{"as_of":"2026-08-18T09:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5773b7ca2e26da2d57ac80d7b5c1e42a0bb4a519e0c363048c1e6038eaf0ba0b","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:49:09.412095Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2504.17282/citation-record","integrity":"/paper/2504.17282/integrity","json":"/paper/2504.17282/citation-record.json","paper":"/paper/2504.17282"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:11.800151Z","title":"Developing a computer use model","venue":null,"work_id":"dfdd4bc7-4ae4-4b42-814b-4f276c719031","year":2024},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:08.994763Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:c1cbd1bb9d4a861db64ca8c1b694b00d5cb0be4dc352911f5a5fb4d3e77204ed","observation_id":"2cd06ae8-6364-4505-887a-d360e806da26","resolution":{"observed_at":"2026-08-16T10:49:11.854451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:11.273561Z","title":"Uniter: Universal image-text representation learning","venue":null,"work_id":"50adaab8-8819-432e-b791-01d6c107fe00","year":2020},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.005944Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:58bb6de1c976d03be905ad3bc04b11cd6bce459d1f6d70441937851d4b1ac88b","observation_id":"6f7bf0b8-78d1-4f4d-a04a-bd3aa1cf70c7","resolution":{"observed_at":"2026-08-16T10:49:11.751490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.10935","last_updated":"2024-02-23T04:36:51Z","snapshot_observed_at":"2026-08-18T02:03:58.046358Z","submitted_at":"2024-01-17T08:10:35Z","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.10935","snapshot_observed_at":"2026-08-16T10:49:09.012769Z","title":"Seeclick: Harnessing gui grounding for advanced visual gui agents, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.012769Z"},"links":{"cited_paper":"/paper/2401.10935","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:a65c7793edb2d9a47cff7bcb000f326ad8169403d9e8b43bf2c0d10892eb9649","observation_id":"2a27898f-37d1-4714-8564-c90a9f5edb2c","resolution":{"observed_at":"2026-08-16T10:49:09.012769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:11.231922Z","title":"The theory of affordances","venue":null,"work_id":"d8e9c4f3-909b-4175-b592-2a60ed88b755","year":1977},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.022420Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:d587cde72aa5b7c1902969009f7e5e26c86ab2ad69b9a9af15702e25661310a5","observation_id":"02e34939-b0ca-4e1d-8a13-2aeae1e66b1e","resolution":{"observed_at":"2026-08-16T10:49:11.244301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05973","last_updated":"2023-11-02T06:53:37Z","snapshot_observed_at":"2026-08-05T01:03:23.456778Z","submitted_at":"2023-07-12T07:40:48Z","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05973","snapshot_observed_at":"2026-08-16T10:49:09.033394Z","title":"Voxposer: Composable 3d value maps for robotic manipulation with language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.033394Z"},"links":{"cited_paper":"/paper/2307.05973","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:2c64aeb1ba1ebcfb6dc800bc5b1092fcbecdd46e265a5f3ff9343e84ef1c28a9","observation_id":"d54c096e-6be0-420d-bc3d-090016d61994","resolution":{"observed_at":"2026-08-16T10:49:09.033394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08137","last_updated":"2022-11-11T13:45:44Z","snapshot_observed_at":"2026-08-16T17:20:49.223058Z","submitted_at":"2022-02-16T15:23:46Z","title":"A data-driven approach for learning to control computers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08137","snapshot_observed_at":"2026-08-16T10:49:09.040202Z","title":"A data-driven approach for learning to control computers, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.040202Z"},"links":{"cited_paper":"/paper/2202.08137","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:88558152c574e2979cb9cd8ac53f39563848df3a6c176c6229e33e91d0b98b38","observation_id":"0b0bc8bb-8f61-49ac-9690-25ecb4844780","resolution":{"observed_at":"2026-08-16T10:49:09.040202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.053057Z","title":"What can i do here? a theory of affordances in reinforcement learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.053057Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:531d372c247421d01b05cf108558a01596fd625c350152d7281085fccc806531","observation_id":"ac4f2dda-a3c9-4579-8f20-8f3991945ab2","resolution":{"observed_at":"2026-08-16T10:49:09.053057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.17491","last_updated":"2023-11-16T20:15:14Z","snapshot_observed_at":"2026-08-14T05:01:21.886306Z","submitted_at":"2023-03-30T16:01:52Z","title":"Language Models can Solve Computer Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.17491","snapshot_observed_at":"2026-08-16T10:49:09.065536Z","title":"Language models can solve computer tasks, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.065536Z"},"links":{"cited_paper":"/paper/2303.17491","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:4b6c893b15385c0f4d87281bcd366eebfee9eb9631ac2923ea2e0162a2246306","observation_id":"93f1210f-e483-456e-91ec-ca18818408e3","resolution":{"observed_at":"2026-08-16T10:49:09.065536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10341","last_updated":"2025-07-25T18:09:11Z","snapshot_observed_at":"2026-08-16T13:34:19.561465Z","submitted_at":"2024-07-14T21:41:29Z","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10341","snapshot_observed_at":"2026-08-16T10:49:09.072600Z","title":"Lee, Annie Xie, Kuan Fang, Karl Pertsch, and Chelsea Finn","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.072600Z"},"links":{"cited_paper":"/paper/2407.10341","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:bb66c504c8339fcd11051ce0f5b0316503c52c3de7f03c40d6610d42fec3ec5e","observation_id":"8aeff68b-927b-4002-8241-9c9a208b97f0","resolution":{"observed_at":"2026-08-16T10:49:09.072600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.079557Z","title":"Code as policies: Language model programs for embodied control, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.079557Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:a10aa83d81089db838ba69d2f25c0b7bf8bbe7e74b3256c2805e98e9308a1cb0","observation_id":"c38090ec-d281-474a-b7ab-3fb578c7307c","resolution":{"observed_at":"2026-08-16T10:49:09.079557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.08802","last_updated":"2018-02-24T05:32:47Z","snapshot_observed_at":"2026-08-14T19:42:39.161822Z","submitted_at":"2018-02-24T05:32:47Z","title":"Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.08802","snapshot_observed_at":"2026-08-16T10:49:09.090104Z","title":"Reinforcement learning on web interfaces using workflow-guided exploration, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.090104Z"},"links":{"cited_paper":"/paper/1802.08802","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:62b60a776334b0c44628bbc21a2bd46ca15cca2b5a45c90b028e2cd7989dab4a","observation_id":"c2c3298b-861a-4172-9203-1f7b4946a3cb","resolution":{"observed_at":"2026-08-16T10:49:09.090104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03174","last_updated":"2024-09-04T01:18:13Z","snapshot_observed_at":"2026-08-16T14:12:33.532936Z","submitted_at":"2024-03-05T18:08:45Z","title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03174","snapshot_observed_at":"2026-08-16T10:49:09.104480Z","title":"Moka: Open-world robotic manipulation through mark-based visual prompting, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.104480Z"},"links":{"cited_paper":"/paper/2403.03174","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:2eaacf064ebc6d8d749c01df80a93a0e7e6ad13a0c03236a73f110216292f3e1","observation_id":"76c6d6d4-50be-4e9c-be2b-248f553a2e39","resolution":{"observed_at":"2026-08-16T10:49:09.104480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.12931","last_updated":"2024-04-30T21:35:53Z","snapshot_observed_at":"2026-08-02T10:40:03.816188Z","submitted_at":"2023-10-19T17:31:01Z","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.12931","snapshot_observed_at":"2026-08-16T10:49:09.110228Z","title":"Eureka: Human-level reward design via coding large language models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.110228Z"},"links":{"cited_paper":"/paper/2310.12931","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:930d873559198226dd8863240bee7f86d2e8f3ea422a7d09019e2aaad4b55fd9","observation_id":"244130b4-9150-468f-80ee-e2c4d87c3c55","resolution":{"observed_at":"2026-08-16T10:49:09.110228Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.5602","last_updated":"2013-12-19T16:00:08Z","snapshot_observed_at":"2026-08-17T17:19:33.060917Z","submitted_at":"2013-12-19T16:00:08Z","title":"Playing Atari with Deep Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.5602","snapshot_observed_at":"2026-08-16T10:49:09.117000Z","title":"Playing atari with deep reinforcement learning, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.117000Z"},"links":{"cited_paper":"/paper/1312.5602","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:ffef7ca5492a046bb065cf771d8cf72ca7a285a20639b78fc30b8243376cce36","observation_id":"e0f1b129-f584-4f5f-8f7a-431082ad5192","resolution":{"observed_at":"2026-08-16T10:49:09.117000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.127020Z","title":"Computer-using agent: Introducing a universal interface for ai to interact with the digital world","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.127020Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:c83645b601094181a2fb1bd940995954ffade58096ac9d5616378ad6a0923121","observation_id":"927e2feb-6dda-4ca5-9f95-4f61a0104888","resolution":{"observed_at":"2026-08-16T10:49:09.127020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:11.074795Z","title":"Gpt-4 technical report, 2023","venue":null,"work_id":"033f0d27-41a3-45eb-8fb4-fa6a618b03f3","year":2023},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.141272Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:238eea25cd600cf180e689b18fed767a18a7641bf86dea1e6b4b2dc561789a6b","observation_id":"70e6037b-9729-4242-a02d-29c23b7a073b","resolution":{"observed_at":"2026-08-16T10:49:11.087355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:10.995797Z","title":"Affordancellm: Grounding affordance from vision language models, 2024","venue":null,"work_id":"e609091f-c9da-446d-9f85-d434470b32df","year":2024},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.154639Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:670f55b84838ad775c191af8cbb2382aaf373df46ac163509583e7f048fc7d04","observation_id":"7ae1b10f-8704-467d-942d-e04a9a5eb038","resolution":{"observed_at":"2026-08-16T10:49:11.026745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.173123Z","title":"Learning transferable visual models from natural language supervision, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.173123Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:c1bb2f3105af6f564559110c437cb24bc4247dccfdf57971deacc0e0f235ec3c","observation_id":"636e48e2-81fa-4972-8eae-72e28b6ee7cf","resolution":{"observed_at":"2026-08-16T10:49:09.173123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-08-14T05:02:11.716316Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-16T10:49:09.189567Z","title":"Sentence-bert: Sentence embeddings using siamese bert-networks, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.189567Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:184f523c20af2dbb92896332a1016fc86412d16882f4e819afb5949109f2a153","observation_id":"2f639c45-05cd-40df-9ae5-09f8000c94d8","resolution":{"observed_at":"2026-08-16T10:49:09.189567Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:10.872902Z","title":"Efficient reductions for imitation learning","venue":null,"work_id":"b9e62bc4-2a90-431e-8036-34d2a5bb6890","year":2010},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.203945Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:eb25c7ba2d73ccd8cdf8b5e7fb9ca78a429a265916905d361c3206f9e65dd115","observation_id":"55d918b1-dbfd-4aa4-a20c-7c6b5381cfa5","resolution":{"observed_at":"2026-08-16T10:49:10.889238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.05952","last_updated":"2016-02-25T17:55:31Z","snapshot_observed_at":"2026-08-15T17:33:32.559096Z","submitted_at":"2015-11-18T20:54:44Z","title":"Prioritized Experience Replay","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.05952","snapshot_observed_at":"2026-08-16T10:49:09.218377Z","title":"Prioritized experience replay, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.218377Z"},"links":{"cited_paper":"/paper/1511.05952","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:d598de73512abeb9f1f95bba090973053ba1c68570fbbd758a76fd709141a630","observation_id":"7649d9fb-99fe-4be6-b8f9-260201ec37fe","resolution":{"observed_at":"2026-08-16T10:49:09.218377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.242278Z","title":"From pixels to ui actions: Learning to follow instructions via graphical user interfaces","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.242278Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:2409f0e1c88b6433dc506cdebffdc3376f95482ebd2d616ed0ccc8ad61f28811","observation_id":"3bda557d-3ef6-4bf2-9113-3c65213a7d44","resolution":{"observed_at":"2026-08-16T10:49:09.242278Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.253142Z","title":"World of bits: An open-domain platform for web-based agents","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.253142Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:823773fc47de97c59112aa5979b325e48600c4f19de23c19fffad21bc56db961","observation_id":"0337c792-d69f-4c7a-ad60-b1bb88b04025","resolution":{"observed_at":"2026-08-16T10:49:09.253142Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.263138Z","title":"Mastering the game of go with deep neural networks and tree search","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.263138Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:338116a150e47fea769338f220710368854adda08e47609f255eb3b6e13d10ff","observation_id":"843d2154-1953-40cb-b97b-fbdbb8a4819b","resolution":{"observed_at":"2026-08-16T10:49:09.263138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.01815","last_updated":"2017-12-05T18:45:38Z","snapshot_observed_at":"2026-08-14T20:06:37.819179Z","submitted_at":"2017-12-05T18:45:38Z","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.01815","snapshot_observed_at":"2026-08-16T10:49:09.276370Z","title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.276370Z"},"links":{"cited_paper":"/paper/1712.01815","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:1c1b9ffdb6225a8a111dff51fd4f9cf2491e3792a7a2b904576d1481abc20732","observation_id":"c341beff-48b7-401c-ac7b-9b53b03d654a","resolution":{"observed_at":"2026-08-16T10:49:09.276370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.292550Z","title":"Reinforcement learning: An introduction","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.292550Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:5e52046dee78153b6731f1a78231b528383ab58011d4691f632f7f8c58deaf33","observation_id":"3f8a2b6c-921e-4c96-9543-535c95787a39","resolution":{"observed_at":"2026-08-16T10:49:09.292550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1509.06461","last_updated":"2015-12-08T21:19:16Z","snapshot_observed_at":"2026-08-14T22:31:25.126692Z","submitted_at":"2015-09-22T04:40:22Z","title":"Deep Reinforcement Learning with Double Q-learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1509.06461","snapshot_observed_at":"2026-08-16T10:49:09.317937Z","title":"Deep reinforcement learning with double q-learning, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.317937Z"},"links":{"cited_paper":"/paper/1509.06461","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:e100246a9d39c769e0b8b1f8d22f4591f0383d57d4db0380d0cdc81d08ba22a4","observation_id":"0269a0a8-39b7-4cc9-b2a9-e5b814bd3c66","resolution":{"observed_at":"2026-08-16T10:49:09.317937Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:10.666483Z","title":"Code as reward: Empowering reinforcement learning with vlms, 2024","venue":null,"work_id":"7d7a30b4-e1a7-42d9-bd03-a8398fa74a5e","year":2024},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.330476Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:b1ad7057de06ca1f53fde4d512ff72cdbe25957b12f2b0321f16a68b62680f88","observation_id":"bbc6079a-c8da-4494-b936-bd504146a7a9","resolution":{"observed_at":"2026-08-16T10:49:10.707685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.350950Z","title":"Voyager: An open-ended embodied agent with large language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.350950Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:37757e0ea42d626eaedd18a695f9af1a0f733cd368fa46e2bff778c57e07603b","observation_id":"0d3968bb-e2a2-4383-a8de-5dec01bb44d8","resolution":{"observed_at":"2026-08-16T10:49:09.350950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.358128Z","title":"Q-learning","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.358128Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:f014138020d7ae6bd04464c8ed088b2e0a9797e3e0509fa14f4c351350ea2900","observation_id":"29bf9a64-c46f-4ffc-ad5c-7868bc37ebd0","resolution":{"observed_at":"2026-08-16T10:49:09.358128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11903","last_updated":"2023-01-10T23:07:57Z","snapshot_observed_at":"2026-08-13T07:04:41.220509Z","submitted_at":"2022-01-28T02:33:07Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11903","snapshot_observed_at":"2026-08-16T10:49:09.375710Z","title":"Chain-of-thought prompting elicits reasoning in large language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.375710Z"},"links":{"cited_paper":"/paper/2201.11903","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:e1976881decc310a6961bd180a8cff5378513ef0bca416927fa9862b7f8fac1e","observation_id":"ae19d999-e9d8-4ad3-b2fe-c1cb23d6bfa2","resolution":{"observed_at":"2026-08-16T10:49:09.375710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08588","last_updated":"2024-10-20T17:57:03Z","snapshot_observed_at":"2026-08-16T14:52:34.833074Z","submitted_at":"2023-10-12T17:59:58Z","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08588","snapshot_observed_at":"2026-08-16T10:49:09.382500Z","title":"Octopus: Embodied vision-language programmer from environmental feedback, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.382500Z"},"links":{"cited_paper":"/paper/2310.08588","citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:ea7c0f7d19249338be909df810b96d70357e53b8c4a0f51e74f73280ec9b0e30","observation_id":"1f2c93d4-a092-419f-9074-90bd50c5bf78","resolution":{"observed_at":"2026-08-16T10:49:09.382500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.388753Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.388753Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:bd5eb680218271bf10ec5fdf4ddeb099e01be0693ff112ac1f096a12cecb5b06","observation_id":"e81a7c74-74ae-4831-8df6-5ea45148d072","resolution":{"observed_at":"2026-08-16T10:49:09.388753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.395648Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.395648Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:3cf2b72e1241bc9ca1ff36f970253f116bb73c610af491edef6d9607dff437dd","observation_id":"5acb3e07-ba17-4243-809a-9bd97665ec30","resolution":{"observed_at":"2026-08-16T10:49:09.395648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.404655Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.404655Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:e2bdae6e8f1dff065492ddaf39bc11d649c6fac777f8884a038cf062cd6c68cb","observation_id":"e728414d-76de-4ab0-b0e9-9bcca7b7dcbc","resolution":{"observed_at":"2026-08-16T10:49:09.404655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:49:09.412095Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-16T10:49:09.412095Z"},"links":{"citing_paper":"/paper/2504.17282"},"observation_digest":"sha256:da0569d36d8bc8500ec75f18286bcd996e2fc1abdcd649b5e7ffdc7be42f26cb","observation_id":"bdde56ee-7ede-4388-b57e-b29695062cfe","resolution":{"observed_at":"2026-08-16T10:49:09.412095Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.17282","last_updated":"2025-04-24T06:20:08Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-16T10:41:46.493224Z","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":0,"verified_fuzzy":7},"total_outbound_references":36},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2504.17282."}