{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WSWSFIL3PWRKV7LT7CFFZNFAYW","short_pith_number":"pith:WSWSFIL3","schema_version":"1.0","canonical_sha256":"b4ad22a17b7da2aafd73f88a5cb4a0c59698f0873f327fa9796da66835ee9852","source":{"kind":"arxiv","id":"2605.15466","version":1},"attestation_state":"computed","paper":{"title":"Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Motion-centric masking in self-supervised video models enables better learning of causal physical dynamics by focusing on interactions rather than static patches.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Santosh Kumar Paidi","submitted_at":"2026-05-14T23:10:04Z","abstract_excerpt":"Learning predictive world models from unlabelled video is a foundational challenge in artificial intelligence. While Joint Embedding Predictive Architectures (JEPA) have set new benchmarks in semantic classification, they often remain physics-blind, failing to capture the causal dynamics necessary for downstream reasoning. We hypothesize that this stems from standard patch-based masking strategies, which prioritize visual texture over rare but informative kinematic events. We propose Interaction-Aware JEPA (IA-JEPA), which utilizes a self-supervised motion-centric masking strategy to prioritiz"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T23:10:04Z","cross_cats_sorted":[],"title_canon_sha256":"65f8a46fe3a9c8de7d95549e2bf65b5fc800aea31088f93438fcb4bdf24ebb1d","abstract_canon_sha256":"a5905b24c4e2218cf1e1ed35f581c36e863d935b7e1b197cab33bdc896d1b150"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:00.063673Z","signature_b64":"kbDg3/57mmhw/7BJYJnRavj7h/GvtbpdwB0w2646LAXLrjs0dxt1xpVdO/hTpbVh2Xx7PQ+7CCBrDxaFUSG6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4ad22a17b7da2aafd73f88a5cb4a0c59698f0873f327fa9796da66835ee9852","last_reissued_at":"2026-05-20T00:01:00.062944Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:00.062944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Motion-centric masking in self-supervised video models enables better learning of causal physical dynamics by focusing on interactions rather than static patches.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Santosh Kumar Paidi","submitted_at":"2026-05-14T23:10:04Z","abstract_excerpt":"Learning predictive world models from unlabelled video is a foundational challenge in artificial intelligence. While Joint Embedding Predictive Architectures (JEPA) have set new benchmarks in semantic classification, they often remain physics-blind, failing to capture the causal dynamics necessary for downstream reasoning. We hypothesize that this stems from standard patch-based masking strategies, which prioritize visual texture over rare but informative kinematic events. We propose Interaction-Aware JEPA (IA-JEPA), which utilizes a self-supervised motion-centric masking strategy to prioritiz"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"IA-JEPA achieves 14.26% accuracy on causal reasoning tasks on CLEVRER, a significant lead over the 3.22% achieved by standard patch-masked baselines, while inducing a higher-entropy latent space that linearizes physical energy (R²=0.43).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that self-supervised motion-centric masking targeting collisions and momentum transfers will force reconstruction of latent trajectories rather than static background features, as stated in the hypothesis section of the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"IA-JEPA applies interaction-aware masking to JEPA, raising causal reasoning accuracy on CLEVRER from 3.22% to 14.26% while producing a higher-entropy latent space that better aligns with physical energy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Motion-centric masking in self-supervised video models enables better learning of causal physical dynamics by focusing on interactions rather than static patches.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"eb3cc5b199f81656c0618002dbdd3df67fb05cdc726dc5c7cd1a295953f24e08"},"source":{"id":"2605.15466","kind":"arxiv","version":1},"verdict":{"id":"82815f3e-9255-4357-a695-6b5a70fbe473","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T14:47:01.208588Z","strongest_claim":"IA-JEPA achieves 14.26% accuracy on causal reasoning tasks on CLEVRER, a significant lead over the 3.22% achieved by standard patch-masked baselines, while inducing a higher-entropy latent space that linearizes physical energy (R²=0.43).","one_line_summary":"IA-JEPA applies interaction-aware masking to JEPA, raising causal reasoning accuracy on CLEVRER from 3.22% to 14.26% while producing a higher-entropy latent space that better aligns with physical energy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that self-supervised motion-centric masking targeting collisions and momentum transfers will force reconstruction of latent trajectories rather than static background features, as stated in the hypothesis section of the abstract.","pith_extraction_headline":"Motion-centric masking in self-supervised video models enables better learning of causal physical dynamics by focusing on interactions rather than static patches."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15466/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T15:22:27.318179Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T15:01:17.597392Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:00:38.852451Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.092944Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.413784Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.666693Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d7d9139d469b48e2826300510ae414636852894f389560e4a3d2147f66bfe59b"},"references":{"count":35,"sample":[{"doi":"","year":2024,"title":"Video generation models as world simulators.OpenAI Blog, 2024","work_id":"4f22b49c-b820-4a3f-9f6f-5273805df4d1","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","work_id":"a9c28401-f16a-4933-89f0-788e2f94e52b","ref_index":2,"cited_arxiv_id":"2506.09985","is_internal_anchor":true},{"doi":"","year":1910,"title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","work_id":"595fdbf7-89d5-4593-8f57-24e8b469a43c","ref_index":3,"cited_arxiv_id":"1910.01442","is_internal_anchor":true},{"doi":"","year":2017,"title":"something something","work_id":"a40b0c21-8c68-4e98-9adb-1f90135432f9","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Phyre: A new benchmark for physical reasoning","work_id":"d2c80b4d-2fe5-40a1-9b4f-0efe0581edc2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":35,"snapshot_sha256":"cfa31b16a6c8aeb1d985d1a0aa47a20a879ccad37daafb1b8ac1cb962ee4b18f","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d4576378eac17aeb1491e00efd95af7b4d716cb6c2e88f048a7cf1ca5910117c"},"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":"2605.15466","created_at":"2026-05-20T00:01:00.063059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15466v1","created_at":"2026-05-20T00:01:00.063059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15466","created_at":"2026-05-20T00:01:00.063059+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSWSFIL3PWRK","created_at":"2026-05-20T00:01:00.063059+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSWSFIL3PWRKV7LT","created_at":"2026-05-20T00:01:00.063059+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSWSFIL3","created_at":"2026-05-20T00:01:00.063059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WSWSFIL3PWRKV7LT7CFFZNFAYW","json":"https://pith.science/pith/WSWSFIL3PWRKV7LT7CFFZNFAYW.json","graph_json":"https://pith.science/api/pith-number/WSWSFIL3PWRKV7LT7CFFZNFAYW/graph.json","events_json":"https://pith.science/api/pith-number/WSWSFIL3PWRKV7LT7CFFZNFAYW/events.json","paper":"https://pith.science/paper/WSWSFIL3"},"agent_actions":{"view_html":"https://pith.science/pith/WSWSFIL3PWRKV7LT7CFFZNFAYW","download_json":"https://pith.science/pith/WSWSFIL3PWRKV7LT7CFFZNFAYW.json","view_paper":"https://pith.science/paper/WSWSFIL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15466&json=true","fetch_graph":"https://pith.science/api/pith-number/WSWSFIL3PWRKV7LT7CFFZNFAYW/graph.json","fetch_events":"https://pith.science/api/pith-number/WSWSFIL3PWRKV7LT7CFFZNFAYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSWSFIL3PWRKV7LT7CFFZNFAYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSWSFIL3PWRKV7LT7CFFZNFAYW/action/storage_attestation","attest_author":"https://pith.science/pith/WSWSFIL3PWRKV7LT7CFFZNFAYW/action/author_attestation","sign_citation":"https://pith.science/pith/WSWSFIL3PWRKV7LT7CFFZNFAYW/action/citation_signature","submit_replication":"https://pith.science/pith/WSWSFIL3PWRKV7LT7CFFZNFAYW/action/replication_record"}},"created_at":"2026-05-20T00:01:00.063059+00:00","updated_at":"2026-05-20T00:01:00.063059+00:00"}