{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6UPARSE23RA6KURLSHNKU2S7LB","short_pith_number":"pith:6UPARSE2","canonical_record":{"source":{"id":"2505.20732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T05:21:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd0a571591063ba727b55b6a537d533010c9b9f9c8b89384524ad6954349edca","abstract_canon_sha256":"66624f54845599cf7d24dee28c280139de567973755ae93120d41a145787d69c"},"schema_version":"1.0"},"canonical_sha256":"f51e08c89adc41e5522b91daaa6a5f5861d2d79c15aa009f3680b76ba3ca8611","source":{"kind":"arxiv","id":"2505.20732","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20732","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20732v1","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20732","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"6UPARSE23RA6","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"6UPARSE23RA6KURL","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"6UPARSE2","created_at":"2026-07-05T11:10:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6UPARSE23RA6KURLSHNKU2S7LB","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T05:21:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd0a571591063ba727b55b6a537d533010c9b9f9c8b89384524ad6954349edca","abstract_canon_sha256":"66624f54845599cf7d24dee28c280139de567973755ae93120d41a145787d69c"},"schema_version":"1.0"},"canonical_sha256":"f51e08c89adc41e5522b91daaa6a5f5861d2d79c15aa009f3680b76ba3ca8611","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:17.657446Z","signature_b64":"D0xotvFEYuKlgKA3zxG3J1TE9hygUDvXdd9/5SJpWhdXHv++TGocIIGsfGZnQPfskYBrIjBr2ZoefVgH8GGnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f51e08c89adc41e5522b91daaa6a5f5861d2d79c15aa009f3680b76ba3ca8611","last_reissued_at":"2026-07-05T11:10:17.657022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:17.657022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20732","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":"2026-07-05T11:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hneQOnPa0iCOxLljSolIqvRUfx82txKSux2fXgOGfSoEfzxsytDspY8dnFHRflCGeHTAPkR0Vbao/uaC6XxBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:24:54.618913Z"},"content_sha256":"0fae96afc9d03fdfb614e1878b0a2ef867e7f509e2072443024fc82a37637e94","schema_version":"1.0","event_id":"sha256:0fae96afc9d03fdfb614e1878b0a2ef867e7f509e2072443024fc82a37637e94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6UPARSE23RA6KURLSHNKU2S7LB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chak Tou Leong, Hanlin Wang, Jian Wang, Jiashuo Wang, Wenjie Li","submitted_at":"2025-05-27T05:21:04Z","abstract_excerpt":"Reinforcement learning (RL) holds significant promise for training LLM agents to handle complex, goal-oriented tasks that require multi-step interactions with external environments. However, a critical challenge when applying RL to these agentic tasks arises from delayed rewards: feedback signals are typically available only after the entire task is completed. This makes it non-trivial to assign delayed rewards to earlier actions, providing insufficient guidance regarding environmental constraints and hindering agent training. In this work, we draw on the insight that the ultimate completion o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20732","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/2505.20732/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":"2026-07-05T11:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BB/tPzeaQVhmXYqIb8tnN5G1TQXCsMOSjGMEeQocUf/CgquKYQzuSc9mBDbGwyEIuQ9qjPE6p57Ph6jR+IcXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:24:54.619274Z"},"content_sha256":"f6d833a9221dda373e6e8327396023d63f9e62d130543e626e94d319dbeef495","schema_version":"1.0","event_id":"sha256:f6d833a9221dda373e6e8327396023d63f9e62d130543e626e94d319dbeef495"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6UPARSE23RA6KURLSHNKU2S7LB/bundle.json","state_url":"https://pith.science/pith/6UPARSE23RA6KURLSHNKU2S7LB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6UPARSE23RA6KURLSHNKU2S7LB/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":"2026-07-06T20:24:54Z","links":{"resolver":"https://pith.science/pith/6UPARSE23RA6KURLSHNKU2S7LB","bundle":"https://pith.science/pith/6UPARSE23RA6KURLSHNKU2S7LB/bundle.json","state":"https://pith.science/pith/6UPARSE23RA6KURLSHNKU2S7LB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6UPARSE23RA6KURLSHNKU2S7LB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6UPARSE23RA6KURLSHNKU2S7LB","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":"66624f54845599cf7d24dee28c280139de567973755ae93120d41a145787d69c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T05:21:04Z","title_canon_sha256":"dd0a571591063ba727b55b6a537d533010c9b9f9c8b89384524ad6954349edca"},"schema_version":"1.0","source":{"id":"2505.20732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20732","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20732v1","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20732","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"6UPARSE23RA6","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"6UPARSE23RA6KURL","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"6UPARSE2","created_at":"2026-07-05T11:10:17Z"}],"graph_snapshots":[{"event_id":"sha256:f6d833a9221dda373e6e8327396023d63f9e62d130543e626e94d319dbeef495","target":"graph","created_at":"2026-07-05T11:10:17Z","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/2505.20732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) holds significant promise for training LLM agents to handle complex, goal-oriented tasks that require multi-step interactions with external environments. However, a critical challenge when applying RL to these agentic tasks arises from delayed rewards: feedback signals are typically available only after the entire task is completed. This makes it non-trivial to assign delayed rewards to earlier actions, providing insufficient guidance regarding environmental constraints and hindering agent training. In this work, we draw on the insight that the ultimate completion o","authors_text":"Chak Tou Leong, Hanlin Wang, Jian Wang, Jiashuo Wang, Wenjie Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T05:21:04Z","title":"SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20732","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":"sha256:0fae96afc9d03fdfb614e1878b0a2ef867e7f509e2072443024fc82a37637e94","target":"record","created_at":"2026-07-05T11:10:17Z","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":"66624f54845599cf7d24dee28c280139de567973755ae93120d41a145787d69c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T05:21:04Z","title_canon_sha256":"dd0a571591063ba727b55b6a537d533010c9b9f9c8b89384524ad6954349edca"},"schema_version":"1.0","source":{"id":"2505.20732","kind":"arxiv","version":1}},"canonical_sha256":"f51e08c89adc41e5522b91daaa6a5f5861d2d79c15aa009f3680b76ba3ca8611","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f51e08c89adc41e5522b91daaa6a5f5861d2d79c15aa009f3680b76ba3ca8611","first_computed_at":"2026-07-05T11:10:17.657022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:17.657022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D0xotvFEYuKlgKA3zxG3J1TE9hygUDvXdd9/5SJpWhdXHv++TGocIIGsfGZnQPfskYBrIjBr2ZoefVgH8GGnCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:17.657446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fae96afc9d03fdfb614e1878b0a2ef867e7f509e2072443024fc82a37637e94","sha256:f6d833a9221dda373e6e8327396023d63f9e62d130543e626e94d319dbeef495"],"state_sha256":"c69144ca847bf4d39462dfa030b27c78b9eb727bbcefb452857555363992ffbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iCUIrrb0EvtydlsTWK6WNy0YXDlPl2aD63U8uaVO0Z+uLVPj0XDuzSWWwus0Hl5J6OZr2nnwgtLm44zAsgCRDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:24:54.621268Z","bundle_sha256":"4bebf0b84f1ce72404124fe026d0c4e417ec509b8f9ce097f2b85518a82b0938"}}