{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ML6SNFQ5VCHRSY32UPX7MXXNZD","short_pith_number":"pith:ML6SNFQ5","schema_version":"1.0","canonical_sha256":"62fd26961da88f19637aa3eff65eedc8e0e27c46c531507ae31e95d950bd87f6","source":{"kind":"arxiv","id":"2310.05905","version":2},"attestation_state":"computed","paper":{"title":"TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Jesse Zhang, Kavosh Asadi, Rasool Fakoor, Shoham Sabach, Yao Liu, Zuxin Liu","submitted_at":"2023-10-09T17:49:50Z","abstract_excerpt":"The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challenges associated with training or fine-tuning these large models for such applications. Prior work mainly emphasizes either effective pretraining of large models for decision-making or single-task adaptation. But real-world problems will require data-efficient, continual adaptation for new control tasks. Recognizing these constraints, we introduce TAIL (Task-specific Adapters for Imitation Learning), a framework for e"},"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":"2310.05905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T17:49:50Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"d5cdb1c51591895d5afaf04d56786c51531ea4d826d490ab22d949e231329c13","abstract_canon_sha256":"fe50569bae86ea90158cacfa5b3ecfc8a25cb9f40e1b47344a77cf6112424a87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:31.474130Z","signature_b64":"bSnWdymZ/vdjURhjwkt/hut5urPEtK0EcuYUkApxvLLmAqjypjv/p93a9FElN6JEziNKRKSBlRfNvi3rtWlxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62fd26961da88f19637aa3eff65eedc8e0e27c46c531507ae31e95d950bd87f6","last_reissued_at":"2026-07-05T07:53:31.473690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:31.473690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Jesse Zhang, Kavosh Asadi, Rasool Fakoor, Shoham Sabach, Yao Liu, Zuxin Liu","submitted_at":"2023-10-09T17:49:50Z","abstract_excerpt":"The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challenges associated with training or fine-tuning these large models for such applications. Prior work mainly emphasizes either effective pretraining of large models for decision-making or single-task adaptation. But real-world problems will require data-efficient, continual adaptation for new control tasks. Recognizing these constraints, we introduce TAIL (Task-specific Adapters for Imitation Learning), a framework for e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05905","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/2310.05905/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":"2310.05905","created_at":"2026-07-05T07:53:31.473748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05905v2","created_at":"2026-07-05T07:53:31.473748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05905","created_at":"2026-07-05T07:53:31.473748+00:00"},{"alias_kind":"pith_short_12","alias_value":"ML6SNFQ5VCHR","created_at":"2026-07-05T07:53:31.473748+00:00"},{"alias_kind":"pith_short_16","alias_value":"ML6SNFQ5VCHRSY32","created_at":"2026-07-05T07:53:31.473748+00:00"},{"alias_kind":"pith_short_8","alias_value":"ML6SNFQ5","created_at":"2026-07-05T07:53:31.473748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27374","citing_title":"World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07999","citing_title":"Efficient Skill Grounding via Code Refactoring with Small Language Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09512","citing_title":"CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10503","citing_title":"Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18085","citing_title":"Continually Evolving Skill Knowledge in Vision Language Action Model","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08311","citing_title":"Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ML6SNFQ5VCHRSY32UPX7MXXNZD","json":"https://pith.science/pith/ML6SNFQ5VCHRSY32UPX7MXXNZD.json","graph_json":"https://pith.science/api/pith-number/ML6SNFQ5VCHRSY32UPX7MXXNZD/graph.json","events_json":"https://pith.science/api/pith-number/ML6SNFQ5VCHRSY32UPX7MXXNZD/events.json","paper":"https://pith.science/paper/ML6SNFQ5"},"agent_actions":{"view_html":"https://pith.science/pith/ML6SNFQ5VCHRSY32UPX7MXXNZD","download_json":"https://pith.science/pith/ML6SNFQ5VCHRSY32UPX7MXXNZD.json","view_paper":"https://pith.science/paper/ML6SNFQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05905&json=true","fetch_graph":"https://pith.science/api/pith-number/ML6SNFQ5VCHRSY32UPX7MXXNZD/graph.json","fetch_events":"https://pith.science/api/pith-number/ML6SNFQ5VCHRSY32UPX7MXXNZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ML6SNFQ5VCHRSY32UPX7MXXNZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ML6SNFQ5VCHRSY32UPX7MXXNZD/action/storage_attestation","attest_author":"https://pith.science/pith/ML6SNFQ5VCHRSY32UPX7MXXNZD/action/author_attestation","sign_citation":"https://pith.science/pith/ML6SNFQ5VCHRSY32UPX7MXXNZD/action/citation_signature","submit_replication":"https://pith.science/pith/ML6SNFQ5VCHRSY32UPX7MXXNZD/action/replication_record"}},"created_at":"2026-07-05T07:53:31.473748+00:00","updated_at":"2026-07-05T07:53:31.473748+00:00"}