{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5X3ETB67TQKKOL6URYMS74IJQ7","short_pith_number":"pith:5X3ETB67","canonical_record":{"source":{"id":"2608.00969","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T03:48:41Z","cross_cats_sorted":[],"title_canon_sha256":"ac02abb641f04b4d1872aa7272b05cb211aa9ecbe15bd85a8ca5004f7981dbe9","abstract_canon_sha256":"86657bd4da940c93fc4e2e8727067219630fd97edc16bd1aed783ce35423ec27"},"schema_version":"1.0"},"canonical_sha256":"edf64987df9c14a72fd48e192ff10987d6c0863a8d8de8ca3cf8092890b265f5","source":{"kind":"arxiv","id":"2608.00969","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00969","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00969v1","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00969","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"pith_short_12","alias_value":"5X3ETB67TQKK","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"pith_short_16","alias_value":"5X3ETB67TQKKOL6U","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"pith_short_8","alias_value":"5X3ETB67","created_at":"2026-08-04T01:56:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5X3ETB67TQKKOL6URYMS74IJQ7","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00969","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T03:48:41Z","cross_cats_sorted":[],"title_canon_sha256":"ac02abb641f04b4d1872aa7272b05cb211aa9ecbe15bd85a8ca5004f7981dbe9","abstract_canon_sha256":"86657bd4da940c93fc4e2e8727067219630fd97edc16bd1aed783ce35423ec27"},"schema_version":"1.0"},"canonical_sha256":"edf64987df9c14a72fd48e192ff10987d6c0863a8d8de8ca3cf8092890b265f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:56:08.214460Z","signature_b64":"t2mdE9j+CkG/j6/TbmoL2qqZNoCj4gxISFMLLiHnns3jC86hBKrYXXlGzjd+PZzWioILE8PMJ8c6kt1051P0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edf64987df9c14a72fd48e192ff10987d6c0863a8d8de8ca3cf8092890b265f5","last_reissued_at":"2026-08-04T01:56:08.212821Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:56:08.212821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00969","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":"2026-08-04T01:56:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+5JCtMtbyx/GjKZ5BMP6bPilTifocpECq4V+muzPgC2PruUwaJBysuGqZGmAFLWoIPU4fC8cWoM+d1H9INtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:45:25.613090Z"},"content_sha256":"c289c7701339464328a9703a0ee24a611c29350ca69e8bf1f7c86682c9c57558","schema_version":"1.0","event_id":"sha256:c289c7701339464328a9703a0ee24a611c29350ca69e8bf1f7c86682c9c57558"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5X3ETB67TQKKOL6URYMS74IJQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aounon Kumar, Srinivas Chappidi, Sudipta Paul, Vijay Srinivasan, Vivek Kulkarni, Wenbo Li, Yashas Malur Saidutta","submitted_at":"2026-08-02T03:48:41Z","abstract_excerpt":"Existing search-augmented LLM agents are trained using Reinforcement Learning to boost its reasoning capabilities. However, these approaches primarily rely on outcome-level rewards, which provide little supervision over search behavior and overlook agent's ability to decompose complex queries properly. To mitigate this issue, we propose PROGRESS which utilizes teacher-guided coverage reward to explicitly shape decomposed query generation of the policy model. During training, frozen teacher models are used to decompose complex queries into essential search queries. These essential search querie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00969","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/2608.00969/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":"2026-08-04T01:56:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJYl2cOU9jTZBYnVyu1JCxmZ2nLAtKCvXqLAAiLpDpd66lv0qB/Ll+zzahC62t/CFEqrncRmAoEjj+WmDsX+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:45:25.614534Z"},"content_sha256":"8fe23329500adc8d63944f6854d69d9358d7d27794267fc2aa41a371e6d20e80","schema_version":"1.0","event_id":"sha256:8fe23329500adc8d63944f6854d69d9358d7d27794267fc2aa41a371e6d20e80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5X3ETB67TQKKOL6URYMS74IJQ7/bundle.json","state_url":"https://pith.science/pith/5X3ETB67TQKKOL6URYMS74IJQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5X3ETB67TQKKOL6URYMS74IJQ7/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":"2026-08-11T07:45:25Z","links":{"resolver":"https://pith.science/pith/5X3ETB67TQKKOL6URYMS74IJQ7","bundle":"https://pith.science/pith/5X3ETB67TQKKOL6URYMS74IJQ7/bundle.json","state":"https://pith.science/pith/5X3ETB67TQKKOL6URYMS74IJQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5X3ETB67TQKKOL6URYMS74IJQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5X3ETB67TQKKOL6URYMS74IJQ7","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":"86657bd4da940c93fc4e2e8727067219630fd97edc16bd1aed783ce35423ec27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T03:48:41Z","title_canon_sha256":"ac02abb641f04b4d1872aa7272b05cb211aa9ecbe15bd85a8ca5004f7981dbe9"},"schema_version":"1.0","source":{"id":"2608.00969","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00969","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00969v1","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00969","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"pith_short_12","alias_value":"5X3ETB67TQKK","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"pith_short_16","alias_value":"5X3ETB67TQKKOL6U","created_at":"2026-08-04T01:56:08Z"},{"alias_kind":"pith_short_8","alias_value":"5X3ETB67","created_at":"2026-08-04T01:56:08Z"}],"graph_snapshots":[{"event_id":"sha256:8fe23329500adc8d63944f6854d69d9358d7d27794267fc2aa41a371e6d20e80","target":"graph","created_at":"2026-08-04T01:56:08Z","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/2608.00969/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing search-augmented LLM agents are trained using Reinforcement Learning to boost its reasoning capabilities. However, these approaches primarily rely on outcome-level rewards, which provide little supervision over search behavior and overlook agent's ability to decompose complex queries properly. To mitigate this issue, we propose PROGRESS which utilizes teacher-guided coverage reward to explicitly shape decomposed query generation of the policy model. During training, frozen teacher models are used to decompose complex queries into essential search queries. These essential search querie","authors_text":"Aounon Kumar, Srinivas Chappidi, Sudipta Paul, Vijay Srinivasan, Vivek Kulkarni, Wenbo Li, Yashas Malur Saidutta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T03:48:41Z","title":"PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00969","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:c289c7701339464328a9703a0ee24a611c29350ca69e8bf1f7c86682c9c57558","target":"record","created_at":"2026-08-04T01:56:08Z","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":"86657bd4da940c93fc4e2e8727067219630fd97edc16bd1aed783ce35423ec27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T03:48:41Z","title_canon_sha256":"ac02abb641f04b4d1872aa7272b05cb211aa9ecbe15bd85a8ca5004f7981dbe9"},"schema_version":"1.0","source":{"id":"2608.00969","kind":"arxiv","version":1}},"canonical_sha256":"edf64987df9c14a72fd48e192ff10987d6c0863a8d8de8ca3cf8092890b265f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edf64987df9c14a72fd48e192ff10987d6c0863a8d8de8ca3cf8092890b265f5","first_computed_at":"2026-08-04T01:56:08.212821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:56:08.212821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t2mdE9j+CkG/j6/TbmoL2qqZNoCj4gxISFMLLiHnns3jC86hBKrYXXlGzjd+PZzWioILE8PMJ8c6kt1051P0Cw==","signature_status":"signed_v1","signed_at":"2026-08-04T01:56:08.214460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00969","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c289c7701339464328a9703a0ee24a611c29350ca69e8bf1f7c86682c9c57558","sha256:8fe23329500adc8d63944f6854d69d9358d7d27794267fc2aa41a371e6d20e80"],"state_sha256":"fb6fe4c1861792c7dbeb4b53ae8b1ba22824ed5883cf3f7911c61126327042de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GYZMfr29HhVyzpF0GN+PtH2fDEN8jJaw9gwWIKkkUL4W2Ie6Ly2uZkg/H/oQ6oCfKA5Pb2XlfyFgbcoPzEUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T07:45:25.623161Z","bundle_sha256":"b0cb8e19eefac8163d369efb27954f8f3a7a822c9de9c301c355ed44335f09fb"}}