{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JQ7CIAGHN354UGIZGZMDRK72SU","short_pith_number":"pith:JQ7CIAGH","canonical_record":{"source":{"id":"2607.27937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:47:58Z","cross_cats_sorted":[],"title_canon_sha256":"7b9553c239315b4471c9a275b954721172123e1569af071c9f3e21672119ccb5","abstract_canon_sha256":"c73a6470d5817755422a012a901440cdb2c048a428b016dd94b007fec2330b8e"},"schema_version":"1.0"},"canonical_sha256":"4c3e2400c76efbca1919365838abfa9513d530a84f1314b70e8cd56b05ca8e2e","source":{"kind":"arxiv","id":"2607.27937","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27937","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27937v1","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27937","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"pith_short_12","alias_value":"JQ7CIAGHN354","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"pith_short_16","alias_value":"JQ7CIAGHN354UGIZ","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"pith_short_8","alias_value":"JQ7CIAGH","created_at":"2026-07-31T01:34:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JQ7CIAGHN354UGIZGZMDRK72SU","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:47:58Z","cross_cats_sorted":[],"title_canon_sha256":"7b9553c239315b4471c9a275b954721172123e1569af071c9f3e21672119ccb5","abstract_canon_sha256":"c73a6470d5817755422a012a901440cdb2c048a428b016dd94b007fec2330b8e"},"schema_version":"1.0"},"canonical_sha256":"4c3e2400c76efbca1919365838abfa9513d530a84f1314b70e8cd56b05ca8e2e","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c3e2400c76efbca1919365838abfa9513d530a84f1314b70e8cd56b05ca8e2e","last_reissued_at":"2026-07-31T01:34:50.676570Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:34:50.676570Z"},"source_kind":"arxiv","source_id":"2607.27937","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":"2026-07-31T01:34:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pz3XEf3r3zbCU8WJUk/Wn3ENjvFNtH1hnewFVE2B3zebKEkzetR2bfHu/apNh1WAOoNCMP43Aq1W2hBnv0hRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:59:16.630598Z"},"content_sha256":"5088dededf0d6e383b92331828d098e7986cb35a58248ff7eb9d7d65cea57490","schema_version":"1.0","event_id":"sha256:5088dededf0d6e383b92331828d098e7986cb35a58248ff7eb9d7d65cea57490"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JQ7CIAGHN354UGIZGZMDRK72SU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiaju Chen, Jinghua Piao, Min Yang, Xiaochong Lan, Xu Xia, Yong Li","submitted_at":"2026-07-30T09:47:58Z","abstract_excerpt":"Recent work on LLM agents is shifting from external capability elicitation to capability internalization, enabling agents to retain useful skills without retrieval at inference time. On-policy self-distillation (OPSD) offers a promising direction, but many existing methods typically supervise students by scoring actions along student-generated trajectories. Such supervision has two limitations: teacher preferences are not validated by environment outcomes, and action-level scores underuse information from student rollouts, teacher rollouts, and their behavioral relationship. We therefore advoc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27937","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/2607.27937/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":"2026-07-31T01:34:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oUABqxhHq8c9EgJfFmfEGLweYnvmxHlm4YDXlTv1YL0kZ/c8X1uED7MEzZq1haBmUe/KCe39FtrjSJPcgXo7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:59:16.631109Z"},"content_sha256":"560391ee73bba00c2dc2dbcf95b790df278a34aa859c4d4724bebdfd064e4ab4","schema_version":"1.0","event_id":"sha256:560391ee73bba00c2dc2dbcf95b790df278a34aa859c4d4724bebdfd064e4ab4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQ7CIAGHN354UGIZGZMDRK72SU/bundle.json","state_url":"https://pith.science/pith/JQ7CIAGHN354UGIZGZMDRK72SU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQ7CIAGHN354UGIZGZMDRK72SU/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":"2026-08-15T20:59:16Z","links":{"resolver":"https://pith.science/pith/JQ7CIAGHN354UGIZGZMDRK72SU","bundle":"https://pith.science/pith/JQ7CIAGHN354UGIZGZMDRK72SU/bundle.json","state":"https://pith.science/pith/JQ7CIAGHN354UGIZGZMDRK72SU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQ7CIAGHN354UGIZGZMDRK72SU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JQ7CIAGHN354UGIZGZMDRK72SU","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":"c73a6470d5817755422a012a901440cdb2c048a428b016dd94b007fec2330b8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:47:58Z","title_canon_sha256":"7b9553c239315b4471c9a275b954721172123e1569af071c9f3e21672119ccb5"},"schema_version":"1.0","source":{"id":"2607.27937","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27937","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27937v1","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27937","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"pith_short_12","alias_value":"JQ7CIAGHN354","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"pith_short_16","alias_value":"JQ7CIAGHN354UGIZ","created_at":"2026-07-31T01:34:50Z"},{"alias_kind":"pith_short_8","alias_value":"JQ7CIAGH","created_at":"2026-07-31T01:34:50Z"}],"graph_snapshots":[{"event_id":"sha256:560391ee73bba00c2dc2dbcf95b790df278a34aa859c4d4724bebdfd064e4ab4","target":"graph","created_at":"2026-07-31T01:34:50Z","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/2607.27937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work on LLM agents is shifting from external capability elicitation to capability internalization, enabling agents to retain useful skills without retrieval at inference time. On-policy self-distillation (OPSD) offers a promising direction, but many existing methods typically supervise students by scoring actions along student-generated trajectories. Such supervision has two limitations: teacher preferences are not validated by environment outcomes, and action-level scores underuse information from student rollouts, teacher rollouts, and their behavioral relationship. We therefore advoc","authors_text":"Jiaju Chen, Jinghua Piao, Min Yang, Xiaochong Lan, Xu Xia, Yong Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:47:58Z","title":"From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27937","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":"sha256:5088dededf0d6e383b92331828d098e7986cb35a58248ff7eb9d7d65cea57490","target":"record","created_at":"2026-07-31T01:34:50Z","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":"c73a6470d5817755422a012a901440cdb2c048a428b016dd94b007fec2330b8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:47:58Z","title_canon_sha256":"7b9553c239315b4471c9a275b954721172123e1569af071c9f3e21672119ccb5"},"schema_version":"1.0","source":{"id":"2607.27937","kind":"arxiv","version":1}},"canonical_sha256":"4c3e2400c76efbca1919365838abfa9513d530a84f1314b70e8cd56b05ca8e2e","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c3e2400c76efbca1919365838abfa9513d530a84f1314b70e8cd56b05ca8e2e","first_computed_at":"2026-07-31T01:34:50.676570Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:34:50.676570Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27937","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5088dededf0d6e383b92331828d098e7986cb35a58248ff7eb9d7d65cea57490","sha256:560391ee73bba00c2dc2dbcf95b790df278a34aa859c4d4724bebdfd064e4ab4"],"state_sha256":"237a74b1978755560eb6e1aa4d7d38a6c271c7d012b26fad45a711c1ccb144f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wUkTVt5XhUpXH0b91j7b+UhC/DceDp+MDgR7W47zITFLWt2dt0E7IhBzAbfJlpio8woBj67ZvVUhA1LOuttIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T20:59:16.635946Z","bundle_sha256":"c9c7ffbe20f7aa98b12d8639d8c5355bdb2e295a755b811304d88e9bc0b85a2b"}}