{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LFF7P2AHTCBHADQ63EJSR7NCUL","short_pith_number":"pith:LFF7P2AH","schema_version":"1.0","canonical_sha256":"594bf7e8079882700e1ed91328fda2a2e908329bc8111147f2d368a3b9f142b4","source":{"kind":"arxiv","id":"2404.07498","version":1},"attestation_state":"computed","paper":{"title":"Interactive Prompt Debugging with Sequence Salience","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Du, Ian Tenney, Lucas Dixon, Minsuk Kahng, Ryan Mullins, Shree Pandya","submitted_at":"2024-04-11T06:22:56Z","abstract_excerpt":"We present Sequence Salience, a visual tool for interactive prompt debugging with input salience methods. Sequence Salience builds on widely used salience methods for text classification and single-token prediction, and extends this to a system tailored for debugging complex LLM prompts. Our system is well-suited for long texts, and expands on previous work by 1) providing controllable aggregation of token-level salience to the word, sentence, or paragraph level, making salience over long inputs tractable; and 2) supporting rapid iteration where practitioners can act on salience results, refin"},"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":"2404.07498","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T06:22:56Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"a1410ed1f853463c390beefd9e7b29a65a891077232e692ed2379a1b7cf599ef","abstract_canon_sha256":"267baff8520c93f913cb99476eea0202528851ac8ef098fc8c74c7842af32c98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:53.985575Z","signature_b64":"GfCOlHkPWSgM+RjJldeH8Lj4hyYQcB9L4lkqoxB4JIW+kkXNxVYfrsBKmCck4kfFgXwoyCrUuMRV8wu1J8xPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"594bf7e8079882700e1ed91328fda2a2e908329bc8111147f2d368a3b9f142b4","last_reissued_at":"2026-07-05T08:06:53.985117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:53.985117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Prompt Debugging with Sequence Salience","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Du, Ian Tenney, Lucas Dixon, Minsuk Kahng, Ryan Mullins, Shree Pandya","submitted_at":"2024-04-11T06:22:56Z","abstract_excerpt":"We present Sequence Salience, a visual tool for interactive prompt debugging with input salience methods. Sequence Salience builds on widely used salience methods for text classification and single-token prediction, and extends this to a system tailored for debugging complex LLM prompts. Our system is well-suited for long texts, and expands on previous work by 1) providing controllable aggregation of token-level salience to the word, sentence, or paragraph level, making salience over long inputs tractable; and 2) supporting rapid iteration where practitioners can act on salience results, refin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07498","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/2404.07498/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":"2404.07498","created_at":"2026-07-05T08:06:53.985173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07498v1","created_at":"2026-07-05T08:06:53.985173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07498","created_at":"2026-07-05T08:06:53.985173+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFF7P2AHTCBH","created_at":"2026-07-05T08:06:53.985173+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFF7P2AHTCBHADQ6","created_at":"2026-07-05T08:06:53.985173+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFF7P2AH","created_at":"2026-07-05T08:06:53.985173+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14770","citing_title":"Toward Inclusive AI-Driven Development: Exploring Gender Differences in Code Generation Tool Interactions","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFF7P2AHTCBHADQ63EJSR7NCUL","json":"https://pith.science/pith/LFF7P2AHTCBHADQ63EJSR7NCUL.json","graph_json":"https://pith.science/api/pith-number/LFF7P2AHTCBHADQ63EJSR7NCUL/graph.json","events_json":"https://pith.science/api/pith-number/LFF7P2AHTCBHADQ63EJSR7NCUL/events.json","paper":"https://pith.science/paper/LFF7P2AH"},"agent_actions":{"view_html":"https://pith.science/pith/LFF7P2AHTCBHADQ63EJSR7NCUL","download_json":"https://pith.science/pith/LFF7P2AHTCBHADQ63EJSR7NCUL.json","view_paper":"https://pith.science/paper/LFF7P2AH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07498&json=true","fetch_graph":"https://pith.science/api/pith-number/LFF7P2AHTCBHADQ63EJSR7NCUL/graph.json","fetch_events":"https://pith.science/api/pith-number/LFF7P2AHTCBHADQ63EJSR7NCUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFF7P2AHTCBHADQ63EJSR7NCUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFF7P2AHTCBHADQ63EJSR7NCUL/action/storage_attestation","attest_author":"https://pith.science/pith/LFF7P2AHTCBHADQ63EJSR7NCUL/action/author_attestation","sign_citation":"https://pith.science/pith/LFF7P2AHTCBHADQ63EJSR7NCUL/action/citation_signature","submit_replication":"https://pith.science/pith/LFF7P2AHTCBHADQ63EJSR7NCUL/action/replication_record"}},"created_at":"2026-07-05T08:06:53.985173+00:00","updated_at":"2026-07-05T08:06:53.985173+00:00"}