{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KQKLQRMKTG7RL5JRFON74BEDNM","short_pith_number":"pith:KQKLQRMK","schema_version":"1.0","canonical_sha256":"5414b8458a99bf15f5312b9bfe04836b24747894f4439a4b6ba8fad2b2e5d9d1","source":{"kind":"arxiv","id":"2606.03539","version":1},"attestation_state":"computed","paper":{"title":"Knowledge-Preserved Model Tuning in Null-Space for Robust Spatio-Temporal Video Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxuan Chen, Jian-Fang Hu, Xianqin Liu","submitted_at":"2026-06-02T11:59:27Z","abstract_excerpt":"Spatio-Temporal Video Grounding aims to localize object tubes based on textual queries. While recent methods have achieved remarkable success, they mainly focus on high-quality(HQ) inputs, neglecting the widespread presence of low-quality(LQ) videos in real-world scenarios. Although tuning methods like LoRA can adapt to degraded inputs, they inevitably disrupt pre-trained knowledge. To address this, we propose Null-Space Tuning (NST). This framework exploits the geometric property that adding vectors within the null-space of frozen weights to the layer input does not affect the output. Leverag"},"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":"2606.03539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T11:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"fd71ca1689a586e65aace76ae51ac2e0ffd42243fe7d7fec69aea1d1b13cbd7c","abstract_canon_sha256":"685500d61752ed775431ef2ed3365cfc6d984fa130c1a0dbe1edeb1bea510844"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:06:00.351716Z","signature_b64":"nJ3ytZkQP0AZRQA03gKlIl2tpNfrSTtKUT0jb0Ig4bioGPqrN4KukcwTHj2wbPWrBplY2K+vp1KGkDH0pePFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5414b8458a99bf15f5312b9bfe04836b24747894f4439a4b6ba8fad2b2e5d9d1","last_reissued_at":"2026-06-03T01:06:00.351322Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:06:00.351322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge-Preserved Model Tuning in Null-Space for Robust Spatio-Temporal Video Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxuan Chen, Jian-Fang Hu, Xianqin Liu","submitted_at":"2026-06-02T11:59:27Z","abstract_excerpt":"Spatio-Temporal Video Grounding aims to localize object tubes based on textual queries. While recent methods have achieved remarkable success, they mainly focus on high-quality(HQ) inputs, neglecting the widespread presence of low-quality(LQ) videos in real-world scenarios. Although tuning methods like LoRA can adapt to degraded inputs, they inevitably disrupt pre-trained knowledge. To address this, we propose Null-Space Tuning (NST). This framework exploits the geometric property that adding vectors within the null-space of frozen weights to the layer input does not affect the output. Leverag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03539","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/2606.03539/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":"2606.03539","created_at":"2026-06-03T01:06:00.351377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03539v1","created_at":"2026-06-03T01:06:00.351377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03539","created_at":"2026-06-03T01:06:00.351377+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQKLQRMKTG7R","created_at":"2026-06-03T01:06:00.351377+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQKLQRMKTG7RL5JR","created_at":"2026-06-03T01:06:00.351377+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQKLQRMK","created_at":"2026-06-03T01:06:00.351377+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/KQKLQRMKTG7RL5JRFON74BEDNM","json":"https://pith.science/pith/KQKLQRMKTG7RL5JRFON74BEDNM.json","graph_json":"https://pith.science/api/pith-number/KQKLQRMKTG7RL5JRFON74BEDNM/graph.json","events_json":"https://pith.science/api/pith-number/KQKLQRMKTG7RL5JRFON74BEDNM/events.json","paper":"https://pith.science/paper/KQKLQRMK"},"agent_actions":{"view_html":"https://pith.science/pith/KQKLQRMKTG7RL5JRFON74BEDNM","download_json":"https://pith.science/pith/KQKLQRMKTG7RL5JRFON74BEDNM.json","view_paper":"https://pith.science/paper/KQKLQRMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03539&json=true","fetch_graph":"https://pith.science/api/pith-number/KQKLQRMKTG7RL5JRFON74BEDNM/graph.json","fetch_events":"https://pith.science/api/pith-number/KQKLQRMKTG7RL5JRFON74BEDNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQKLQRMKTG7RL5JRFON74BEDNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQKLQRMKTG7RL5JRFON74BEDNM/action/storage_attestation","attest_author":"https://pith.science/pith/KQKLQRMKTG7RL5JRFON74BEDNM/action/author_attestation","sign_citation":"https://pith.science/pith/KQKLQRMKTG7RL5JRFON74BEDNM/action/citation_signature","submit_replication":"https://pith.science/pith/KQKLQRMKTG7RL5JRFON74BEDNM/action/replication_record"}},"created_at":"2026-06-03T01:06:00.351377+00:00","updated_at":"2026-06-03T01:06:00.351377+00:00"}