{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7L6WMI2HRFYHQP7CLPI5RNQPWN","short_pith_number":"pith:7L6WMI2H","schema_version":"1.0","canonical_sha256":"fafd6623478970783fe25bd1d8b60fb34770bdf1ba1f64a1aa74e448d1335e57","source":{"kind":"arxiv","id":"2507.14725","version":4},"attestation_state":"computed","paper":{"title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anushka Tiwari, Kaiyi Ji, Rohini K. Srihari, Sayantan Pal","submitted_at":"2025-07-19T19:15:03Z","abstract_excerpt":"Prompt-based continual learning (CL) offers a parameter-efficient way to adapt large language models (LLMs) across task sequences. However, existing methods often rely on task-aware inference and maintain an expanding set of task-specific prompts, leading to (1) severe performance degradation on earlier tasks when task identifiers are unavailable for prompt selection at inference time, and (2) limited scalability as task sequence grows. We propose GRID, a unified framework designed to address these challenges. GRID incorporates an output-space-aware decoding mechanism that enhances backward tr"},"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":"2507.14725","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-19T19:15:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f13678a132ff05065b0186fc3256f37bf0bc1cc590a43caa8b06b31c8605125","abstract_canon_sha256":"eb459058337d7c8e7520dfadbfee31775cd3121a9f6414990b22df35bf2e2e4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:20.097497Z","signature_b64":"wjaJg9t5J8HamO7CJGNZ3y7gKn7ZDtaU7Isbh5SNaCskYDPeIIcBtix6MQwxx1KWoVOFoEOSOcSILE8bob3EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fafd6623478970783fe25bd1d8b60fb34770bdf1ba1f64a1aa74e448d1335e57","last_reissued_at":"2026-06-10T01:09:20.096283Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:20.096283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anushka Tiwari, Kaiyi Ji, Rohini K. Srihari, Sayantan Pal","submitted_at":"2025-07-19T19:15:03Z","abstract_excerpt":"Prompt-based continual learning (CL) offers a parameter-efficient way to adapt large language models (LLMs) across task sequences. However, existing methods often rely on task-aware inference and maintain an expanding set of task-specific prompts, leading to (1) severe performance degradation on earlier tasks when task identifiers are unavailable for prompt selection at inference time, and (2) limited scalability as task sequence grows. We propose GRID, a unified framework designed to address these challenges. GRID incorporates an output-space-aware decoding mechanism that enhances backward tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14725","kind":"arxiv","version":4},"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/2507.14725/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":"2507.14725","created_at":"2026-06-10T01:09:20.096512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14725v4","created_at":"2026-06-10T01:09:20.096512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14725","created_at":"2026-06-10T01:09:20.096512+00:00"},{"alias_kind":"pith_short_12","alias_value":"7L6WMI2HRFYH","created_at":"2026-06-10T01:09:20.096512+00:00"},{"alias_kind":"pith_short_16","alias_value":"7L6WMI2HRFYHQP7C","created_at":"2026-06-10T01:09:20.096512+00:00"},{"alias_kind":"pith_short_8","alias_value":"7L6WMI2H","created_at":"2026-06-10T01:09:20.096512+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/7L6WMI2HRFYHQP7CLPI5RNQPWN","json":"https://pith.science/pith/7L6WMI2HRFYHQP7CLPI5RNQPWN.json","graph_json":"https://pith.science/api/pith-number/7L6WMI2HRFYHQP7CLPI5RNQPWN/graph.json","events_json":"https://pith.science/api/pith-number/7L6WMI2HRFYHQP7CLPI5RNQPWN/events.json","paper":"https://pith.science/paper/7L6WMI2H"},"agent_actions":{"view_html":"https://pith.science/pith/7L6WMI2HRFYHQP7CLPI5RNQPWN","download_json":"https://pith.science/pith/7L6WMI2HRFYHQP7CLPI5RNQPWN.json","view_paper":"https://pith.science/paper/7L6WMI2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14725&json=true","fetch_graph":"https://pith.science/api/pith-number/7L6WMI2HRFYHQP7CLPI5RNQPWN/graph.json","fetch_events":"https://pith.science/api/pith-number/7L6WMI2HRFYHQP7CLPI5RNQPWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7L6WMI2HRFYHQP7CLPI5RNQPWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7L6WMI2HRFYHQP7CLPI5RNQPWN/action/storage_attestation","attest_author":"https://pith.science/pith/7L6WMI2HRFYHQP7CLPI5RNQPWN/action/author_attestation","sign_citation":"https://pith.science/pith/7L6WMI2HRFYHQP7CLPI5RNQPWN/action/citation_signature","submit_replication":"https://pith.science/pith/7L6WMI2HRFYHQP7CLPI5RNQPWN/action/replication_record"}},"created_at":"2026-06-10T01:09:20.096512+00:00","updated_at":"2026-06-10T01:09:20.096512+00:00"}