{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GY3VKSLRG3BB766HV4AIKSXJGF","short_pith_number":"pith:GY3VKSLR","schema_version":"1.0","canonical_sha256":"363755497136c21ffbc7af00854ae9316a14a16b0279a825930715f93681e880","source":{"kind":"arxiv","id":"2606.07687","version":1},"attestation_state":"computed","paper":{"title":"What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hanseul Kim, Jaejin Lee, Jeongjae Park, Jewon Yeom, Sungmok Jung, Taesup Kim","submitted_at":"2026-06-05T04:43:02Z","abstract_excerpt":"Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces. We study this question through a unified probe-based evaluation across diverse encoder families, including image-only self-supervision, video pretraining with and without latent prediction, reconstruction-based autoencoders, diffusion models, and shortcut-forcing dynamics models. Using a common inverse-dynamics probing objective, we find that action-relevant structure is driven primarily by temporal vide"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.07687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T04:43:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"151a5756e338d00852169839fc436623e6afe3011dcf2f1ee37c85b7418fcf6e","abstract_canon_sha256":"35c9bf63d9d23496b242a341c19d1c60c197a02c6fbfee72306b9fb9ddb3508f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:46.852570Z","signature_b64":"B0SN74P+5DpF0oLsDCbnU0DOWAm/L5pCVURcfTJ8C7i6dili2iBKbhznmWwvoqgb8fpKHSSITwrmwAX8xTvMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"363755497136c21ffbc7af00854ae9316a14a16b0279a825930715f93681e880","last_reissued_at":"2026-06-09T00:04:46.852207Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:46.852207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hanseul Kim, Jaejin Lee, Jeongjae Park, Jewon Yeom, Sungmok Jung, Taesup Kim","submitted_at":"2026-06-05T04:43:02Z","abstract_excerpt":"Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces. We study this question through a unified probe-based evaluation across diverse encoder families, including image-only self-supervision, video pretraining with and without latent prediction, reconstruction-based autoencoders, diffusion models, and shortcut-forcing dynamics models. Using a common inverse-dynamics probing objective, we find that action-relevant structure is driven primarily by temporal vide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07687","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.07687/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.07687","created_at":"2026-06-09T00:04:46.852270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07687v1","created_at":"2026-06-09T00:04:46.852270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07687","created_at":"2026-06-09T00:04:46.852270+00:00"},{"alias_kind":"pith_short_12","alias_value":"GY3VKSLRG3BB","created_at":"2026-06-09T00:04:46.852270+00:00"},{"alias_kind":"pith_short_16","alias_value":"GY3VKSLRG3BB766H","created_at":"2026-06-09T00:04:46.852270+00:00"},{"alias_kind":"pith_short_8","alias_value":"GY3VKSLR","created_at":"2026-06-09T00:04:46.852270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GY3VKSLRG3BB766HV4AIKSXJGF","json":"https://pith.science/pith/GY3VKSLRG3BB766HV4AIKSXJGF.json","graph_json":"https://pith.science/api/pith-number/GY3VKSLRG3BB766HV4AIKSXJGF/graph.json","events_json":"https://pith.science/api/pith-number/GY3VKSLRG3BB766HV4AIKSXJGF/events.json","paper":"https://pith.science/paper/GY3VKSLR"},"agent_actions":{"view_html":"https://pith.science/pith/GY3VKSLRG3BB766HV4AIKSXJGF","download_json":"https://pith.science/pith/GY3VKSLRG3BB766HV4AIKSXJGF.json","view_paper":"https://pith.science/paper/GY3VKSLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07687&json=true","fetch_graph":"https://pith.science/api/pith-number/GY3VKSLRG3BB766HV4AIKSXJGF/graph.json","fetch_events":"https://pith.science/api/pith-number/GY3VKSLRG3BB766HV4AIKSXJGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GY3VKSLRG3BB766HV4AIKSXJGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GY3VKSLRG3BB766HV4AIKSXJGF/action/storage_attestation","attest_author":"https://pith.science/pith/GY3VKSLRG3BB766HV4AIKSXJGF/action/author_attestation","sign_citation":"https://pith.science/pith/GY3VKSLRG3BB766HV4AIKSXJGF/action/citation_signature","submit_replication":"https://pith.science/pith/GY3VKSLRG3BB766HV4AIKSXJGF/action/replication_record"}},"created_at":"2026-06-09T00:04:46.852270+00:00","updated_at":"2026-06-09T00:04:46.852270+00:00"}