{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2BFU3VJHWALERXVUE5CNXA72RU","short_pith_number":"pith:2BFU3VJH","schema_version":"1.0","canonical_sha256":"d04b4dd527b01648deb42744db83fa8d2e40c6245b236e37abcc949ca1741aa1","source":{"kind":"arxiv","id":"2504.08696","version":2},"attestation_state":"computed","paper":{"title":"SeaView: Software Engineering Agent Visual Interface for Enhanced Workflow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Avirup Sil, Luca Buratti, Mihaela Bornea, Saurabh Pujar, Timothy Bula","submitted_at":"2025-04-11T17:03:58Z","abstract_excerpt":"Auto-regressive LLM-based software engineering (SWE) agents, henceforth SWE agents, have made tremendous progress (>60% on SWE-Bench Verified) on real-world coding challenges including GitHub issue resolution. SWE agents use a combination of reasoning, environment interaction and self-reflection to resolve issues thereby generating \"trajectories\". Analysis of SWE agent trajectories is difficult, not only as they exceed LLM sequence length (sometimes, greater than 128k) but also because it involves a relatively prolonged interaction between an LLM and the environment managed by the agent. In ca"},"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":"2504.08696","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-11T17:03:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a52320c984a2a87b7f8030453e469657707bfc987e1e989ea685e415c8e7602a","abstract_canon_sha256":"5a3dfc3cb6d31c5085c15a79986980737fba0da1adf75585fd0c39b9929b131a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:58.846698Z","signature_b64":"OSnSgNEApBaumw+5wbJhVaUrdktwVdMU7D0a9nkQrN8bWsXdBNjS8XjAU0x4FAFJixAZtBleOdVZExEq5kA8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d04b4dd527b01648deb42744db83fa8d2e40c6245b236e37abcc949ca1741aa1","last_reissued_at":"2026-07-05T10:48:58.846180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:58.846180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeaView: Software Engineering Agent Visual Interface for Enhanced Workflow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Avirup Sil, Luca Buratti, Mihaela Bornea, Saurabh Pujar, Timothy Bula","submitted_at":"2025-04-11T17:03:58Z","abstract_excerpt":"Auto-regressive LLM-based software engineering (SWE) agents, henceforth SWE agents, have made tremendous progress (>60% on SWE-Bench Verified) on real-world coding challenges including GitHub issue resolution. SWE agents use a combination of reasoning, environment interaction and self-reflection to resolve issues thereby generating \"trajectories\". Analysis of SWE agent trajectories is difficult, not only as they exceed LLM sequence length (sometimes, greater than 128k) but also because it involves a relatively prolonged interaction between an LLM and the environment managed by the agent. In ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08696","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/2504.08696/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":"2504.08696","created_at":"2026-07-05T10:48:58.846247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08696v2","created_at":"2026-07-05T10:48:58.846247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08696","created_at":"2026-07-05T10:48:58.846247+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BFU3VJHWALE","created_at":"2026-07-05T10:48:58.846247+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BFU3VJHWALERXVU","created_at":"2026-07-05T10:48:58.846247+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BFU3VJH","created_at":"2026-07-05T10:48:58.846247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22110","citing_title":"TraceView: Interactive Visualization of Agentic Program Repair Trajectories","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BFU3VJHWALERXVUE5CNXA72RU","json":"https://pith.science/pith/2BFU3VJHWALERXVUE5CNXA72RU.json","graph_json":"https://pith.science/api/pith-number/2BFU3VJHWALERXVUE5CNXA72RU/graph.json","events_json":"https://pith.science/api/pith-number/2BFU3VJHWALERXVUE5CNXA72RU/events.json","paper":"https://pith.science/paper/2BFU3VJH"},"agent_actions":{"view_html":"https://pith.science/pith/2BFU3VJHWALERXVUE5CNXA72RU","download_json":"https://pith.science/pith/2BFU3VJHWALERXVUE5CNXA72RU.json","view_paper":"https://pith.science/paper/2BFU3VJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08696&json=true","fetch_graph":"https://pith.science/api/pith-number/2BFU3VJHWALERXVUE5CNXA72RU/graph.json","fetch_events":"https://pith.science/api/pith-number/2BFU3VJHWALERXVUE5CNXA72RU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BFU3VJHWALERXVUE5CNXA72RU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BFU3VJHWALERXVUE5CNXA72RU/action/storage_attestation","attest_author":"https://pith.science/pith/2BFU3VJHWALERXVUE5CNXA72RU/action/author_attestation","sign_citation":"https://pith.science/pith/2BFU3VJHWALERXVUE5CNXA72RU/action/citation_signature","submit_replication":"https://pith.science/pith/2BFU3VJHWALERXVUE5CNXA72RU/action/replication_record"}},"created_at":"2026-07-05T10:48:58.846247+00:00","updated_at":"2026-07-05T10:48:58.846247+00:00"}