{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2N4SP2IZD76B6Z3ZYYL7SGH2M3","short_pith_number":"pith:2N4SP2IZ","schema_version":"1.0","canonical_sha256":"d37927e9191ffc1f6779c617f918fa66c683609bce1749f6a134d58d60372bf6","source":{"kind":"arxiv","id":"2607.06856","version":1},"attestation_state":"computed","paper":{"title":"Gen4U: Unifying Video Generation and Understanding via Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adham Elarabawy, Aravindh Mahendran, Fedor Kitashov, Maks Ovsjanikov, Matthew Koichi Grimes, Michael King, Pedro Velez, Viorica P\\u{a}tr\\u{a}ucean","submitted_at":"2026-07-07T23:17:26Z","abstract_excerpt":"Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that state-of-the-art video diffusion models overcome this limitation. By systematically probing their intermediate activations using recent mutual-kNN alignment metrics, we reveal a highly structured latent space where visual representations evolve across both network depth and noise levels. We show that while moderate noise levels yield linearly separable global semantics, fine-grained details persist at lower noise levels but become spatially scattered, requir"},"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":"2607.06856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T23:17:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fc48beb4348deffe2d360de167c910410ae01e1c624a4a53d8afc019a92f3cce","abstract_canon_sha256":"6d4f03879ac4d0d6cd38efaed03647a898d1ef3591e01d2b9916a16284e3d349"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:31.554829Z","signature_b64":"E8nU81BmnkIMZnSMPxz937EVX4ARHGvAi0gocHvXbxSYbkf/QFbSe3uV5jBU5Afdyp40vwOclRbKjDnpfLzKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d37927e9191ffc1f6779c617f918fa66c683609bce1749f6a134d58d60372bf6","last_reissued_at":"2026-07-09T00:19:31.554106Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:31.554106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gen4U: Unifying Video Generation and Understanding via Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adham Elarabawy, Aravindh Mahendran, Fedor Kitashov, Maks Ovsjanikov, Matthew Koichi Grimes, Michael King, Pedro Velez, Viorica P\\u{a}tr\\u{a}ucean","submitted_at":"2026-07-07T23:17:26Z","abstract_excerpt":"Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that state-of-the-art video diffusion models overcome this limitation. By systematically probing their intermediate activations using recent mutual-kNN alignment metrics, we reveal a highly structured latent space where visual representations evolve across both network depth and noise levels. We show that while moderate noise levels yield linearly separable global semantics, fine-grained details persist at lower noise levels but become spatially scattered, requir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06856","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/2607.06856/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":"2607.06856","created_at":"2026-07-09T00:19:31.554221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06856v1","created_at":"2026-07-09T00:19:31.554221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06856","created_at":"2026-07-09T00:19:31.554221+00:00"},{"alias_kind":"pith_short_12","alias_value":"2N4SP2IZD76B","created_at":"2026-07-09T00:19:31.554221+00:00"},{"alias_kind":"pith_short_16","alias_value":"2N4SP2IZD76B6Z3Z","created_at":"2026-07-09T00:19:31.554221+00:00"},{"alias_kind":"pith_short_8","alias_value":"2N4SP2IZ","created_at":"2026-07-09T00:19:31.554221+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/2N4SP2IZD76B6Z3ZYYL7SGH2M3","json":"https://pith.science/pith/2N4SP2IZD76B6Z3ZYYL7SGH2M3.json","graph_json":"https://pith.science/api/pith-number/2N4SP2IZD76B6Z3ZYYL7SGH2M3/graph.json","events_json":"https://pith.science/api/pith-number/2N4SP2IZD76B6Z3ZYYL7SGH2M3/events.json","paper":"https://pith.science/paper/2N4SP2IZ"},"agent_actions":{"view_html":"https://pith.science/pith/2N4SP2IZD76B6Z3ZYYL7SGH2M3","download_json":"https://pith.science/pith/2N4SP2IZD76B6Z3ZYYL7SGH2M3.json","view_paper":"https://pith.science/paper/2N4SP2IZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06856&json=true","fetch_graph":"https://pith.science/api/pith-number/2N4SP2IZD76B6Z3ZYYL7SGH2M3/graph.json","fetch_events":"https://pith.science/api/pith-number/2N4SP2IZD76B6Z3ZYYL7SGH2M3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2N4SP2IZD76B6Z3ZYYL7SGH2M3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2N4SP2IZD76B6Z3ZYYL7SGH2M3/action/storage_attestation","attest_author":"https://pith.science/pith/2N4SP2IZD76B6Z3ZYYL7SGH2M3/action/author_attestation","sign_citation":"https://pith.science/pith/2N4SP2IZD76B6Z3ZYYL7SGH2M3/action/citation_signature","submit_replication":"https://pith.science/pith/2N4SP2IZD76B6Z3ZYYL7SGH2M3/action/replication_record"}},"created_at":"2026-07-09T00:19:31.554221+00:00","updated_at":"2026-07-09T00:19:31.554221+00:00"}