{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GISE5V3RCJXD62QQAFNNY3VMTL","short_pith_number":"pith:GISE5V3R","canonical_record":{"source":{"id":"2606.09748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T17:08:36Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d24469e9463b7c04362a9885be324f10c0d68658f01aa5a930d355446accaff9","abstract_canon_sha256":"0dd59ee4ac44f20caa368f2f992401feb2a16675f220690f7da7b793a225210e"},"schema_version":"1.0"},"canonical_sha256":"32244ed771126e3f6a10015adc6eac9adf3bc762271f6cb6d7afd7f47341200c","source":{"kind":"arxiv","id":"2606.09748","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09748","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09748v1","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09748","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"pith_short_12","alias_value":"GISE5V3RCJXD","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"pith_short_16","alias_value":"GISE5V3RCJXD62QQ","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"pith_short_8","alias_value":"GISE5V3R","created_at":"2026-06-09T02:09:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GISE5V3RCJXD62QQAFNNY3VMTL","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T17:08:36Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d24469e9463b7c04362a9885be324f10c0d68658f01aa5a930d355446accaff9","abstract_canon_sha256":"0dd59ee4ac44f20caa368f2f992401feb2a16675f220690f7da7b793a225210e"},"schema_version":"1.0"},"canonical_sha256":"32244ed771126e3f6a10015adc6eac9adf3bc762271f6cb6d7afd7f47341200c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:07.433725Z","signature_b64":"a3lFTtBooc6sdVCGR7amWvTmhhtQ6qY8H8HGWIKT8glXbO7up6Zi7W27bNCmUdS4lFc5sDuf6Vde/X+Fd/TgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32244ed771126e3f6a10015adc6eac9adf3bc762271f6cb6d7afd7f47341200c","last_reissued_at":"2026-06-09T02:09:07.432856Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:07.432856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09748","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":"2026-06-09T02:09:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f9evE3RaDhCPpO6THttMg/cUXRSY5aNMJiQw/jONXxZjvMJPx1LwbhzrtJhYlx1EjeVDj8cDBebQVooYP+JQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T01:44:10.902158Z"},"content_sha256":"54e8f825be6f949340224bb83ba19ad527a23041f8c0513dcf69aeb932e559f8","schema_version":"1.0","event_id":"sha256:54e8f825be6f949340224bb83ba19ad527a23041f8c0513dcf69aeb932e559f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GISE5V3RCJXD62QQAFNNY3VMTL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Amos Storkey, Hongru Wang, Jeff Z. Pan, Rishabh Sabharwal","submitted_at":"2026-06-08T17:08:36Z","abstract_excerpt":"Existing benchmarks for deep research agents (DRAs) assess only single-shot outputs, ignoring a key question: can DRAs improve their reports when guided by feedback? To investigate this, we conduct a multi-turn evaluation of DRAs under two feedback settings: self-reflection, in which the agent revises its report without any external diagnostic signal, and process-level feedback, in which the agent receives guidance targeting gaps in its research strategy. To enable process-level feedback, we design Research Gap Inference (RGI), a method that analyzes patterns of satisfied and unsatisfied rubri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09748","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/2606.09748/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":"2026-06-09T02:09:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KNMxntJl6046sNqOEteXObpO/bXd1C391rNCKRHEzy9k9YzUkg7vQyTVhMevWhDMXJeUX+yUMmAlxoE4k2/rAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T01:44:10.902551Z"},"content_sha256":"876336dd23cd70382c985b6189c0f493f5eb6ca1ae360e24f946b8e25867d3f2","schema_version":"1.0","event_id":"sha256:876336dd23cd70382c985b6189c0f493f5eb6ca1ae360e24f946b8e25867d3f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GISE5V3RCJXD62QQAFNNY3VMTL/bundle.json","state_url":"https://pith.science/pith/GISE5V3RCJXD62QQAFNNY3VMTL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GISE5V3RCJXD62QQAFNNY3VMTL/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":"2026-07-05T01:44:10Z","links":{"resolver":"https://pith.science/pith/GISE5V3RCJXD62QQAFNNY3VMTL","bundle":"https://pith.science/pith/GISE5V3RCJXD62QQAFNNY3VMTL/bundle.json","state":"https://pith.science/pith/GISE5V3RCJXD62QQAFNNY3VMTL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GISE5V3RCJXD62QQAFNNY3VMTL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GISE5V3RCJXD62QQAFNNY3VMTL","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":"0dd59ee4ac44f20caa368f2f992401feb2a16675f220690f7da7b793a225210e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T17:08:36Z","title_canon_sha256":"d24469e9463b7c04362a9885be324f10c0d68658f01aa5a930d355446accaff9"},"schema_version":"1.0","source":{"id":"2606.09748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09748","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09748v1","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09748","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"pith_short_12","alias_value":"GISE5V3RCJXD","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"pith_short_16","alias_value":"GISE5V3RCJXD62QQ","created_at":"2026-06-09T02:09:07Z"},{"alias_kind":"pith_short_8","alias_value":"GISE5V3R","created_at":"2026-06-09T02:09:07Z"}],"graph_snapshots":[{"event_id":"sha256:876336dd23cd70382c985b6189c0f493f5eb6ca1ae360e24f946b8e25867d3f2","target":"graph","created_at":"2026-06-09T02:09:07Z","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/2606.09748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing benchmarks for deep research agents (DRAs) assess only single-shot outputs, ignoring a key question: can DRAs improve their reports when guided by feedback? To investigate this, we conduct a multi-turn evaluation of DRAs under two feedback settings: self-reflection, in which the agent revises its report without any external diagnostic signal, and process-level feedback, in which the agent receives guidance targeting gaps in its research strategy. To enable process-level feedback, we design Research Gap Inference (RGI), a method that analyzes patterns of satisfied and unsatisfied rubri","authors_text":"Amos Storkey, Hongru Wang, Jeff Z. Pan, Rishabh Sabharwal","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T17:08:36Z","title":"Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09748","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":"sha256:54e8f825be6f949340224bb83ba19ad527a23041f8c0513dcf69aeb932e559f8","target":"record","created_at":"2026-06-09T02:09:07Z","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":"0dd59ee4ac44f20caa368f2f992401feb2a16675f220690f7da7b793a225210e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T17:08:36Z","title_canon_sha256":"d24469e9463b7c04362a9885be324f10c0d68658f01aa5a930d355446accaff9"},"schema_version":"1.0","source":{"id":"2606.09748","kind":"arxiv","version":1}},"canonical_sha256":"32244ed771126e3f6a10015adc6eac9adf3bc762271f6cb6d7afd7f47341200c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32244ed771126e3f6a10015adc6eac9adf3bc762271f6cb6d7afd7f47341200c","first_computed_at":"2026-06-09T02:09:07.432856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:09:07.432856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a3lFTtBooc6sdVCGR7amWvTmhhtQ6qY8H8HGWIKT8glXbO7up6Zi7W27bNCmUdS4lFc5sDuf6Vde/X+Fd/TgDA==","signature_status":"signed_v1","signed_at":"2026-06-09T02:09:07.433725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54e8f825be6f949340224bb83ba19ad527a23041f8c0513dcf69aeb932e559f8","sha256:876336dd23cd70382c985b6189c0f493f5eb6ca1ae360e24f946b8e25867d3f2"],"state_sha256":"e36f41f1be1484c038995c9d1dbe2e9e48eaa3ee03a20c31af4c31821cf24d01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0sNOS742TvSP4vJeXAvTx+FtDC5enx7F8sOXvpEQbSwfV8SMZNJkkFuihKI5h4XytCTiQXgk8RUAgZWpNzlgBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T01:44:10.904514Z","bundle_sha256":"5d93764e4e0ced6412b854d72b52823273f789c514eb937a4000c463ef509892"}}