{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BC6556JHE5DBB756YJL6WQ4PXB","short_pith_number":"pith:BC6556JH","schema_version":"1.0","canonical_sha256":"08bddef927274610ffbec257eb438fb867b999a849c9040b823dfa084c38c396","source":{"kind":"arxiv","id":"2607.00310","version":1},"attestation_state":"computed","paper":{"title":"RetailSMV: Exocentric vs. Egocentric Adaptation of Foundation Video World Models in Retail","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Amirreza Rouhi, Anoop M. Namboodiri, Parikshit Sakurikar, Rajat Aggarwal, Sashi P. Reddi","submitted_at":"2026-07-01T01:23:34Z","abstract_excerpt":"Foundation video diffusion models are increasingly viewed as world simulators for embodied agents, yet their pretraining on internet-scale generic video leaves them poorly aligned with real-world deployment domains. We study parameter-efficient adaptation of a pretrained foundation video world model to retail scenes: when synchronized egocentric and exocentric video of the same activity are available, which viewpoint of training data produces the strongest adapted model?\n  We introduce RetailSMV (Retail Synchronized Multi-View), a corpus of 32,105 captioned retail clips from five supermarkets "},"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":"2607.00310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T01:23:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5aa2e18e9c00dfd777c0aae687095920ea574d2435907e4122f0325579e2a7d6","abstract_canon_sha256":"e05e9cc8fef1253e8234e974b729943d7edbef10aa5614a870e597b58588942a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:44.096061Z","signature_b64":"fP8LYZQrGZZGCkgxXFzi7Oz9LmUWXvdCfqx730el68i17NNGkZWgb+rwZSUGoYYrSfPw+x/G4tQDkSPKioOSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08bddef927274610ffbec257eb438fb867b999a849c9040b823dfa084c38c396","last_reissued_at":"2026-07-02T00:18:44.095471Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:44.095471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RetailSMV: Exocentric vs. Egocentric Adaptation of Foundation Video World Models in Retail","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Amirreza Rouhi, Anoop M. Namboodiri, Parikshit Sakurikar, Rajat Aggarwal, Sashi P. Reddi","submitted_at":"2026-07-01T01:23:34Z","abstract_excerpt":"Foundation video diffusion models are increasingly viewed as world simulators for embodied agents, yet their pretraining on internet-scale generic video leaves them poorly aligned with real-world deployment domains. We study parameter-efficient adaptation of a pretrained foundation video world model to retail scenes: when synchronized egocentric and exocentric video of the same activity are available, which viewpoint of training data produces the strongest adapted model?\n  We introduce RetailSMV (Retail Synchronized Multi-View), a corpus of 32,105 captioned retail clips from five supermarkets "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00310","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/2607.00310/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":"2607.00310","created_at":"2026-07-02T00:18:44.095544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00310v1","created_at":"2026-07-02T00:18:44.095544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00310","created_at":"2026-07-02T00:18:44.095544+00:00"},{"alias_kind":"pith_short_12","alias_value":"BC6556JHE5DB","created_at":"2026-07-02T00:18:44.095544+00:00"},{"alias_kind":"pith_short_16","alias_value":"BC6556JHE5DBB756","created_at":"2026-07-02T00:18:44.095544+00:00"},{"alias_kind":"pith_short_8","alias_value":"BC6556JH","created_at":"2026-07-02T00:18:44.095544+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/BC6556JHE5DBB756YJL6WQ4PXB","json":"https://pith.science/pith/BC6556JHE5DBB756YJL6WQ4PXB.json","graph_json":"https://pith.science/api/pith-number/BC6556JHE5DBB756YJL6WQ4PXB/graph.json","events_json":"https://pith.science/api/pith-number/BC6556JHE5DBB756YJL6WQ4PXB/events.json","paper":"https://pith.science/paper/BC6556JH"},"agent_actions":{"view_html":"https://pith.science/pith/BC6556JHE5DBB756YJL6WQ4PXB","download_json":"https://pith.science/pith/BC6556JHE5DBB756YJL6WQ4PXB.json","view_paper":"https://pith.science/paper/BC6556JH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00310&json=true","fetch_graph":"https://pith.science/api/pith-number/BC6556JHE5DBB756YJL6WQ4PXB/graph.json","fetch_events":"https://pith.science/api/pith-number/BC6556JHE5DBB756YJL6WQ4PXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BC6556JHE5DBB756YJL6WQ4PXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BC6556JHE5DBB756YJL6WQ4PXB/action/storage_attestation","attest_author":"https://pith.science/pith/BC6556JHE5DBB756YJL6WQ4PXB/action/author_attestation","sign_citation":"https://pith.science/pith/BC6556JHE5DBB756YJL6WQ4PXB/action/citation_signature","submit_replication":"https://pith.science/pith/BC6556JHE5DBB756YJL6WQ4PXB/action/replication_record"}},"created_at":"2026-07-02T00:18:44.095544+00:00","updated_at":"2026-07-02T00:18:44.095544+00:00"}