{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PZBKTLETVROZY26WVZBLBTQXJ7","short_pith_number":"pith:PZBKTLET","canonical_record":{"source":{"id":"2501.01426","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:45Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"45a43dfd953ed3a3af93ff42ce371f2d028ba5c5b7f7341b7f7eefdbb8399099","abstract_canon_sha256":"2891400d88cdaae331ec7a0ef7321082c81f1a314cd15377b3a130b6cd98099c"},"schema_version":"1.0"},"canonical_sha256":"7e42a9ac93ac5d9c6bd6ae42b0ce174fd794704969dd523abf97c848c53e1da1","source":{"kind":"arxiv","id":"2501.01426","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01426","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01426v2","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01426","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"PZBKTLETVROZ","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"PZBKTLETVROZY26W","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"PZBKTLET","created_at":"2026-07-05T11:21:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PZBKTLETVROZY26WVZBLBTQXJ7","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01426","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:45Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"45a43dfd953ed3a3af93ff42ce371f2d028ba5c5b7f7341b7f7eefdbb8399099","abstract_canon_sha256":"2891400d88cdaae331ec7a0ef7321082c81f1a314cd15377b3a130b6cd98099c"},"schema_version":"1.0"},"canonical_sha256":"7e42a9ac93ac5d9c6bd6ae42b0ce174fd794704969dd523abf97c848c53e1da1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:40.050860Z","signature_b64":"n+RvVzSPp9SwmVrENW4nph2WXEYv8ybH+PtuxiUFqUSf57E4bwx7pvpyeGCUy77kLjObRBO56mNauyVsA8DkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e42a9ac93ac5d9c6bd6ae42b0ce174fd794704969dd523abf97c848c53e1da1","last_reissued_at":"2026-07-05T11:21:40.050303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:40.050303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01426","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1VJ9UlD2ds9h22Foyuka0Qel37MZ0W4eM+y5XfVutrwSQCnmKw3OK0a36EisKwCGjc+bf3l+zmzkZ+EdtnepCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:12:12.505667Z"},"content_sha256":"acb24141f73cbf86f4e663e8040149f540d83ab17e85554da4c103d4c9f491ca","schema_version":"1.0","event_id":"sha256:acb24141f73cbf86f4e663e8040149f540d83ab17e85554da4c103d4c9f491ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PZBKTLETVROZY26WVZBLBTQXJ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unifying Specialized Visual Encoders for Video Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Honglu Zhou, Jihoon Chung, Juan Carlos Niebles, Max Gonzalez Saez-Diez, Olga Russakovsky, Tyler Zhu","submitted_at":"2025-01-02T18:59:45Z","abstract_excerpt":"The recent advent of Large Language Models (LLMs) has ushered sophisticated reasoning capabilities into the realm of video through Video Large Language Models (VideoLLMs). However, VideoLLMs currently rely on a single vision encoder for all of their visual processing, which limits the amount and type of visual information that can be conveyed to the LLM. Our method, MERV, Multi-Encoder Representation of Videos, instead leverages multiple frozen visual encoders to create a unified representation of a video, providing the VideoLLM with a comprehensive set of specialized visual knowledge. Spatio-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01426","kind":"arxiv","version":2},"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/2501.01426/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":"2026-07-05T11:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HJ2mRETi5kK4fITewb5hEeS/CiJV8YRjUMzRKLxHWigteuNVnotNhtL7qRTMCeWp+xQbmZQfj5iFHukRZzKnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:12:12.506157Z"},"content_sha256":"5ed3253e31b2da5e67b29554648d851d59fed4b8e5ab641cf9f632a49b2231f8","schema_version":"1.0","event_id":"sha256:5ed3253e31b2da5e67b29554648d851d59fed4b8e5ab641cf9f632a49b2231f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZBKTLETVROZY26WVZBLBTQXJ7/bundle.json","state_url":"https://pith.science/pith/PZBKTLETVROZY26WVZBLBTQXJ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZBKTLETVROZY26WVZBLBTQXJ7/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":"2026-08-05T21:12:12Z","links":{"resolver":"https://pith.science/pith/PZBKTLETVROZY26WVZBLBTQXJ7","bundle":"https://pith.science/pith/PZBKTLETVROZY26WVZBLBTQXJ7/bundle.json","state":"https://pith.science/pith/PZBKTLETVROZY26WVZBLBTQXJ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZBKTLETVROZY26WVZBLBTQXJ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PZBKTLETVROZY26WVZBLBTQXJ7","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":"2891400d88cdaae331ec7a0ef7321082c81f1a314cd15377b3a130b6cd98099c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:45Z","title_canon_sha256":"45a43dfd953ed3a3af93ff42ce371f2d028ba5c5b7f7341b7f7eefdbb8399099"},"schema_version":"1.0","source":{"id":"2501.01426","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01426","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01426v2","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01426","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"PZBKTLETVROZ","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"PZBKTLETVROZY26W","created_at":"2026-07-05T11:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"PZBKTLET","created_at":"2026-07-05T11:21:40Z"}],"graph_snapshots":[{"event_id":"sha256:5ed3253e31b2da5e67b29554648d851d59fed4b8e5ab641cf9f632a49b2231f8","target":"graph","created_at":"2026-07-05T11:21:40Z","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/2501.01426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent advent of Large Language Models (LLMs) has ushered sophisticated reasoning capabilities into the realm of video through Video Large Language Models (VideoLLMs). However, VideoLLMs currently rely on a single vision encoder for all of their visual processing, which limits the amount and type of visual information that can be conveyed to the LLM. Our method, MERV, Multi-Encoder Representation of Videos, instead leverages multiple frozen visual encoders to create a unified representation of a video, providing the VideoLLM with a comprehensive set of specialized visual knowledge. Spatio-","authors_text":"Honglu Zhou, Jihoon Chung, Juan Carlos Niebles, Max Gonzalez Saez-Diez, Olga Russakovsky, Tyler Zhu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:45Z","title":"Unifying Specialized Visual Encoders for Video Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01426","kind":"arxiv","version":2},"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:acb24141f73cbf86f4e663e8040149f540d83ab17e85554da4c103d4c9f491ca","target":"record","created_at":"2026-07-05T11:21:40Z","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":"2891400d88cdaae331ec7a0ef7321082c81f1a314cd15377b3a130b6cd98099c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:45Z","title_canon_sha256":"45a43dfd953ed3a3af93ff42ce371f2d028ba5c5b7f7341b7f7eefdbb8399099"},"schema_version":"1.0","source":{"id":"2501.01426","kind":"arxiv","version":2}},"canonical_sha256":"7e42a9ac93ac5d9c6bd6ae42b0ce174fd794704969dd523abf97c848c53e1da1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e42a9ac93ac5d9c6bd6ae42b0ce174fd794704969dd523abf97c848c53e1da1","first_computed_at":"2026-07-05T11:21:40.050303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:40.050303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n+RvVzSPp9SwmVrENW4nph2WXEYv8ybH+PtuxiUFqUSf57E4bwx7pvpyeGCUy77kLjObRBO56mNauyVsA8DkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:40.050860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01426","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acb24141f73cbf86f4e663e8040149f540d83ab17e85554da4c103d4c9f491ca","sha256:5ed3253e31b2da5e67b29554648d851d59fed4b8e5ab641cf9f632a49b2231f8"],"state_sha256":"911e5bbfc2f08d9c9eb4340d0bef536943a8da45702bfc3a209dd4c9ef7191a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+pl121ag1485ACC78M+rGEXhUIUvsWGA6TI0D9a3K8zkBulkS9ZLcCkpUukRaOXC++dpIaEJ0gWt+uOZXtwlCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:12:12.510049Z","bundle_sha256":"98900525d00423601f0bdf863cbcc7d5170ddb2ffc2a45933785450b64f090f6"}}