{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JD52WJBDHEAOFMSFFNCWLEWRCF","short_pith_number":"pith:JD52WJBD","canonical_record":{"source":{"id":"2503.05977","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-07T23:17:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80489093f3143662e76060de067eee3b26508092c929e593039240e1afe5ccb1","abstract_canon_sha256":"8538a7f85a8457fdcff42d5314b4b0ea2a8322aad9f9502b58c6c2ee8872adbb"},"schema_version":"1.0"},"canonical_sha256":"48fbab24233900e2b2452b456592d1116b33945c07b59d0b700a214af0a92230","source":{"kind":"arxiv","id":"2503.05977","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05977","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05977v1","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05977","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"pith_short_12","alias_value":"JD52WJBDHEAO","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"pith_short_16","alias_value":"JD52WJBDHEAOFMSF","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"pith_short_8","alias_value":"JD52WJBD","created_at":"2026-07-05T10:26:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JD52WJBDHEAOFMSFFNCWLEWRCF","target":"record","payload":{"canonical_record":{"source":{"id":"2503.05977","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-07T23:17:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80489093f3143662e76060de067eee3b26508092c929e593039240e1afe5ccb1","abstract_canon_sha256":"8538a7f85a8457fdcff42d5314b4b0ea2a8322aad9f9502b58c6c2ee8872adbb"},"schema_version":"1.0"},"canonical_sha256":"48fbab24233900e2b2452b456592d1116b33945c07b59d0b700a214af0a92230","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:50.470173Z","signature_b64":"0QuxnUQ5tYfksq/Kco0MzZd74iTJPJRsJn7XSTE5p3dz7k8/WkBCNYhXTCSMWuVTroMXQ/7mbzHtdtPRa2gwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48fbab24233900e2b2452b456592d1116b33945c07b59d0b700a214af0a92230","last_reissued_at":"2026-07-05T10:26:50.469666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:50.469666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.05977","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:26:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vD+iTDVer5l07V4mQfpFV0obXwWVknieXWCHLpAtmMXi39dpfyZt1OagJT/7DJ+e6AtDf3f7i9v4Tx21ckAxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:30:50.455670Z"},"content_sha256":"58b73f2178a3f9b5c00c24006f2e0787882435ac4fac7a99916b5824ad00beb6","schema_version":"1.0","event_id":"sha256:58b73f2178a3f9b5c00c24006f2e0787882435ac4fac7a99916b5824ad00beb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JD52WJBDHEAOFMSFFNCWLEWRCF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Your Video Language Model a Reliable Judge?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ming Liu, Wensheng Zhang","submitted_at":"2025-03-07T23:17:59Z","abstract_excerpt":"As video language models (VLMs) gain more applications in various scenarios, the need for robust and scalable evaluation of their performance becomes increasingly critical. The traditional human expert-based evaluation of VLMs has limitations in consistency and scalability, which sparked interest in automatic methods such as employing VLMs to evaluate VLMs. However, the reliability of VLMs as judges remains underexplored. Existing methods often rely on a single VLM as the evaluator. However, this approach can be unreliable or biased because such a model may lack the ability to fully understand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05977","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/2503.05977/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:26:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86dUAItTxB+BQO6JRha9mU9uP1Z9xbXEQZPJKyRQm52GzMCwY54tPPz2WFWhfyVK6nJyPwhQbfLNgDLpTZ1iBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:30:50.456039Z"},"content_sha256":"2e11e6c6931c036eea846aa138483bfe940f2986ff87a32353cebdb9a73fa78c","schema_version":"1.0","event_id":"sha256:2e11e6c6931c036eea846aa138483bfe940f2986ff87a32353cebdb9a73fa78c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JD52WJBDHEAOFMSFFNCWLEWRCF/bundle.json","state_url":"https://pith.science/pith/JD52WJBDHEAOFMSFFNCWLEWRCF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JD52WJBDHEAOFMSFFNCWLEWRCF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T22:30:50Z","links":{"resolver":"https://pith.science/pith/JD52WJBDHEAOFMSFFNCWLEWRCF","bundle":"https://pith.science/pith/JD52WJBDHEAOFMSFFNCWLEWRCF/bundle.json","state":"https://pith.science/pith/JD52WJBDHEAOFMSFFNCWLEWRCF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JD52WJBDHEAOFMSFFNCWLEWRCF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JD52WJBDHEAOFMSFFNCWLEWRCF","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":"8538a7f85a8457fdcff42d5314b4b0ea2a8322aad9f9502b58c6c2ee8872adbb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-07T23:17:59Z","title_canon_sha256":"80489093f3143662e76060de067eee3b26508092c929e593039240e1afe5ccb1"},"schema_version":"1.0","source":{"id":"2503.05977","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05977","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05977v1","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05977","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"pith_short_12","alias_value":"JD52WJBDHEAO","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"pith_short_16","alias_value":"JD52WJBDHEAOFMSF","created_at":"2026-07-05T10:26:50Z"},{"alias_kind":"pith_short_8","alias_value":"JD52WJBD","created_at":"2026-07-05T10:26:50Z"}],"graph_snapshots":[{"event_id":"sha256:2e11e6c6931c036eea846aa138483bfe940f2986ff87a32353cebdb9a73fa78c","target":"graph","created_at":"2026-07-05T10:26:50Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.05977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As video language models (VLMs) gain more applications in various scenarios, the need for robust and scalable evaluation of their performance becomes increasingly critical. The traditional human expert-based evaluation of VLMs has limitations in consistency and scalability, which sparked interest in automatic methods such as employing VLMs to evaluate VLMs. However, the reliability of VLMs as judges remains underexplored. Existing methods often rely on a single VLM as the evaluator. However, this approach can be unreliable or biased because such a model may lack the ability to fully understand","authors_text":"Ming Liu, Wensheng Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-07T23:17:59Z","title":"Is Your Video Language Model a Reliable Judge?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05977","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:58b73f2178a3f9b5c00c24006f2e0787882435ac4fac7a99916b5824ad00beb6","target":"record","created_at":"2026-07-05T10:26:50Z","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":"8538a7f85a8457fdcff42d5314b4b0ea2a8322aad9f9502b58c6c2ee8872adbb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-07T23:17:59Z","title_canon_sha256":"80489093f3143662e76060de067eee3b26508092c929e593039240e1afe5ccb1"},"schema_version":"1.0","source":{"id":"2503.05977","kind":"arxiv","version":1}},"canonical_sha256":"48fbab24233900e2b2452b456592d1116b33945c07b59d0b700a214af0a92230","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48fbab24233900e2b2452b456592d1116b33945c07b59d0b700a214af0a92230","first_computed_at":"2026-07-05T10:26:50.469666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:50.469666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0QuxnUQ5tYfksq/Kco0MzZd74iTJPJRsJn7XSTE5p3dz7k8/WkBCNYhXTCSMWuVTroMXQ/7mbzHtdtPRa2gwDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:50.470173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.05977","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58b73f2178a3f9b5c00c24006f2e0787882435ac4fac7a99916b5824ad00beb6","sha256:2e11e6c6931c036eea846aa138483bfe940f2986ff87a32353cebdb9a73fa78c"],"state_sha256":"49967b818d43e53238c32dec1f77494de0ada013cc88fec7ff613c598fa8ab61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n7s5TqZ9Kq1DOOo11UVO58GZRz5HOrv2rFmIg2oAD3HDrxS18f/fG+68wGnGJotzg7vc8o/eVYDW64wzXjixCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:30:50.458388Z","bundle_sha256":"d04b2a4d25c19640b6e3d94fd56ce7f8a8fdbc51fc4a2414160bcef91a306803"}}