{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:N6YXBJB7LGGFOM3CLBIEDJHKLG","short_pith_number":"pith:N6YXBJB7","canonical_record":{"source":{"id":"2605.23562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-22T12:29:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b836a86ed6537d5ab3dd75d59036262c28bd41cf80eaec15f0b626d45156a58e","abstract_canon_sha256":"f319db0d7cbb6a058e5df2f1f7157d2fd0630c0a6eb6d0143bf2943c8e5ef1c2"},"schema_version":"1.0"},"canonical_sha256":"6fb170a43f598c573362585041a4ea59988c632cec84b165b8a5ca32434ecde3","source":{"kind":"arxiv","id":"2605.23562","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23562","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23562v1","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23562","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"pith_short_12","alias_value":"N6YXBJB7LGGF","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"pith_short_16","alias_value":"N6YXBJB7LGGFOM3C","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"pith_short_8","alias_value":"N6YXBJB7","created_at":"2026-05-25T02:02:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:N6YXBJB7LGGFOM3CLBIEDJHKLG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-22T12:29:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b836a86ed6537d5ab3dd75d59036262c28bd41cf80eaec15f0b626d45156a58e","abstract_canon_sha256":"f319db0d7cbb6a058e5df2f1f7157d2fd0630c0a6eb6d0143bf2943c8e5ef1c2"},"schema_version":"1.0"},"canonical_sha256":"6fb170a43f598c573362585041a4ea59988c632cec84b165b8a5ca32434ecde3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:19.606340Z","signature_b64":"WHWpBFyj2iml9BMPKan2I29NnNxBoi24+6VUqXeCQ+OPMRD5M/PFypB6RfaSWZh7EKfFoowEbA/zeRvDinYYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fb170a43f598c573362585041a4ea59988c632cec84b165b8a5ca32434ecde3","last_reissued_at":"2026-05-25T02:02:19.605551Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:19.605551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23562","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":"2026-05-25T02:02:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvQOZCNQBpuoxvTX96LsUOgyIbfDRoFnrUDUZqdqKwD0b1Gu83uTMxM7GJ6t0utbqNLzYgwbnr/nm7PethxWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:00:23.271485Z"},"content_sha256":"76ffc4ccd789f6182f2caf16448a9ff8ec6d87a852cb94456ef14a2f4ca05f9d","schema_version":"1.0","event_id":"sha256:76ffc4ccd789f6182f2caf16448a9ff8ec6d87a852cb94456ef14a2f4ca05f9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:N6YXBJB7LGGFOM3CLBIEDJHKLG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Elie Abboud, Oren Gal","submitted_at":"2026-05-22T12:29:29Z","abstract_excerpt":"Sparse rewards are a major bottleneck in multi-agent reinforcement learning (MARL), where simultaneous learning induces non-stationarity and makes reward design especially delicate. Reward shaping can accelerate learning, but in the multi-agent setting it must preserve the strategic structure of the problem rather than merely improve short-term optimization. We propose Automatic Reward-shaping in Multi-agent Systems (ARMS), a self-supervised reward shaping framework for MARL that learns dense shaping signals from sparse environmental rewards through trajectory ranking. Since single-agent traje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23562","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/2605.23562/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":"2026-05-25T02:02:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WhAfkyprqL7rJMZz5LUN6j3o56CzPYtqZrLkoEj18Kzd4PgCU+lomqXhydIjQVoaJ8/I8edbOYPrelkekcjqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:00:23.272213Z"},"content_sha256":"9a7a13a5db1d25e9cf9011b90c18a8bea0d3ab9610c68b6a4764e3010d82dabd","schema_version":"1.0","event_id":"sha256:9a7a13a5db1d25e9cf9011b90c18a8bea0d3ab9610c68b6a4764e3010d82dabd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N6YXBJB7LGGFOM3CLBIEDJHKLG/bundle.json","state_url":"https://pith.science/pith/N6YXBJB7LGGFOM3CLBIEDJHKLG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N6YXBJB7LGGFOM3CLBIEDJHKLG/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":"2026-06-10T12:00:23Z","links":{"resolver":"https://pith.science/pith/N6YXBJB7LGGFOM3CLBIEDJHKLG","bundle":"https://pith.science/pith/N6YXBJB7LGGFOM3CLBIEDJHKLG/bundle.json","state":"https://pith.science/pith/N6YXBJB7LGGFOM3CLBIEDJHKLG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N6YXBJB7LGGFOM3CLBIEDJHKLG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N6YXBJB7LGGFOM3CLBIEDJHKLG","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":"f319db0d7cbb6a058e5df2f1f7157d2fd0630c0a6eb6d0143bf2943c8e5ef1c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-22T12:29:29Z","title_canon_sha256":"b836a86ed6537d5ab3dd75d59036262c28bd41cf80eaec15f0b626d45156a58e"},"schema_version":"1.0","source":{"id":"2605.23562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23562","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23562v1","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23562","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"pith_short_12","alias_value":"N6YXBJB7LGGF","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"pith_short_16","alias_value":"N6YXBJB7LGGFOM3C","created_at":"2026-05-25T02:02:19Z"},{"alias_kind":"pith_short_8","alias_value":"N6YXBJB7","created_at":"2026-05-25T02:02:19Z"}],"graph_snapshots":[{"event_id":"sha256:9a7a13a5db1d25e9cf9011b90c18a8bea0d3ab9610c68b6a4764e3010d82dabd","target":"graph","created_at":"2026-05-25T02:02:19Z","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/2605.23562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse rewards are a major bottleneck in multi-agent reinforcement learning (MARL), where simultaneous learning induces non-stationarity and makes reward design especially delicate. Reward shaping can accelerate learning, but in the multi-agent setting it must preserve the strategic structure of the problem rather than merely improve short-term optimization. We propose Automatic Reward-shaping in Multi-agent Systems (ARMS), a self-supervised reward shaping framework for MARL that learns dense shaping signals from sparse environmental rewards through trajectory ranking. Since single-agent traje","authors_text":"Elie Abboud, Oren Gal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-22T12:29:29Z","title":"ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23562","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":"sha256:76ffc4ccd789f6182f2caf16448a9ff8ec6d87a852cb94456ef14a2f4ca05f9d","target":"record","created_at":"2026-05-25T02:02:19Z","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":"f319db0d7cbb6a058e5df2f1f7157d2fd0630c0a6eb6d0143bf2943c8e5ef1c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-22T12:29:29Z","title_canon_sha256":"b836a86ed6537d5ab3dd75d59036262c28bd41cf80eaec15f0b626d45156a58e"},"schema_version":"1.0","source":{"id":"2605.23562","kind":"arxiv","version":1}},"canonical_sha256":"6fb170a43f598c573362585041a4ea59988c632cec84b165b8a5ca32434ecde3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fb170a43f598c573362585041a4ea59988c632cec84b165b8a5ca32434ecde3","first_computed_at":"2026-05-25T02:02:19.605551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:19.605551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WHWpBFyj2iml9BMPKan2I29NnNxBoi24+6VUqXeCQ+OPMRD5M/PFypB6RfaSWZh7EKfFoowEbA/zeRvDinYYDg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:19.606340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76ffc4ccd789f6182f2caf16448a9ff8ec6d87a852cb94456ef14a2f4ca05f9d","sha256:9a7a13a5db1d25e9cf9011b90c18a8bea0d3ab9610c68b6a4764e3010d82dabd"],"state_sha256":"28e57356d2117ccf3b340282b4502b06a41ab360db9567b0ece2ba389ba0eb04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zpcnXPayciPUY4URRyG+LF2Q4vzE7MmOY1vv4u+dGcyU4FpZkDOaCmpikhzFX4VY1nXqr9sSUJ4fcQcFSkV6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T12:00:23.276429Z","bundle_sha256":"3553b08e6789d6dff3bb9d9cfb4de401934437fa0ce0dd693c564deed086601b"}}