{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6B5CUK32SJQA2OQSLAVFBPORD5","short_pith_number":"pith:6B5CUK32","canonical_record":{"source":{"id":"2409.12798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-19T14:08:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a213838291e626139f840924088dca152e96219d42adb81292d42d871564ad3","abstract_canon_sha256":"233ad535a54145fc280da1a7e0f2af81cf3bddef28fd27c16709099ae6c94dd3"},"schema_version":"1.0"},"canonical_sha256":"f07a2a2b7a92600d3a12582a50bdd11f6bf4bdbe51c09c1ed27d3e4750457cd0","source":{"kind":"arxiv","id":"2409.12798","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12798","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12798v1","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12798","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"6B5CUK32SJQA","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"6B5CUK32SJQA2OQS","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"6B5CUK32","created_at":"2026-07-05T09:09:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6B5CUK32SJQA2OQSLAVFBPORD5","target":"record","payload":{"canonical_record":{"source":{"id":"2409.12798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-19T14:08:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a213838291e626139f840924088dca152e96219d42adb81292d42d871564ad3","abstract_canon_sha256":"233ad535a54145fc280da1a7e0f2af81cf3bddef28fd27c16709099ae6c94dd3"},"schema_version":"1.0"},"canonical_sha256":"f07a2a2b7a92600d3a12582a50bdd11f6bf4bdbe51c09c1ed27d3e4750457cd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:12.319023Z","signature_b64":"GC2q8919tI8EOsUR4nU7fvsbIs62rhjWwAgGWpvHS9m24fu89VgaAtItWZ/M+gj69nCvF6xJtiNW9eFHAlgpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f07a2a2b7a92600d3a12582a50bdd11f6bf4bdbe51c09c1ed27d3e4750457cd0","last_reissued_at":"2026-07-05T09:09:12.318538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:12.318538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.12798","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":"2026-07-05T09:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dEhy2pxRJvxrl0DNMwL6eCA9QuSjHiUvYbCRZwkftt7bp1zRK+oOXCwPnLTLAQS9RGCv3Fa+yE949nUH8+GLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:42:53.604570Z"},"content_sha256":"a23cd2b5c2087c25cb0ee35b928b46bac67b9f2188cf5894937cfb9eeb1a7266","schema_version":"1.0","event_id":"sha256:a23cd2b5c2087c25cb0ee35b928b46bac67b9f2188cf5894937cfb9eeb1a7266"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6B5CUK32SJQA2OQSLAVFBPORD5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Davide Paglieri, Eduardo Pignatelli, Edward Grefenstette, Johan Ferret, Laura Toni, Samuel Coward, Tim Rock\\\"aschel","submitted_at":"2024-09-19T14:08:09Z","abstract_excerpt":"The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory for their ability to achieve a goal. However, when feedback is delayed and sparse, the learning signal is poor, and action evaluation becomes harder. Canonical solutions, such as reward shaping and options, require extensive domain knowledge and manual intervention, limiting their scalability and applicability. In this work, we lay the foundations for Credit Assignment with Language Models (CALM), a novel approach tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12798","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/2409.12798/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":"2026-07-05T09:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"irnN2sqCZfGTmRAzfGP9F5YbO0lRnuCkFQfioJlycxWjh+doFfbC2LNzVrfGZLPZCsSuBQ2F2jIDb7eMfSuKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:42:53.605082Z"},"content_sha256":"c0b7a26bed576e6866c639c06c22e74a8fc2e9f41ff6c23565869a356e226df1","schema_version":"1.0","event_id":"sha256:c0b7a26bed576e6866c639c06c22e74a8fc2e9f41ff6c23565869a356e226df1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6B5CUK32SJQA2OQSLAVFBPORD5/bundle.json","state_url":"https://pith.science/pith/6B5CUK32SJQA2OQSLAVFBPORD5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6B5CUK32SJQA2OQSLAVFBPORD5/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":"2026-08-01T09:42:53Z","links":{"resolver":"https://pith.science/pith/6B5CUK32SJQA2OQSLAVFBPORD5","bundle":"https://pith.science/pith/6B5CUK32SJQA2OQSLAVFBPORD5/bundle.json","state":"https://pith.science/pith/6B5CUK32SJQA2OQSLAVFBPORD5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6B5CUK32SJQA2OQSLAVFBPORD5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6B5CUK32SJQA2OQSLAVFBPORD5","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":"233ad535a54145fc280da1a7e0f2af81cf3bddef28fd27c16709099ae6c94dd3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-19T14:08:09Z","title_canon_sha256":"5a213838291e626139f840924088dca152e96219d42adb81292d42d871564ad3"},"schema_version":"1.0","source":{"id":"2409.12798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12798","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12798v1","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12798","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"6B5CUK32SJQA","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"6B5CUK32SJQA2OQS","created_at":"2026-07-05T09:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"6B5CUK32","created_at":"2026-07-05T09:09:12Z"}],"graph_snapshots":[{"event_id":"sha256:c0b7a26bed576e6866c639c06c22e74a8fc2e9f41ff6c23565869a356e226df1","target":"graph","created_at":"2026-07-05T09:09:12Z","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/2409.12798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory for their ability to achieve a goal. However, when feedback is delayed and sparse, the learning signal is poor, and action evaluation becomes harder. Canonical solutions, such as reward shaping and options, require extensive domain knowledge and manual intervention, limiting their scalability and applicability. In this work, we lay the foundations for Credit Assignment with Language Models (CALM), a novel approach tha","authors_text":"Davide Paglieri, Eduardo Pignatelli, Edward Grefenstette, Johan Ferret, Laura Toni, Samuel Coward, Tim Rock\\\"aschel","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-19T14:08:09Z","title":"Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12798","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:a23cd2b5c2087c25cb0ee35b928b46bac67b9f2188cf5894937cfb9eeb1a7266","target":"record","created_at":"2026-07-05T09:09:12Z","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":"233ad535a54145fc280da1a7e0f2af81cf3bddef28fd27c16709099ae6c94dd3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-19T14:08:09Z","title_canon_sha256":"5a213838291e626139f840924088dca152e96219d42adb81292d42d871564ad3"},"schema_version":"1.0","source":{"id":"2409.12798","kind":"arxiv","version":1}},"canonical_sha256":"f07a2a2b7a92600d3a12582a50bdd11f6bf4bdbe51c09c1ed27d3e4750457cd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f07a2a2b7a92600d3a12582a50bdd11f6bf4bdbe51c09c1ed27d3e4750457cd0","first_computed_at":"2026-07-05T09:09:12.318538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:12.318538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GC2q8919tI8EOsUR4nU7fvsbIs62rhjWwAgGWpvHS9m24fu89VgaAtItWZ/M+gj69nCvF6xJtiNW9eFHAlgpBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:12.319023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a23cd2b5c2087c25cb0ee35b928b46bac67b9f2188cf5894937cfb9eeb1a7266","sha256:c0b7a26bed576e6866c639c06c22e74a8fc2e9f41ff6c23565869a356e226df1"],"state_sha256":"bfc05d234c44e1203e612742c42c3fbecdc3b54e0e68274bb97827219ad71627"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L+lGUVLXyiDCZJGdo3rr+4veMYCSMLtWf7IK14N4PrKik8F3MAGsqFwEvvaj5JcYXzufavecra5qeeyrbpcvCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T09:42:53.608109Z","bundle_sha256":"c5a3d3dbcfca14110e2769e451642e59cb982fb6646e961a4025a88f68e670f3"}}