{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VKBP3EXKV3FEZ3IUOJPQVAPFYL","short_pith_number":"pith:VKBP3EXK","canonical_record":{"source":{"id":"2607.18597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T00:17:55Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"c0a98b2e452d0be2386d4036e81071b69c03ed1c77ea252215e2ac7a7a4418cf","abstract_canon_sha256":"aef1f93dd9fba4ed6801bd52ab0e1e24f4c32dcce940aaca9d86dea66187fe62"},"schema_version":"1.0"},"canonical_sha256":"aa82fd92eaaeca4ced14725f0a81e5c2ed218c4f2cc83e318614b26030763899","source":{"kind":"arxiv","id":"2607.18597","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18597","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18597v1","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18597","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"pith_short_12","alias_value":"VKBP3EXKV3FE","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"pith_short_16","alias_value":"VKBP3EXKV3FEZ3IU","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"pith_short_8","alias_value":"VKBP3EXK","created_at":"2026-07-22T00:22:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VKBP3EXKV3FEZ3IUOJPQVAPFYL","target":"record","payload":{"canonical_record":{"source":{"id":"2607.18597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T00:17:55Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"c0a98b2e452d0be2386d4036e81071b69c03ed1c77ea252215e2ac7a7a4418cf","abstract_canon_sha256":"aef1f93dd9fba4ed6801bd52ab0e1e24f4c32dcce940aaca9d86dea66187fe62"},"schema_version":"1.0"},"canonical_sha256":"aa82fd92eaaeca4ced14725f0a81e5c2ed218c4f2cc83e318614b26030763899","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:55.988201Z","signature_b64":"smWfuGRLpURcL1x6Q0EXAlRTX1nA1H91WCswDya5AiE3TuLmqtFP7R0sMiNOGl6Txgpel2rZiST9aBDTKYtMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa82fd92eaaeca4ced14725f0a81e5c2ed218c4f2cc83e318614b26030763899","last_reissued_at":"2026-07-22T00:22:55.987465Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:55.987465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.18597","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":"2026-07-22T00:22:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GWXE+tlTx1HWUh+oKFn1qo09jviAgs2eOCzhS0UtyppOBKcz2JCKGZ7UkJSV6OLrv/4V28OJaldrJzFK5btnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:47:14.711983Z"},"content_sha256":"8104cf1a86a5f0233ac27ad40d3821a6e49ddc14331601b5c23b97bef2ed6347","schema_version":"1.0","event_id":"sha256:8104cf1a86a5f0233ac27ad40d3821a6e49ddc14331601b5c23b97bef2ed6347"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VKBP3EXKV3FEZ3IUOJPQVAPFYL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Self-Evolving Default Action for Cooperative Tasks with Continuous Action Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Shuangyao Huang","submitted_at":"2026-07-21T00:17:55Z","abstract_excerpt":"Counterfactual credit assignment has proven effective in multi-agent reinforcement learning (MARL) for discrete action spaces, yet its extension to continuous-action cooperative tasks remains challenging. Existing methods that approximate the counterfactual baseline via Monte Carlo sampling often introduce bias into policy gradients and fail to guarantee convergence to local optima, as the sampled actions may not have been sufficiently trained. To address these limitations, we propose SAFE, a novel MARL framework that employs a counterfactual baseline conditioned on a self-evolving default act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18597","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/2607.18597/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":"2026-07-22T00:22:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zdPo1s/tFtJ099wa4sI+DFKPrWZLPVCpnQ8d201/xAv76804zeSvZxGMljkY5Z11lVqaazexpNA6m7NbQvqVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:47:14.712541Z"},"content_sha256":"6124fcdb71231715c8cb8f8e132793ce73cd70c462187ff3f3fc854b7713a363","schema_version":"1.0","event_id":"sha256:6124fcdb71231715c8cb8f8e132793ce73cd70c462187ff3f3fc854b7713a363"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VKBP3EXKV3FEZ3IUOJPQVAPFYL/bundle.json","state_url":"https://pith.science/pith/VKBP3EXKV3FEZ3IUOJPQVAPFYL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VKBP3EXKV3FEZ3IUOJPQVAPFYL/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":"2026-08-05T01:47:14Z","links":{"resolver":"https://pith.science/pith/VKBP3EXKV3FEZ3IUOJPQVAPFYL","bundle":"https://pith.science/pith/VKBP3EXKV3FEZ3IUOJPQVAPFYL/bundle.json","state":"https://pith.science/pith/VKBP3EXKV3FEZ3IUOJPQVAPFYL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VKBP3EXKV3FEZ3IUOJPQVAPFYL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VKBP3EXKV3FEZ3IUOJPQVAPFYL","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":"aef1f93dd9fba4ed6801bd52ab0e1e24f4c32dcce940aaca9d86dea66187fe62","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T00:17:55Z","title_canon_sha256":"c0a98b2e452d0be2386d4036e81071b69c03ed1c77ea252215e2ac7a7a4418cf"},"schema_version":"1.0","source":{"id":"2607.18597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18597","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18597v1","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18597","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"pith_short_12","alias_value":"VKBP3EXKV3FE","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"pith_short_16","alias_value":"VKBP3EXKV3FEZ3IU","created_at":"2026-07-22T00:22:55Z"},{"alias_kind":"pith_short_8","alias_value":"VKBP3EXK","created_at":"2026-07-22T00:22:55Z"}],"graph_snapshots":[{"event_id":"sha256:6124fcdb71231715c8cb8f8e132793ce73cd70c462187ff3f3fc854b7713a363","target":"graph","created_at":"2026-07-22T00:22:55Z","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/2607.18597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual credit assignment has proven effective in multi-agent reinforcement learning (MARL) for discrete action spaces, yet its extension to continuous-action cooperative tasks remains challenging. Existing methods that approximate the counterfactual baseline via Monte Carlo sampling often introduce bias into policy gradients and fail to guarantee convergence to local optima, as the sampled actions may not have been sufficiently trained. To address these limitations, we propose SAFE, a novel MARL framework that employs a counterfactual baseline conditioned on a self-evolving default act","authors_text":"Shuangyao Huang","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T00:17:55Z","title":"A Self-Evolving Default Action for Cooperative Tasks with Continuous Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18597","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":"sha256:8104cf1a86a5f0233ac27ad40d3821a6e49ddc14331601b5c23b97bef2ed6347","target":"record","created_at":"2026-07-22T00:22:55Z","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":"aef1f93dd9fba4ed6801bd52ab0e1e24f4c32dcce940aaca9d86dea66187fe62","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T00:17:55Z","title_canon_sha256":"c0a98b2e452d0be2386d4036e81071b69c03ed1c77ea252215e2ac7a7a4418cf"},"schema_version":"1.0","source":{"id":"2607.18597","kind":"arxiv","version":1}},"canonical_sha256":"aa82fd92eaaeca4ced14725f0a81e5c2ed218c4f2cc83e318614b26030763899","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa82fd92eaaeca4ced14725f0a81e5c2ed218c4f2cc83e318614b26030763899","first_computed_at":"2026-07-22T00:22:55.987465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:55.987465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"smWfuGRLpURcL1x6Q0EXAlRTX1nA1H91WCswDya5AiE3TuLmqtFP7R0sMiNOGl6Txgpel2rZiST9aBDTKYtMCg==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:55.988201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8104cf1a86a5f0233ac27ad40d3821a6e49ddc14331601b5c23b97bef2ed6347","sha256:6124fcdb71231715c8cb8f8e132793ce73cd70c462187ff3f3fc854b7713a363"],"state_sha256":"ba95c17c804700245a2bf5b91b7a57769730ec2d74ae52cfde14b521f39f5c3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G3iclMLobyPLn1SeFKF+YNYtzlfCPNNUS7Olk6qotMZmhsEMVVfGupR8Eyu8Q47YdfZ/E+puCQsD0pnk53giBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:47:14.716749Z","bundle_sha256":"0f0e5f56c83618e72ed89a7482b2c77747d4ed364c587d933ea094f8a5d9f4d6"}}