{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UZ3CUIEO2ZMSRGRXYOY2KOL7CO","short_pith_number":"pith:UZ3CUIEO","schema_version":"1.0","canonical_sha256":"a6762a208ed659289a37c3b1a5397f13ab63ee68372debf78403d2a4df5c83cd","source":{"kind":"arxiv","id":"2501.16404","version":1},"attestation_state":"computed","paper":{"title":"DynaPrompt: Dynamic Test-Time Prompt Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cees G. M. Snoek, Jack Hong, Jiayin Cai, Jiayi Shen, Qi Wang, Shilin Yan, Xiaolong Jiang, Yao Hu, Zehao Xiao","submitted_at":"2025-01-27T09:10:06Z","abstract_excerpt":"Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in previous test samples, albeit with the risk of prompt collapse due to error accumulation. To enhance test-time prompt tuning, we propose DynaPrompt, short for dynamic test-time prompt tuning, exploiting relevant data distribution information while reducing error accumulation. Built on an online prompt buffer, DynaPrompt adaptively selects and optimizes the "},"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":"2501.16404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T09:10:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fc2de7e00d326730dd8a7ce8efdfa3231385f4a74891f326cdfdaf165585821e","abstract_canon_sha256":"b56cbd6aff6d55cad2926358783bd113fe6478c02de650524e22cb81464e3f24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:33.322344Z","signature_b64":"Nobcwtmp3/GePZxf2QLZwIrFX/HX63D+pGnEdwPx7ZfCOhfaqBO73QlSfHDpw1BNiC9I+an1nQrkQK1yYh+CCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6762a208ed659289a37c3b1a5397f13ab63ee68372debf78403d2a4df5c83cd","last_reissued_at":"2026-07-05T10:06:33.321890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:33.321890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynaPrompt: Dynamic Test-Time Prompt Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cees G. M. Snoek, Jack Hong, Jiayin Cai, Jiayi Shen, Qi Wang, Shilin Yan, Xiaolong Jiang, Yao Hu, Zehao Xiao","submitted_at":"2025-01-27T09:10:06Z","abstract_excerpt":"Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in previous test samples, albeit with the risk of prompt collapse due to error accumulation. To enhance test-time prompt tuning, we propose DynaPrompt, short for dynamic test-time prompt tuning, exploiting relevant data distribution information while reducing error accumulation. Built on an online prompt buffer, DynaPrompt adaptively selects and optimizes the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16404","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/2501.16404/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":"2501.16404","created_at":"2026-07-05T10:06:33.321946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16404v1","created_at":"2026-07-05T10:06:33.321946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16404","created_at":"2026-07-05T10:06:33.321946+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZ3CUIEO2ZMS","created_at":"2026-07-05T10:06:33.321946+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZ3CUIEO2ZMSRGRX","created_at":"2026-07-05T10:06:33.321946+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZ3CUIEO","created_at":"2026-07-05T10:06:33.321946+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28719","citing_title":"ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZ3CUIEO2ZMSRGRXYOY2KOL7CO","json":"https://pith.science/pith/UZ3CUIEO2ZMSRGRXYOY2KOL7CO.json","graph_json":"https://pith.science/api/pith-number/UZ3CUIEO2ZMSRGRXYOY2KOL7CO/graph.json","events_json":"https://pith.science/api/pith-number/UZ3CUIEO2ZMSRGRXYOY2KOL7CO/events.json","paper":"https://pith.science/paper/UZ3CUIEO"},"agent_actions":{"view_html":"https://pith.science/pith/UZ3CUIEO2ZMSRGRXYOY2KOL7CO","download_json":"https://pith.science/pith/UZ3CUIEO2ZMSRGRXYOY2KOL7CO.json","view_paper":"https://pith.science/paper/UZ3CUIEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16404&json=true","fetch_graph":"https://pith.science/api/pith-number/UZ3CUIEO2ZMSRGRXYOY2KOL7CO/graph.json","fetch_events":"https://pith.science/api/pith-number/UZ3CUIEO2ZMSRGRXYOY2KOL7CO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZ3CUIEO2ZMSRGRXYOY2KOL7CO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZ3CUIEO2ZMSRGRXYOY2KOL7CO/action/storage_attestation","attest_author":"https://pith.science/pith/UZ3CUIEO2ZMSRGRXYOY2KOL7CO/action/author_attestation","sign_citation":"https://pith.science/pith/UZ3CUIEO2ZMSRGRXYOY2KOL7CO/action/citation_signature","submit_replication":"https://pith.science/pith/UZ3CUIEO2ZMSRGRXYOY2KOL7CO/action/replication_record"}},"created_at":"2026-07-05T10:06:33.321946+00:00","updated_at":"2026-07-05T10:06:33.321946+00:00"}