{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LB4N4GZHXSTNIGXRV354EFTVPD","short_pith_number":"pith:LB4N4GZH","schema_version":"1.0","canonical_sha256":"5878de1b27bca6d41af1aefbc2167578e940df1fa9c70fcbea350c2d21053946","source":{"kind":"arxiv","id":"2607.12463","version":1},"attestation_state":"computed","paper":{"title":"Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Cong Wei, Jiarong Liang, Ping Nie, Wenhu Chen, Xuye Liu, Yubo Wang, Yuxuan Zhang, Yuyu Zhang","submitted_at":"2026-07-14T07:44:26Z","abstract_excerpt":"Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction. We observe that the action-observation-continuation loop of a coding agent is structurally isomorphic to a function call site, where a caller binds arguments, a callee returns a value computed elsewhere, and downstream code consumes that value. This conditioning structure exists at internet scale in ordinary code. We exploit it through function-aware fill-in-the-middle (FIM) mid-training: a self-supervised objective that"},"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":"2607.12463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T07:44:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"24094fb3eb465333a81d7ef926ff6e5639c7f5f42185af19e8bf522eed5aeb47","abstract_canon_sha256":"cd13545a46a19292892dc20580a30a4c83ac039fba6cbffd6e02e904ce9f5d63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:21:36.510643Z","signature_b64":"TF0rl5ux40GOVnLT1vz+eIiG9zCjI+V7uyxBgFoxrQeP0r2ediXqd9On2XcH/8gpZSFLVuPFnzdxUp/jXhHbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5878de1b27bca6d41af1aefbc2167578e940df1fa9c70fcbea350c2d21053946","last_reissued_at":"2026-07-15T01:21:36.509836Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:21:36.509836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Cong Wei, Jiarong Liang, Ping Nie, Wenhu Chen, Xuye Liu, Yubo Wang, Yuxuan Zhang, Yuyu Zhang","submitted_at":"2026-07-14T07:44:26Z","abstract_excerpt":"Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction. We observe that the action-observation-continuation loop of a coding agent is structurally isomorphic to a function call site, where a caller binds arguments, a callee returns a value computed elsewhere, and downstream code consumes that value. This conditioning structure exists at internet scale in ordinary code. We exploit it through function-aware fill-in-the-middle (FIM) mid-training: a self-supervised objective that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12463","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/2607.12463/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":"2607.12463","created_at":"2026-07-15T01:21:36.510251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.12463v1","created_at":"2026-07-15T01:21:36.510251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12463","created_at":"2026-07-15T01:21:36.510251+00:00"},{"alias_kind":"pith_short_12","alias_value":"LB4N4GZHXSTN","created_at":"2026-07-15T01:21:36.510251+00:00"},{"alias_kind":"pith_short_16","alias_value":"LB4N4GZHXSTNIGXR","created_at":"2026-07-15T01:21:36.510251+00:00"},{"alias_kind":"pith_short_8","alias_value":"LB4N4GZH","created_at":"2026-07-15T01:21:36.510251+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/LB4N4GZHXSTNIGXRV354EFTVPD","json":"https://pith.science/pith/LB4N4GZHXSTNIGXRV354EFTVPD.json","graph_json":"https://pith.science/api/pith-number/LB4N4GZHXSTNIGXRV354EFTVPD/graph.json","events_json":"https://pith.science/api/pith-number/LB4N4GZHXSTNIGXRV354EFTVPD/events.json","paper":"https://pith.science/paper/LB4N4GZH"},"agent_actions":{"view_html":"https://pith.science/pith/LB4N4GZHXSTNIGXRV354EFTVPD","download_json":"https://pith.science/pith/LB4N4GZHXSTNIGXRV354EFTVPD.json","view_paper":"https://pith.science/paper/LB4N4GZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.12463&json=true","fetch_graph":"https://pith.science/api/pith-number/LB4N4GZHXSTNIGXRV354EFTVPD/graph.json","fetch_events":"https://pith.science/api/pith-number/LB4N4GZHXSTNIGXRV354EFTVPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LB4N4GZHXSTNIGXRV354EFTVPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LB4N4GZHXSTNIGXRV354EFTVPD/action/storage_attestation","attest_author":"https://pith.science/pith/LB4N4GZHXSTNIGXRV354EFTVPD/action/author_attestation","sign_citation":"https://pith.science/pith/LB4N4GZHXSTNIGXRV354EFTVPD/action/citation_signature","submit_replication":"https://pith.science/pith/LB4N4GZHXSTNIGXRV354EFTVPD/action/replication_record"}},"created_at":"2026-07-15T01:21:36.510251+00:00","updated_at":"2026-07-15T01:21:36.510251+00:00"}