{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WSWSFIL3PWRKV7LT7CFFZNFAYW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a5905b24c4e2218cf1e1ed35f581c36e863d935b7e1b197cab33bdc896d1b150","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T23:10:04Z","title_canon_sha256":"65f8a46fe3a9c8de7d95549e2bf65b5fc800aea31088f93438fcb4bdf24ebb1d"},"schema_version":"1.0","source":{"id":"2605.15466","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15466","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15466v1","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15466","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"pith_short_12","alias_value":"WSWSFIL3PWRK","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"pith_short_16","alias_value":"WSWSFIL3PWRKV7LT","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"pith_short_8","alias_value":"WSWSFIL3","created_at":"2026-05-20T00:01:00Z"}],"graph_snapshots":[{"event_id":"sha256:381d8cf0b34df3be7a7b5a72d6ed147d39bde07fba2ee640499249b7fe3df240","target":"graph","created_at":"2026-05-20T00:01:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Motion-centric masking in self-supervised video models enables better learning of causal physical dynamics by focusing on interactions rather than static patches."}],"snapshot_sha256":"eb3cc5b199f81656c0618002dbdd3df67fb05cdc726dc5c7cd1a295953f24e08"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d4576378eac17aeb1491e00efd95af7b4d716cb6c2e88f048a7cf1ca5910117c"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.15466/integrity.json","findings":[],"snapshot_sha256":"d7d9139d469b48e2826300510ae414636852894f389560e4a3d2147f66bfe59b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Santosh Kumar Paidi","cross_cats":[],"headline":"Motion-centric masking in self-supervised video models enables better learning of causal physical dynamics by focusing on interactions rather than static patches.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T23:10:04Z","title":"Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction"},"references":{"count":35,"internal_anchors":3,"resolved_work":35,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Video generation models as world simulators.OpenAI Blog, 2024","work_id":"4f22b49c-b820-4a3f-9f6f-5273805df4d1","year":2024},{"cited_arxiv_id":"2506.09985","doi":"","is_internal_anchor":true,"ref_index":2,"title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","work_id":"a9c28401-f16a-4933-89f0-788e2f94e52b","year":2025},{"cited_arxiv_id":"1910.01442","doi":"","is_internal_anchor":true,"ref_index":3,"title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","work_id":"595fdbf7-89d5-4593-8f57-24e8b469a43c","year":1910},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"something something","work_id":"a40b0c21-8c68-4e98-9adb-1f90135432f9","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Phyre: A new benchmark for physical reasoning","work_id":"d2c80b4d-2fe5-40a1-9b4f-0efe0581edc2","year":2019}],"snapshot_sha256":"cfa31b16a6c8aeb1d985d1a0aa47a20a879ccad37daafb1b8ac1cb962ee4b18f"},"source":{"id":"2605.15466","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T14:47:01.208588Z","id":"82815f3e-9255-4357-a695-6b5a70fbe473","model_set":{"reader":"grok-4.3"},"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","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.","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).","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."}},"verdict_id":"82815f3e-9255-4357-a695-6b5a70fbe473"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:50611cd659f0084a4cdc5950495f47fe60af49c73ba8f5f94c3968bde9cb0653","target":"record","created_at":"2026-05-20T00:01:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a5905b24c4e2218cf1e1ed35f581c36e863d935b7e1b197cab33bdc896d1b150","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T23:10:04Z","title_canon_sha256":"65f8a46fe3a9c8de7d95549e2bf65b5fc800aea31088f93438fcb4bdf24ebb1d"},"schema_version":"1.0","source":{"id":"2605.15466","kind":"arxiv","version":1}},"canonical_sha256":"b4ad22a17b7da2aafd73f88a5cb4a0c59698f0873f327fa9796da66835ee9852","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4ad22a17b7da2aafd73f88a5cb4a0c59698f0873f327fa9796da66835ee9852","first_computed_at":"2026-05-20T00:01:00.062944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:00.062944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kbDg3/57mmhw/7BJYJnRavj7h/GvtbpdwB0w2646LAXLrjs0dxt1xpVdO/hTpbVh2Xx7PQ+7CCBrDxaFUSG6AQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:00.063673Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15466","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50611cd659f0084a4cdc5950495f47fe60af49c73ba8f5f94c3968bde9cb0653","sha256:381d8cf0b34df3be7a7b5a72d6ed147d39bde07fba2ee640499249b7fe3df240"],"state_sha256":"f21385a595320d62fa4acc826dba0fc0165b28f24f89b6d3f52b585af9fb7fd8"}