{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y6XLWCIDJ54OQDORNUISOOHJQU","short_pith_number":"pith:Y6XLWCID","schema_version":"1.0","canonical_sha256":"c7aebb09034f78e80dd16d112738e985367b14a6ff7012fc579b2ea6711a2d32","source":{"kind":"arxiv","id":"2605.17165","version":1},"attestation_state":"computed","paper":{"title":"Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Santosh Premi","submitted_at":"2026-05-16T21:30:51Z","abstract_excerpt":"Joint-Embedding Predictive Architectures (JEPA) are a promising framework for self-supervised video representation learning, yet the behavior of auxiliary objectives in small-scale Video-JEPA training is not well characterized. We report a small-scale empirical study of 18 auxiliary objective variants for Video-JEPA across two pretraining regimes: single-dataset (UCF-101) and mixed-dataset (UCF-101 + Something-Something V2 + ImageNet-100). We evaluate frozen representations on three complementary benchmarks: Diving-48 (fine-grained motion), SomethingSomething V2 (temporal reasoning), and Image"},"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":"2605.17165","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T21:30:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"64d5ecc122607dc4e5b8a82edc8b8c9b63855164692dd77cf126dc4e46fe8e65","abstract_canon_sha256":"26f5d204f02b3181302f737dec6fe5eeb764871b1f1c537f62f9357c64157103"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:42.855464Z","signature_b64":"jpHuLLqGALsaHtE0mOGW22ajmwVEQEJFmD/t/wMrK14XLsU8I+j73Xh91PIv0WhokzuP5jDtcQ79V4vlmrIXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7aebb09034f78e80dd16d112738e985367b14a6ff7012fc579b2ea6711a2d32","last_reissued_at":"2026-05-20T00:03:42.854618Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:42.854618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Santosh Premi","submitted_at":"2026-05-16T21:30:51Z","abstract_excerpt":"Joint-Embedding Predictive Architectures (JEPA) are a promising framework for self-supervised video representation learning, yet the behavior of auxiliary objectives in small-scale Video-JEPA training is not well characterized. We report a small-scale empirical study of 18 auxiliary objective variants for Video-JEPA across two pretraining regimes: single-dataset (UCF-101) and mixed-dataset (UCF-101 + Something-Something V2 + ImageNet-100). We evaluate frozen representations on three complementary benchmarks: Diving-48 (fine-grained motion), SomethingSomething V2 (temporal reasoning), and Image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17165","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/2605.17165/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.756460Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.984050Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"151a90eaecd7a3eee950af5e53cf431abd7652a6795cb9b379095017303bc22f"},"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":"2605.17165","created_at":"2026-05-20T00:03:42.854747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17165v1","created_at":"2026-05-20T00:03:42.854747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17165","created_at":"2026-05-20T00:03:42.854747+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6XLWCIDJ54O","created_at":"2026-05-20T00:03:42.854747+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6XLWCIDJ54OQDOR","created_at":"2026-05-20T00:03:42.854747+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6XLWCID","created_at":"2026-05-20T00:03:42.854747+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/Y6XLWCIDJ54OQDORNUISOOHJQU","json":"https://pith.science/pith/Y6XLWCIDJ54OQDORNUISOOHJQU.json","graph_json":"https://pith.science/api/pith-number/Y6XLWCIDJ54OQDORNUISOOHJQU/graph.json","events_json":"https://pith.science/api/pith-number/Y6XLWCIDJ54OQDORNUISOOHJQU/events.json","paper":"https://pith.science/paper/Y6XLWCID"},"agent_actions":{"view_html":"https://pith.science/pith/Y6XLWCIDJ54OQDORNUISOOHJQU","download_json":"https://pith.science/pith/Y6XLWCIDJ54OQDORNUISOOHJQU.json","view_paper":"https://pith.science/paper/Y6XLWCID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17165&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6XLWCIDJ54OQDORNUISOOHJQU/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6XLWCIDJ54OQDORNUISOOHJQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6XLWCIDJ54OQDORNUISOOHJQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6XLWCIDJ54OQDORNUISOOHJQU/action/storage_attestation","attest_author":"https://pith.science/pith/Y6XLWCIDJ54OQDORNUISOOHJQU/action/author_attestation","sign_citation":"https://pith.science/pith/Y6XLWCIDJ54OQDORNUISOOHJQU/action/citation_signature","submit_replication":"https://pith.science/pith/Y6XLWCIDJ54OQDORNUISOOHJQU/action/replication_record"}},"created_at":"2026-05-20T00:03:42.854747+00:00","updated_at":"2026-05-20T00:03:42.854747+00:00"}