{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OTILUYV66P7VG7HRS7B7ULDIFZ","short_pith_number":"pith:OTILUYV6","schema_version":"1.0","canonical_sha256":"74d0ba62bef3ff537cf197c3fa2c682e4f2b7e11fc3bfc6eac5aff00281ab982","source":{"kind":"arxiv","id":"2606.22918","version":1},"attestation_state":"computed","paper":{"title":"Each Judge Its Own Yardstick: Discovering Per-VLM Taxonomies for Physical Video Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.CV","authors_text":"Jiankang Deng, Jifei Song, Shaogang Gong, Yu Cao, Zhensong Zhang, Ziquan Liu","submitted_at":"2026-06-22T06:58:39Z","abstract_excerpt":"Maintaining physical consistency in video generators and world models increasingly relies on vision-language models (VLMs) as automated judges that provide reward signals, ranking decisions, and data-filtering criteria. Yet VLMs differ substantially in training data and architecture, encoding physical phenomena through distinct internal representations. A single global evaluation schema therefore gives every VLM the same axes of competence, regardless of what each can actually perceive. We propose JudgeFit, an iterative refinement procedure that discovers a per-VLM evaluation taxonomy. An init"},"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":"2606.22918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T06:58:39Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"bd32f64616a1956c9b0c6f713e98e91050b291d965b4d6c76dbc86e630ede45f","abstract_canon_sha256":"4ce58dfbb21a33cb9b1eae4581a463c55da4d15e74a3d22f44793c545ffd278d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:04.159799Z","signature_b64":"SEtLpdBEFfC41CaLaQX0Mty677W++AzDeA7fDlPSTv25jZJXXU5vS+zlwivkAkhf2+jsin/Auw9C4FlTSkUYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74d0ba62bef3ff537cf197c3fa2c682e4f2b7e11fc3bfc6eac5aff00281ab982","last_reissued_at":"2026-06-23T03:14:04.159408Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:04.159408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Each Judge Its Own Yardstick: Discovering Per-VLM Taxonomies for Physical Video Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.CV","authors_text":"Jiankang Deng, Jifei Song, Shaogang Gong, Yu Cao, Zhensong Zhang, Ziquan Liu","submitted_at":"2026-06-22T06:58:39Z","abstract_excerpt":"Maintaining physical consistency in video generators and world models increasingly relies on vision-language models (VLMs) as automated judges that provide reward signals, ranking decisions, and data-filtering criteria. Yet VLMs differ substantially in training data and architecture, encoding physical phenomena through distinct internal representations. A single global evaluation schema therefore gives every VLM the same axes of competence, regardless of what each can actually perceive. We propose JudgeFit, an iterative refinement procedure that discovers a per-VLM evaluation taxonomy. An init"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22918","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/2606.22918/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":"2606.22918","created_at":"2026-06-23T03:14:04.159464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22918v1","created_at":"2026-06-23T03:14:04.159464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22918","created_at":"2026-06-23T03:14:04.159464+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTILUYV66P7V","created_at":"2026-06-23T03:14:04.159464+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTILUYV66P7VG7HR","created_at":"2026-06-23T03:14:04.159464+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTILUYV6","created_at":"2026-06-23T03:14:04.159464+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/OTILUYV66P7VG7HRS7B7ULDIFZ","json":"https://pith.science/pith/OTILUYV66P7VG7HRS7B7ULDIFZ.json","graph_json":"https://pith.science/api/pith-number/OTILUYV66P7VG7HRS7B7ULDIFZ/graph.json","events_json":"https://pith.science/api/pith-number/OTILUYV66P7VG7HRS7B7ULDIFZ/events.json","paper":"https://pith.science/paper/OTILUYV6"},"agent_actions":{"view_html":"https://pith.science/pith/OTILUYV66P7VG7HRS7B7ULDIFZ","download_json":"https://pith.science/pith/OTILUYV66P7VG7HRS7B7ULDIFZ.json","view_paper":"https://pith.science/paper/OTILUYV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22918&json=true","fetch_graph":"https://pith.science/api/pith-number/OTILUYV66P7VG7HRS7B7ULDIFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OTILUYV66P7VG7HRS7B7ULDIFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTILUYV66P7VG7HRS7B7ULDIFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTILUYV66P7VG7HRS7B7ULDIFZ/action/storage_attestation","attest_author":"https://pith.science/pith/OTILUYV66P7VG7HRS7B7ULDIFZ/action/author_attestation","sign_citation":"https://pith.science/pith/OTILUYV66P7VG7HRS7B7ULDIFZ/action/citation_signature","submit_replication":"https://pith.science/pith/OTILUYV66P7VG7HRS7B7ULDIFZ/action/replication_record"}},"created_at":"2026-06-23T03:14:04.159464+00:00","updated_at":"2026-06-23T03:14:04.159464+00:00"}