{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DT7QFW6KCJEFBNM5HIB4ZYXTZC","short_pith_number":"pith:DT7QFW6K","canonical_record":{"source":{"id":"2607.13501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T06:55:28Z","cross_cats_sorted":[],"title_canon_sha256":"0d8777635499cd895f23946ad297289d4f43920e98e67862a8493fb6dfa6cd11","abstract_canon_sha256":"1f156c5e560e272e3a9e02a044f9e715b6bf082b592381974d8dffec4e7f0d34"},"schema_version":"1.0"},"canonical_sha256":"1cff02dbca124850b59d3a03cce2f3c89e0accc60a53db2f998f0d051f078204","source":{"kind":"arxiv","id":"2607.13501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13501","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13501v1","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13501","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"DT7QFW6KCJEF","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"DT7QFW6KCJEFBNM5","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"DT7QFW6K","created_at":"2026-07-16T01:22:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DT7QFW6KCJEFBNM5HIB4ZYXTZC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.13501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T06:55:28Z","cross_cats_sorted":[],"title_canon_sha256":"0d8777635499cd895f23946ad297289d4f43920e98e67862a8493fb6dfa6cd11","abstract_canon_sha256":"1f156c5e560e272e3a9e02a044f9e715b6bf082b592381974d8dffec4e7f0d34"},"schema_version":"1.0"},"canonical_sha256":"1cff02dbca124850b59d3a03cce2f3c89e0accc60a53db2f998f0d051f078204","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:16.183974Z","signature_b64":"399iSs8XkM/EKoZXwxY7ya9FY3iIxM/pXej5aT/3Elu7VlA+a/KBUQL58Dw6YTHmudLSM/wMhEBGI+tPAwzKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cff02dbca124850b59d3a03cce2f3c89e0accc60a53db2f998f0d051f078204","last_reissued_at":"2026-07-16T01:22:16.183129Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:16.183129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.13501","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":"2026-07-16T01:22:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HlJgXzJzmq5Pa6C2DKjxJY9je0ANzjbnRrqcAQcQ4yZt+cga6vDdPU6kqYtyVcm03yI9Bs8Px9OomORHPN6ACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:27:27.261889Z"},"content_sha256":"912929ee7cc137993036ce228a585bdf579d8c6f310bca116512cd0bf575d03a","schema_version":"1.0","event_id":"sha256:912929ee7cc137993036ce228a585bdf579d8c6f310bca116512cd0bf575d03a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DT7QFW6KCJEFBNM5HIB4ZYXTZC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiajun Wu, Qiang Zhu","submitted_at":"2026-07-15T06:55:28Z","abstract_excerpt":"Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LAPO, a self-generated process-supervision method based on backward leave-one-turn attribution. For each search turn, LAPO replaces the turn and its retrieval observation with a fixed [DELETE] placeholder and measures the resulting change in the current policy's mean log-likelihood of the gold answer. This Answer-Likelihood Gain estimates the turn's contribution while preserving all downstream interact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13501","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/2607.13501/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":"2026-07-16T01:22:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ubxotjx2Xu32bylHk5NK6yL+yNaAnr4QFKxeX8X/7feG4RC6r1rp/Ec6uIILvelFzahhAvzfXzBrFjl7K6dDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:27:27.262493Z"},"content_sha256":"d5e0b85a887a66887c0bf3deb9bce2f1b55b784874f1d48a36f17243c5e5fe93","schema_version":"1.0","event_id":"sha256:d5e0b85a887a66887c0bf3deb9bce2f1b55b784874f1d48a36f17243c5e5fe93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DT7QFW6KCJEFBNM5HIB4ZYXTZC/bundle.json","state_url":"https://pith.science/pith/DT7QFW6KCJEFBNM5HIB4ZYXTZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DT7QFW6KCJEFBNM5HIB4ZYXTZC/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":"2026-08-06T05:27:27Z","links":{"resolver":"https://pith.science/pith/DT7QFW6KCJEFBNM5HIB4ZYXTZC","bundle":"https://pith.science/pith/DT7QFW6KCJEFBNM5HIB4ZYXTZC/bundle.json","state":"https://pith.science/pith/DT7QFW6KCJEFBNM5HIB4ZYXTZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DT7QFW6KCJEFBNM5HIB4ZYXTZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DT7QFW6KCJEFBNM5HIB4ZYXTZC","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":"1f156c5e560e272e3a9e02a044f9e715b6bf082b592381974d8dffec4e7f0d34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T06:55:28Z","title_canon_sha256":"0d8777635499cd895f23946ad297289d4f43920e98e67862a8493fb6dfa6cd11"},"schema_version":"1.0","source":{"id":"2607.13501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13501","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13501v1","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13501","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"DT7QFW6KCJEF","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"DT7QFW6KCJEFBNM5","created_at":"2026-07-16T01:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"DT7QFW6K","created_at":"2026-07-16T01:22:16Z"}],"graph_snapshots":[{"event_id":"sha256:d5e0b85a887a66887c0bf3deb9bce2f1b55b784874f1d48a36f17243c5e5fe93","target":"graph","created_at":"2026-07-16T01:22:16Z","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/2607.13501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LAPO, a self-generated process-supervision method based on backward leave-one-turn attribution. For each search turn, LAPO replaces the turn and its retrieval observation with a fixed [DELETE] placeholder and measures the resulting change in the current policy's mean log-likelihood of the gold answer. This Answer-Likelihood Gain estimates the turn's contribution while preserving all downstream interact","authors_text":"Jiajun Wu, Qiang Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T06:55:28Z","title":"LAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13501","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":"sha256:912929ee7cc137993036ce228a585bdf579d8c6f310bca116512cd0bf575d03a","target":"record","created_at":"2026-07-16T01:22:16Z","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":"1f156c5e560e272e3a9e02a044f9e715b6bf082b592381974d8dffec4e7f0d34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T06:55:28Z","title_canon_sha256":"0d8777635499cd895f23946ad297289d4f43920e98e67862a8493fb6dfa6cd11"},"schema_version":"1.0","source":{"id":"2607.13501","kind":"arxiv","version":1}},"canonical_sha256":"1cff02dbca124850b59d3a03cce2f3c89e0accc60a53db2f998f0d051f078204","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cff02dbca124850b59d3a03cce2f3c89e0accc60a53db2f998f0d051f078204","first_computed_at":"2026-07-16T01:22:16.183129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:22:16.183129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"399iSs8XkM/EKoZXwxY7ya9FY3iIxM/pXej5aT/3Elu7VlA+a/KBUQL58Dw6YTHmudLSM/wMhEBGI+tPAwzKAQ==","signature_status":"signed_v1","signed_at":"2026-07-16T01:22:16.183974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:912929ee7cc137993036ce228a585bdf579d8c6f310bca116512cd0bf575d03a","sha256:d5e0b85a887a66887c0bf3deb9bce2f1b55b784874f1d48a36f17243c5e5fe93"],"state_sha256":"a14ecceca18ece840bad3b2fa0abbaeb0652a40add3a83a0eae38a118dc65f20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o4FkRhMzcBn8rEMRl0IrHWV+otqSthddv9IPmbKApqp2UYrYD6lc8nE/rm+5mmQ7kUXJPsCUzS3dbOi51W9NDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:27:27.267388Z","bundle_sha256":"d83385f0ae1ca6a86fe53fb1e78c7558b12c204a890e7797d460ac90cbe75934"}}