R., Zhokhov, P., Baker, B., Ecoffet, A., Tang, J., Klimov, O., and Clune, J","venue":null,"work_id":"8e98062f-3808-4ed1-8529-fc090150ba90","year":2021},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:dbfd4f4e6a55c88895359cf0da656a951ec888f8b877ba941a5969ee6009b132","observation_id":"6be24126-4da6-4a97-9d86-924b05bfc58a","resolution":{"observed_at":"2026-05-23T03:17:27.778628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Oudeyer, P.-Y","venue":null,"work_id":"03c6f4e6-527e-416e-b14d-2c75a15c01f9","year":2007},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:4cac235cd7ddcae1bd65b42e0b92fcae9fe55d419014ee9a564fd9d50a63912a","observation_id":"fad2e431-b515-4514-b340-bed843b1475d","resolution":{"observed_at":"2026-05-23T03:17:27.859589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Hayden, B","venue":null,"work_id":"527e0be2-96a6-4f14-aa06-301500deffea","year":2015},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:0e42b657229aa6a59448f4908222d0735a7777da6f229cde24f6bac7abcdec8b","observation_id":"7b1f5eb7-bcf0-4a74-82ba-2fdad328be23","resolution":{"observed_at":"2026-05-23T03:17:27.785558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2022.321691","doi":"10.1109/tcds.2022.3216911","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Grimgep: Learning progress for robust goal sampling in visual deep reinforcement learning","venue":null,"work_id":"aa376981-d1f7-407b-9b4e-439259bacda9","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:52f22bb77373461a8d914319a9e7b3fc7ef2133d434f0bf069f4cd6bb243639e","observation_id":"a9a753e5-f59b-48fc-b43b-cc951a8ef754","resolution":{"observed_at":"2026-05-23T03:17:27.265150Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"P., and Barry, J","venue":null,"work_id":"83962ccd-4f11-4fda-92b8-5171aa1dd13f","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:e094f2e40f3bf65274286f5cd6c38cc87de8b8b8ae89d0733b377a967fc8cbd1","observation_id":"bd463c37-710d-40d1-a753-c1daecb823d0","resolution":{"observed_at":"2026-05-23T03:17:27.799909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Curiosity driven exploration of learned disentangled goal spaces","venue":null,"work_id":"9fc8d976-0fd0-4f35-9c02-1e3674f4e72f","year":2018},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:0c5948794e6a4f9db5855e1e99798e4f4338d1ed02e4e6b8e32694b6027a66fe","observation_id":"27e369ad-c551-48f5-af05-48174cba62ac","resolution":{"observed_at":"2026-05-23T03:17:27.810660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A., Cordrey, S","venue":null,"work_id":"de0a57a7-e1a4-475b-a2ea-cc94cc896354","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:52407308b4e701888c48c15fbced756b40a957a887ad06cd8e68ecb5ed8a05f3","observation_id":"b8006fa9-cf5d-4c85-9d53-a30fe6eafcf3","resolution":{"observed_at":"2026-05-23T03:17:27.714610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Oudeyer, P.-Y","venue":null,"work_id":"3a5334a4-027f-436e-b3e6-af15c88d8161","year":2012},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:b08cfcb18e7c0bacd81e433b1644c832f3ef7bb71e0248bd7da341fc89fa3551","observation_id":"9fc73f9c-98ec-43ed-8fc0-127229a02b17","resolution":{"observed_at":"2026-05-23T03:17:27.880685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2012.640080","doi":"10.1109/devlrn.2012.6400807","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"and Oudeyer, P.-Y","venue":null,"work_id":"b4d883c6-b05e-48cd-93c5-59dd745b87c5","year":2012},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:cb6f363989619004e6209674541af0324eace76013cfc1912968747c10241551","observation_id":"c789b727-1783-496a-bb7e-5519ff474551","resolution":{"observed_at":"2026-05-23T03:17:27.287636Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Teacher–student curriculum learning","venue":null,"work_id":"bf6094e0-b0e7-41fb-acab-37e03a3f21c8","year":2020},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:df8766ea7bb2db7f0a0b00c47c9bd15f1ed464770fa4b7787bf3aaf4d69ab2a3","observation_id":"6315b36e-3814-432d-ad3a-4992436f2bd7","resolution":{"observed_at":"2026-05-23T03:17:27.840148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Kinetix: Investigating the training of general agents through open-ended physics-based control tasks","venue":null,"work_id":"43f713bd-3177-43f7-8e66-d01ddbf2fa35","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:8d0cd6440fa760a40e3eed2906d0b27899a6f4698da423de169897dc0ed0827c","observation_id":"d441a1f1-b709-4a24-b83a-65f3e531e2cb","resolution":{"observed_at":"2026-05-23T03:17:27.867802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2013.665253","doi":"10.1109/devlrn.2013.6652535","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"and Oudeyer, P.-Y","venue":null,"work_id":"eeea6e33-c1dd-4290-bb45-7f39a8b97e6a","year":2013},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:afa96aead67a44639b9f94ce32f8907cb44cc7a825ec3f9ac4afcc4dd11caa00","observation_id":"36c465d6-a397-48bd-8295-20d85d65c55a","resolution":{"observed_at":"2026-05-23T03:17:27.280331Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2013.01006","doi":"10.3389/fpsyg.2013.01006","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"M., and Oudeyer, P.-Y","venue":null,"work_id":"6af479c1-73d8-4eaa-9770-f2ff2b92efdf","year":2014},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:ee96ba999a3526e78d67706600821e8cd420d5119b608ab890fc62bc00ae31bb","observation_id":"b7874f47-0154-418b-88f4-75284cb7dd04","resolution":{"observed_at":"2026-05-23T03:17:27.270710Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Smith, L","venue":null,"work_id":"a19954a2-7481-4470-8521-a1e8c9bb942e","year":2016},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:3606ef2f5382a807aac7d932e96a3fdf94afc8101d44c995b2af40f7fc847130","observation_id":"48c954bb-2ae5-4fb6-bdb1-5e420c94346d","resolution":{"observed_at":"2026-05-23T03:17:27.836866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2006.890271","doi":"10.1109/tevc.2006.890271","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Oudeyer, F","venue":null,"work_id":"60bc0080-4eb3-4d60-b1d8-d7a85717be41","year":2007},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:3622d06dfa2be00e0c5bf2c1346770267656c3b0ab8cd13c3ee5f215fd84d965","observation_id":"c6bbf92b-db1f-4e11-9f24-bab25772b1ff","resolution":{"observed_at":"2026-05-23T03:17:27.258855Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Maximum Entropy Gain Exploration for Long Horizon Multi -goal Reinforcement Learning","venue":null,"work_id":"203283cd-2ad5-4038-8340-656310f94c3e","year":2020},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:d67e81e97ab5552c845b18cf4c44e32487e6acb54d5698741c3ea6d763eb9382","observation_id":"d3b1fd02-bda2-42d9-994a-229cafba9ee6","resolution":{"observed_at":"2026-05-23T03:17:27.846669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"B., and Hunnius, S","venue":null,"work_id":"ff314bc1-87a8-4f75-8bf5-4afb1d1faa10","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:2613469c93f186979e3551ff51edd9692cf3a37d1aed3812a51d35a47d47d025","observation_id":"7505f61d-aaba-45cc-abf4-f9c4d2338543","resolution":{"observed_at":"2026-05-23T03:17:27.782245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"X., Mars, R","venue":null,"work_id":"9c394d6b-71f0-4cdd-91ce-f3ab904e9dce","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:d3904d12e7aeab9d60d1add9d85785756fa5397977e52d51b098d810c03aee08","observation_id":"9a047e35-ca00-42ab-8a4c-979239b4799b","resolution":{"observed_at":"2026-05-23T03:17:27.856212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"H., Dalal, M., Lin, S., Nair, A., Bahl, S., and Levine, S","venue":null,"work_id":"5f5fee83-40f1-47c5-82c0-ab434a0c40c2","year":2019},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:ea363695851e0cc81a2ec3c00c351480a934b9c5696257ad3efaa18be9851067","observation_id":"4647f63b-0674-47db-9c6b-8187007090a9","resolution":{"observed_at":"2026-05-23T03:17:27.699155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Teacher algorithms for curriculum learning of deep rl in continuously parameterized environments","venue":null,"work_id":"e407b006-4dab-4ac8-a0a8-3a3b24eddc68","year":2020},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:a4c7df852f960740e19bf7022dcb8db4b28003c9e79e28b2a8fe6d0f88c6103a","observation_id":"dffea8e9-d26e-4149-85ac-d09e7337b4a9","resolution":{"observed_at":"2026-05-23T03:17:27.902716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Automatic curriculum learning for deep rl: A short survey","venue":null,"work_id":"f29585a5-0ec1-49d7-851b-b8ad3d37e980","year":2020},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:aa2326bb4dd8ae7926fb3d34f6282d332de5e64e2561cc809d95372cf30caa5b","observation_id":"c6a003d7-0b22-483b-b349-ccdc73f49d86","resolution":{"observed_at":"2026-05-23T03:17:27.833586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"ACES : Generating a diversity of challenging programming puzzles with autotelic generative models","venue":null,"work_id":"b0da1043-6c32-43cb-9362-10f27cc363a4","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:2d4a9492b7de86d1b3951e8bb5d55b97fa92edd55139813ced569cc0a4311f34","observation_id":"63088d0e-5c3b-4118-bc5b-e07364efc5d4","resolution":{"observed_at":"2026-05-23T03:17:27.692094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.15115","doi":"10.1145/3581783.3612503","metadata_source":"pith","pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Qwen2.5 Technical Report","venue":"cs.CL","work_id":"d8432992-4980-4a81-85c7-9fa2c2b87f85","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:d7c48ddd67a76d4ce9c2aaded3d79abff5932d3aa133310545bc29ca8786050a","observation_id":"72e4b675-bb35-4329-a51c-330e60435d77","resolution":{"observed_at":"2026-05-23T03:17:27.387911Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Automated curriculum generation through setter-solver interactions","venue":null,"work_id":"59d5bd07-6b30-48a1-8913-77523d5d3333","year":2020},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:5b79d89e4f234a387ae28a9584af07ab6fdd8fbd6654888d86ba40fd1de7698e","observation_id":"e1340a93-b496-4bd1-8642-e56f8e839bc9","resolution":{"observed_at":"2026-05-23T03:17:27.828534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"dc0f91df-3402-4e0e-8d7d-522e1fb2617e","year":2020},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:a806895270f574429c3c2aa89d00431901eeb735978e5bcc1fdbf2b6f4ac1aca","observation_id":"f1d9f8ab-3bd9-4d21-a822-f416723082f8","resolution":{"observed_at":"2026-05-23T03:17:27.789107Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"TeachMyAgent : a benchmark for automatic curriculum learning in deep RL","venue":null,"work_id":"ff2c7e17-4ab8-4775-8b9c-76bf3b70bc41","year":2021},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:8853bfb898636f63e6be01b58dd8accfade15cf02525a7b0764e3f8b1b4756ad","observation_id":"a1c25382-086d-431d-9384-2c14dd96fd0e","resolution":{"observed_at":"2026-05-23T03:17:27.792646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning progress mediates the link between cognitive effort and task engagement","venue":null,"work_id":"826d4e4d-48ef-4fc2-836a-92bbc998e889","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:37b9e988020455ef8b00cd5ce829743ebf725a01a7927c1b0d06d46f2c5e6627","observation_id":"b3e764b6-2257-48ec-bf5c-2eb002f7fa45","resolution":{"observed_at":"2026-05-23T03:17:27.703513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2013.00313","doi":"10.3389/fpsyg.2013.00313","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"PowerPlay : Training an increasingly general problem solver by continually searching for the simplest still unsolvable problem","venue":null,"work_id":"81382d1a-aded-4ec8-85c6-b1a1edb93d65","year":2013},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:33a2d843ccc268332771bff578aacb07f1d289abd131b8320eeca3343ad8fa38","observation_id":"cecba0be-cab8-4095-b28f-5341e584a55e","resolution":{"observed_at":"2026-05-23T03:17:27.244779Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reflexion: language agents with verbal reinforcement learning","venue":null,"work_id":"ccf18626-477c-4ce2-93ca-6a7a7e371b4a","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:997a59bcebb2d0bdc89061155eb0668492d2121d886fd689d47f8681279966c1","observation_id":"b5b86382-caca-47b4-97d5-7e3b680a13de","resolution":{"observed_at":"2026-05-23T03:17:27.710944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.00344","last_updated":"2024-06-07T18:52:13Z","snapshot_observed_at":"2026-07-06T16:41:31.021679Z","submitted_at":"2023-11-01T07:37:27Z","title":"A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents","version":4},"cited_work":{"arxiv_id":"2311.00344","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.00344","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2311.00344 , year=","venue":null,"work_id":"f9ca5234-e146-44e0-b713-c045c3607528","year":2023},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"cited_paper":"/paper/2311.00344","citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:3ae47e06cb80166b8f067500c70c43a1de04de7dd1c6690dab2c5a28e8920f32","observation_id":"f608dab0-f2a6-40d4-ae7a-5450cccf3ecf","resolution":{"observed_at":"2026-05-23T03:17:27.378104Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2010.557883","doi":"10.1109/devlrn.2010.5578835","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"and Barto, A","venue":null,"work_id":"b56e5552-3b15-4724-9aeb-d7a082981beb","year":2010},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:dae0768f68e12771442b04d89de56f064c6aa3e7cde06124b4539810f3a4390f","observation_id":"8747a91a-8baf-42d6-a0e6-0426bc5afd63","resolution":{"observed_at":"2026-05-23T03:17:27.232465Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s41467-021-26196-w","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Humans monitor learning progress in curiosity-driven exploration","venue":null,"work_id":"d18c9817-dfee-4c8e-ad8e-4163541781da","year":2021},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:36eb934a92ca37bba83e797e7a2d77dbb180c97cb96d0615696f3571a904d3ba","observation_id":"9fd130dd-4ff3-44ad-96e3-b9e63b6f4e56","resolution":{"observed_at":"2026-05-23T03:17:27.253218Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Hinton, G","venue":null,"work_id":"e06ab619-55ae-429e-8eca-b30effa258a3","year":2008},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:68d8f0f402a894df37843c4b9aa5e5459ec767a3a9b1c81b9a48297e0e58d141","observation_id":"b2429376-abfd-4943-b766-de6a0a5a15a4","resolution":{"observed_at":"2026-05-23T03:17:27.853105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Voyager: An open-ended embodied agent with large language models","venue":null,"work_id":"1f822e8c-a9d0-4607-b017-1d3bbb1464fe","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:b9bc14f1c58a9794748622986040597e9af725f5a94badc34e8a22c0027062ab","observation_id":"10a07e7e-a67e-4c16-bb34-5b3dde2b44dd","resolution":{"observed_at":"2026-05-23T03:17:27.876254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"V., Kulkarni, T., Ionescu, C., Hansen, S., and Mnih, V","venue":null,"work_id":"57cbcce6-112e-473c-b685-dd6036460b5b","year":2019},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:3f77c48f22d8f9ac23717b7787da10b8abe090a3e081d73247ce2ea93c2bdd83","observation_id":"451afe7a-6cfe-47d0-a861-9e1f253f4d18","resolution":{"observed_at":"2026-05-23T03:17:27.906996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Entropy-regularized token-level policy optimization for large language models, 2024 a","venue":null,"work_id":"2d5ac10f-8930-4f3c-8edf-14544ec4fa67","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:1efc86c0d0f110c756f10c837d06c30a68810907a5822db0a51513aa9eeffb38","observation_id":"4bdfdd5c-00be-4b28-9f71-db21f991f0c6","resolution":{"observed_at":"2026-05-23T03:17:27.688178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reinforcing LLM agents via policy optimization with action decomposition, 2024 b","venue":null,"work_id":"31af5979-1f4d-4312-b0e1-ad5f7cebc051","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:2b561e822b883dcc93797f9f08fa7aa4e64d854901bac2c4b72abe7727bd1c98","observation_id":"ce693f63-ea16-47b4-a7ba-0de829c77020","resolution":{"observed_at":"2026-05-23T03:17:27.695420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"React: Synergizing reasoning and acting in language models","venue":null,"work_id":"9f9d56f7-a172-4131-8770-9602f26258ff","year":2022},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:4e8d84aac15e59c41e1c95668ff61e5deb72b3585a7664a48eeeee9bfca315b2","observation_id":"f2cca5fc-8535-4100-8a58-19b6858c9847","resolution":{"observed_at":"2026-05-23T03:17:27.684610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"OMNI : Open-endedness via models of human notions of interestingness","venue":null,"work_id":"ebeffab8-e373-46af-a715-dcf01fe9de81","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:0407fc56adb385ae4241a10c32e04e89cc42d49d7f8bebe71354b553ccece87e","observation_id":"c99d130b-7c8a-4b34-a95a-7221069aa8e5","resolution":{"observed_at":"2026-05-23T03:17:27.803805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A r CH er: Training language model agents via hierarchical multi-turn RL","venue":null,"work_id":"7d991337-7877-4bc6-8b62-7a973bb1160e","year":2024},"citing_paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces","version":3},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-05-23T03:16:10.826692Z"},"links":{"citing_paper":"/paper/2502.07709"},"observation_digest":"sha256:aad9a636ce0d2a54e6f001f882f4eaee5f4bc011f284ceab76fc9b41dfcc8dac","observation_id":"295f9ac5-5ce4-4133-aa8a-3a78a6ee18fd","resolution":{"observed_at":"2026-05-23T03:17:27.707297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.07709","last_updated":"2025-06-17T09:23:02Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T20:34:53.567141Z","submitted_at":"2025-02-11T17:08:00Z","title":"MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces"},"reference_resolution":{"displayed":74,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":3,"verified_exact":13,"verified_fuzzy":57},"total_outbound_references":74},"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":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"thesis":"As of 2 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 1 inbound Pith citation observation for arXiv:2502.07709."}