{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L63647DF4H46DEIFTB3D3YTENV","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":"a3ec82c48c5a0b0f7d54a32e9c5464da5200cc0f13e65edee9aeeb29cca67569","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:02:37Z","title_canon_sha256":"d9bf422e114ab5345e75623993ad34a2acff47c05eaa3f81eb624a1c5139e607"},"schema_version":"1.0","source":{"id":"2503.19794","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19794","created_at":"2026-07-05T10:39:01Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19794v1","created_at":"2026-07-05T10:39:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19794","created_at":"2026-07-05T10:39:01Z"},{"alias_kind":"pith_short_12","alias_value":"L63647DF4H46","created_at":"2026-07-05T10:39:01Z"},{"alias_kind":"pith_short_16","alias_value":"L63647DF4H46DEIF","created_at":"2026-07-05T10:39:01Z"},{"alias_kind":"pith_short_8","alias_value":"L63647DF","created_at":"2026-07-05T10:39:01Z"}],"graph_snapshots":[{"event_id":"sha256:dea42f1fa5a14b4459720a8660eb4293e65001349b4601a3c29a05cc62f046cf","target":"graph","created_at":"2026-07-05T10:39:01Z","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/2503.19794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained video large language models (Video LLMs) exhibit remarkable reasoning capabilities, yet adapting these models to new tasks involving additional modalities or data types (e.g., audio or 3D information) remains challenging. In this paper, we present PAVE, a flexible framework for adapting pre-trained Video LLMs to downstream tasks with side-channel signals, such as audio, 3D cues, or multi-view videos. PAVE introduces lightweight adapters, referred to as \"patches,\" which add a small number of parameters and operations to a base model without modifying its architecture or pre-trained ","authors_text":"Khoi Duc Nguyen, Yin Li, Yiquan Li, Yiwu Zhong, Zhuoming Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:02:37Z","title":"PAVE: Patching and Adapting Video Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19794","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":"sha256:6dc44ae4c21a83d751bd35d96133dc7c2e84d5e02f3c3c5ba99142c10836e6f2","target":"record","created_at":"2026-07-05T10:39:01Z","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":"a3ec82c48c5a0b0f7d54a32e9c5464da5200cc0f13e65edee9aeeb29cca67569","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:02:37Z","title_canon_sha256":"d9bf422e114ab5345e75623993ad34a2acff47c05eaa3f81eb624a1c5139e607"},"schema_version":"1.0","source":{"id":"2503.19794","kind":"arxiv","version":1}},"canonical_sha256":"5fb7ee7c65e1f9e1910598763de2646d40c239dd25ea549f01cb7c124bb1c1e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fb7ee7c65e1f9e1910598763de2646d40c239dd25ea549f01cb7c124bb1c1e2","first_computed_at":"2026-07-05T10:39:01.870942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:01.870942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uo09ViLoBJ6K7UmVlggNmOQwpm4lrMaqSdgDspOTOcZvY3LkvEfrjJNHk01mVvTNu6RMX84FCr0OZ04lF9GbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:01.871466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19794","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6dc44ae4c21a83d751bd35d96133dc7c2e84d5e02f3c3c5ba99142c10836e6f2","sha256:dea42f1fa5a14b4459720a8660eb4293e65001349b4601a3c29a05cc62f046cf"],"state_sha256":"fb2398782fc30dfd6266ac24f58947038fab34ad964e2f0a23ade4ffc0ce3367"}