{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LHAE4NGNL4DF3EZ52A2FRJQNOH","short_pith_number":"pith:LHAE4NGN","canonical_record":{"source":{"id":"2506.23762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-30T12:09:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71614683f28ba5d31f6b704f8d755b9221b4c4788e401cebdc8472e4b15cf6b4","abstract_canon_sha256":"1ca834d793bf298277505e4869602bcf20c0b9744d49ab273061b09537447674"},"schema_version":"1.0"},"canonical_sha256":"59c04e34cd5f065d933dd03458a60d71f78846e32e2945152345741e8c7ec209","source":{"kind":"arxiv","id":"2506.23762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23762","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23762v1","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23762","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"LHAE4NGNL4DF","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"LHAE4NGNL4DF3EZ5","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"LHAE4NGN","created_at":"2026-07-05T11:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LHAE4NGNL4DF3EZ52A2FRJQNOH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-30T12:09:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71614683f28ba5d31f6b704f8d755b9221b4c4788e401cebdc8472e4b15cf6b4","abstract_canon_sha256":"1ca834d793bf298277505e4869602bcf20c0b9744d49ab273061b09537447674"},"schema_version":"1.0"},"canonical_sha256":"59c04e34cd5f065d933dd03458a60d71f78846e32e2945152345741e8c7ec209","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:27.627843Z","signature_b64":"JZY+TjxB+u0y3V+Kjr5kmNizdSDurZg8tre/dXyCDONBJHVRRkpsJQG+nMcoRR7w4vspKBMvQhA3ImuyeyvHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59c04e34cd5f065d933dd03458a60d71f78846e32e2945152345741e8c7ec209","last_reissued_at":"2026-07-05T11:29:27.627431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:27.627431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23762","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hfio3Nvk0pku8eA6wY16zkWaKVZkCV1io0k5+GTmRiJ0dTjRSWQvanx9lMTe57hc4x7rFbTVcP3wnMjCzQIyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:18:47.268570Z"},"content_sha256":"846070c5d998bb398238d44f2eeb31b55c1cd537c4628fcc6d114a0ef3a1d0a3","schema_version":"1.0","event_id":"sha256:846070c5d998bb398238d44f2eeb31b55c1cd537c4628fcc6d114a0ef3a1d0a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LHAE4NGNL4DF3EZ52A2FRJQNOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Haoyu Wang, Hongzhou Rao, Shenao Wang, Xinyi Hou, Yanjie Zhao","submitted_at":"2025-06-30T12:09:29Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) has redefined artificial intelligence (AI), pushing the boundaries of AI research and enabling unbounded possibilities for both academia and the industry. However, LLM development faces increasingly complex challenges throughout its lifecycle, yet no existing research systematically explores these challenges and solutions from the perspective of software engineering (SE) approaches. To fill the gap, we systematically analyze research status throughout the LLM development lifecycle, divided into six phases: requirements engineering, dataset "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23762","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/2506.23762/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VdiwznmgEy4ZnOD/2a16vaMjDMMbf1+KZcDWPe5TgRFqcRVyyoUklzcsjizFL3lRHe+STyUcPiz4BxjkrkBKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:18:47.269119Z"},"content_sha256":"2437140aa76b715f54339536b358fef35922f0235843ca3332287309f383c3a9","schema_version":"1.0","event_id":"sha256:2437140aa76b715f54339536b358fef35922f0235843ca3332287309f383c3a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/bundle.json","state_url":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T04:18:47Z","links":{"resolver":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH","bundle":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/bundle.json","state":"https://pith.science/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHAE4NGNL4DF3EZ52A2FRJQNOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LHAE4NGNL4DF3EZ52A2FRJQNOH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1ca834d793bf298277505e4869602bcf20c0b9744d49ab273061b09537447674","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-30T12:09:29Z","title_canon_sha256":"71614683f28ba5d31f6b704f8d755b9221b4c4788e401cebdc8472e4b15cf6b4"},"schema_version":"1.0","source":{"id":"2506.23762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23762","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23762v1","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23762","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"LHAE4NGNL4DF","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"LHAE4NGNL4DF3EZ5","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"LHAE4NGN","created_at":"2026-07-05T11:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:2437140aa76b715f54339536b358fef35922f0235843ca3332287309f383c3a9","target":"graph","created_at":"2026-07-05T11:29:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.23762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of large language models (LLMs) has redefined artificial intelligence (AI), pushing the boundaries of AI research and enabling unbounded possibilities for both academia and the industry. However, LLM development faces increasingly complex challenges throughout its lifecycle, yet no existing research systematically explores these challenges and solutions from the perspective of software engineering (SE) approaches. To fill the gap, we systematically analyze research status throughout the LLM development lifecycle, divided into six phases: requirements engineering, dataset ","authors_text":"Haoyu Wang, Hongzhou Rao, Shenao Wang, Xinyi Hou, Yanjie Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-30T12:09:29Z","title":"Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23762","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:846070c5d998bb398238d44f2eeb31b55c1cd537c4628fcc6d114a0ef3a1d0a3","target":"record","created_at":"2026-07-05T11:29:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1ca834d793bf298277505e4869602bcf20c0b9744d49ab273061b09537447674","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-30T12:09:29Z","title_canon_sha256":"71614683f28ba5d31f6b704f8d755b9221b4c4788e401cebdc8472e4b15cf6b4"},"schema_version":"1.0","source":{"id":"2506.23762","kind":"arxiv","version":1}},"canonical_sha256":"59c04e34cd5f065d933dd03458a60d71f78846e32e2945152345741e8c7ec209","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59c04e34cd5f065d933dd03458a60d71f78846e32e2945152345741e8c7ec209","first_computed_at":"2026-07-05T11:29:27.627431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:27.627431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JZY+TjxB+u0y3V+Kjr5kmNizdSDurZg8tre/dXyCDONBJHVRRkpsJQG+nMcoRR7w4vspKBMvQhA3ImuyeyvHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:27.627843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:846070c5d998bb398238d44f2eeb31b55c1cd537c4628fcc6d114a0ef3a1d0a3","sha256:2437140aa76b715f54339536b358fef35922f0235843ca3332287309f383c3a9"],"state_sha256":"63fdcfa262bc457b32842d4bab29eb7b283f7138ea82cd92331f03491c8de5f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m28NxTWcVkImY+widcyAD0hiLCmH3iZmapQvUFBf85Af7Qd7wNmI+gk7766Q2R+9P3TXgzdcsGwESaERHtdHBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:18:47.273443Z","bundle_sha256":"940c993c849f74c58b687b5fbe18f7bbcb6de6549a9544bdbcd93eb9da2319c3"}}