{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4PRN2U2ZDOBAI4U2ENCWZIQNCA","short_pith_number":"pith:4PRN2U2Z","schema_version":"1.0","canonical_sha256":"e3e2dd53591b8204729a23456ca20d101c22fe87c019771467f2d4d71ee34b8f","source":{"kind":"arxiv","id":"2302.07994","version":1},"attestation_state":"computed","paper":{"title":"\\`A-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alessandro Achille, Benjamin Bowman, Giovanni Paolini, Luca Zancato, Matthew Trager, Pramuditha Perera, Stefano Soatto","submitted_at":"2023-02-15T23:51:09Z","abstract_excerpt":"We introduce \\`A-la-carte Prompt Tuning (APT), a transformer-based scheme to tune prompts on distinct data so that they can be arbitrarily composed at inference time. The individual prompts can be trained in isolation, possibly on different devices, at different times, and on different distributions or domains. Furthermore each prompt only contains information about the subset of data it was exposed to during training. During inference, models can be assembled based on arbitrary selections of data sources, which we call \"\\`a-la-carte learning\". \\`A-la-carte learning enables constructing bespok"},"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":"2302.07994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-15T23:51:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"2c3b855d0858248d772f73242e818def4f4914f90e1e872835685d57f7c2943c","abstract_canon_sha256":"8c082bf7162f9532e2db756fadfe857ae5cc50d3556cb62268c6ca9619769d66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:32.908800Z","signature_b64":"Z8UhU8oP7zFW2iK2cKa9dvTrQQRh+z4B6B1YIuPQCfkNkM7rl6EDZw+24jwLHw2M5iGP12NSSaxiHObL8NhJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3e2dd53591b8204729a23456ca20d101c22fe87c019771467f2d4d71ee34b8f","last_reissued_at":"2026-07-05T05:42:32.908381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:32.908381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\\`A-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alessandro Achille, Benjamin Bowman, Giovanni Paolini, Luca Zancato, Matthew Trager, Pramuditha Perera, Stefano Soatto","submitted_at":"2023-02-15T23:51:09Z","abstract_excerpt":"We introduce \\`A-la-carte Prompt Tuning (APT), a transformer-based scheme to tune prompts on distinct data so that they can be arbitrarily composed at inference time. The individual prompts can be trained in isolation, possibly on different devices, at different times, and on different distributions or domains. Furthermore each prompt only contains information about the subset of data it was exposed to during training. During inference, models can be assembled based on arbitrary selections of data sources, which we call \"\\`a-la-carte learning\". \\`A-la-carte learning enables constructing bespok"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07994","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/2302.07994/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":"2302.07994","created_at":"2026-07-05T05:42:32.908437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07994v1","created_at":"2026-07-05T05:42:32.908437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07994","created_at":"2026-07-05T05:42:32.908437+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PRN2U2ZDOBA","created_at":"2026-07-05T05:42:32.908437+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PRN2U2ZDOBAI4U2","created_at":"2026-07-05T05:42:32.908437+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PRN2U2Z","created_at":"2026-07-05T05:42:32.908437+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/4PRN2U2ZDOBAI4U2ENCWZIQNCA","json":"https://pith.science/pith/4PRN2U2ZDOBAI4U2ENCWZIQNCA.json","graph_json":"https://pith.science/api/pith-number/4PRN2U2ZDOBAI4U2ENCWZIQNCA/graph.json","events_json":"https://pith.science/api/pith-number/4PRN2U2ZDOBAI4U2ENCWZIQNCA/events.json","paper":"https://pith.science/paper/4PRN2U2Z"},"agent_actions":{"view_html":"https://pith.science/pith/4PRN2U2ZDOBAI4U2ENCWZIQNCA","download_json":"https://pith.science/pith/4PRN2U2ZDOBAI4U2ENCWZIQNCA.json","view_paper":"https://pith.science/paper/4PRN2U2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07994&json=true","fetch_graph":"https://pith.science/api/pith-number/4PRN2U2ZDOBAI4U2ENCWZIQNCA/graph.json","fetch_events":"https://pith.science/api/pith-number/4PRN2U2ZDOBAI4U2ENCWZIQNCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PRN2U2ZDOBAI4U2ENCWZIQNCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PRN2U2ZDOBAI4U2ENCWZIQNCA/action/storage_attestation","attest_author":"https://pith.science/pith/4PRN2U2ZDOBAI4U2ENCWZIQNCA/action/author_attestation","sign_citation":"https://pith.science/pith/4PRN2U2ZDOBAI4U2ENCWZIQNCA/action/citation_signature","submit_replication":"https://pith.science/pith/4PRN2U2ZDOBAI4U2ENCWZIQNCA/action/replication_record"}},"created_at":"2026-07-05T05:42:32.908437+00:00","updated_at":"2026-07-05T05:42:32.908437+00:00"}