{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TJFFPH6E5ZWVUNP5GFGIYILMZK","short_pith_number":"pith:TJFFPH6E","canonical_record":{"source":{"id":"2605.24071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:04:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54f703ea70efb681b966a1aedf2fd9a0b471496a3567dd7368b4a3ecaebb30bc","abstract_canon_sha256":"4dcb3862d82f9107d9dc905fefa27a35131425ad70de7240b3bce8ce012c7416"},"schema_version":"1.0"},"canonical_sha256":"9a4a579fc4ee6d5a35fd314c8c216ccaaeb654dc3082acf43dedad5d2f2e7419","source":{"kind":"arxiv","id":"2605.24071","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24071","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24071v1","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24071","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"pith_short_12","alias_value":"TJFFPH6E5ZWV","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"pith_short_16","alias_value":"TJFFPH6E5ZWVUNP5","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"pith_short_8","alias_value":"TJFFPH6E","created_at":"2026-05-26T01:02:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TJFFPH6E5ZWVUNP5GFGIYILMZK","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:04:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54f703ea70efb681b966a1aedf2fd9a0b471496a3567dd7368b4a3ecaebb30bc","abstract_canon_sha256":"4dcb3862d82f9107d9dc905fefa27a35131425ad70de7240b3bce8ce012c7416"},"schema_version":"1.0"},"canonical_sha256":"9a4a579fc4ee6d5a35fd314c8c216ccaaeb654dc3082acf43dedad5d2f2e7419","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:43.871245Z","signature_b64":"iesEoW2PPPALTmFJ0PRtbsT4cLyq0D+rFJQHD0wuHsx6Hq3erX+d+PN1E6v26YCnMM5TtZ8vDBy2c4XDY3KzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a4a579fc4ee6d5a35fd314c8c216ccaaeb654dc3082acf43dedad5d2f2e7419","last_reissued_at":"2026-05-26T01:02:43.870532Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:43.870532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24071","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":"2026-05-26T01:02:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9TxPrRP6rF3/o0UGAKiqi+5DFJIk6/c5stfY2HnbhC0V844MC345vqCfmr5/gu3cxYUfnoYRkrlvJhfnavWaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T15:47:06.044021Z"},"content_sha256":"a268268dfc5f950d02b6b19fec1d622edc6d6d04e91ba338ded650decd59a4ab","schema_version":"1.0","event_id":"sha256:a268268dfc5f950d02b6b19fec1d622edc6d6d04e91ba338ded650decd59a4ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TJFFPH6E5ZWVUNP5GFGIYILMZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Not All Transitions Matter: Evidence from PPO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ajhesh Basnet","submitted_at":"2026-05-22T12:04:40Z","abstract_excerpt":"Training a reinforcement learning agent on-policy means collecting fresh experience at every update, and that experience comes with a hidden problem. Each state in a rollout is the direct output of the previous one, causally chained together by the agent's own actions. Because of this, consecutive transitions are never truly independent. They carry overlapping information, and the gradient signal the network receives ends up far more repetitive than the batch size suggests. The same directions get reinforced over and over, the value network struggles to keep up as the policy shifts, and traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24071","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/2605.24071/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":"2026-05-26T01:02:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"34rVOuDaehXQgERwv5BhQmj/MtjF6plIQq/nxSk9jxXi+jduh4SoJhP05nPbPiCjQdtqEu6YpZhNZ4jcYcZpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T15:47:06.044429Z"},"content_sha256":"1243a74650d04ce5e2cc9e3d0d286c641a8d02aa32c22aa94ceb51dce28264c6","schema_version":"1.0","event_id":"sha256:1243a74650d04ce5e2cc9e3d0d286c641a8d02aa32c22aa94ceb51dce28264c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJFFPH6E5ZWVUNP5GFGIYILMZK/bundle.json","state_url":"https://pith.science/pith/TJFFPH6E5ZWVUNP5GFGIYILMZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJFFPH6E5ZWVUNP5GFGIYILMZK/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":"2026-07-03T15:47:06Z","links":{"resolver":"https://pith.science/pith/TJFFPH6E5ZWVUNP5GFGIYILMZK","bundle":"https://pith.science/pith/TJFFPH6E5ZWVUNP5GFGIYILMZK/bundle.json","state":"https://pith.science/pith/TJFFPH6E5ZWVUNP5GFGIYILMZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJFFPH6E5ZWVUNP5GFGIYILMZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TJFFPH6E5ZWVUNP5GFGIYILMZK","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":"4dcb3862d82f9107d9dc905fefa27a35131425ad70de7240b3bce8ce012c7416","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:04:40Z","title_canon_sha256":"54f703ea70efb681b966a1aedf2fd9a0b471496a3567dd7368b4a3ecaebb30bc"},"schema_version":"1.0","source":{"id":"2605.24071","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24071","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24071v1","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24071","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"pith_short_12","alias_value":"TJFFPH6E5ZWV","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"pith_short_16","alias_value":"TJFFPH6E5ZWVUNP5","created_at":"2026-05-26T01:02:43Z"},{"alias_kind":"pith_short_8","alias_value":"TJFFPH6E","created_at":"2026-05-26T01:02:43Z"}],"graph_snapshots":[{"event_id":"sha256:1243a74650d04ce5e2cc9e3d0d286c641a8d02aa32c22aa94ceb51dce28264c6","target":"graph","created_at":"2026-05-26T01:02:43Z","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/2605.24071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a reinforcement learning agent on-policy means collecting fresh experience at every update, and that experience comes with a hidden problem. Each state in a rollout is the direct output of the previous one, causally chained together by the agent's own actions. Because of this, consecutive transitions are never truly independent. They carry overlapping information, and the gradient signal the network receives ends up far more repetitive than the batch size suggests. The same directions get reinforced over and over, the value network struggles to keep up as the policy shifts, and traini","authors_text":"Ajhesh Basnet","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:04:40Z","title":"Not All Transitions Matter: Evidence from PPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24071","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:a268268dfc5f950d02b6b19fec1d622edc6d6d04e91ba338ded650decd59a4ab","target":"record","created_at":"2026-05-26T01:02:43Z","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":"4dcb3862d82f9107d9dc905fefa27a35131425ad70de7240b3bce8ce012c7416","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:04:40Z","title_canon_sha256":"54f703ea70efb681b966a1aedf2fd9a0b471496a3567dd7368b4a3ecaebb30bc"},"schema_version":"1.0","source":{"id":"2605.24071","kind":"arxiv","version":1}},"canonical_sha256":"9a4a579fc4ee6d5a35fd314c8c216ccaaeb654dc3082acf43dedad5d2f2e7419","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a4a579fc4ee6d5a35fd314c8c216ccaaeb654dc3082acf43dedad5d2f2e7419","first_computed_at":"2026-05-26T01:02:43.870532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:43.870532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iesEoW2PPPALTmFJ0PRtbsT4cLyq0D+rFJQHD0wuHsx6Hq3erX+d+PN1E6v26YCnMM5TtZ8vDBy2c4XDY3KzDg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:43.871245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24071","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a268268dfc5f950d02b6b19fec1d622edc6d6d04e91ba338ded650decd59a4ab","sha256:1243a74650d04ce5e2cc9e3d0d286c641a8d02aa32c22aa94ceb51dce28264c6"],"state_sha256":"e1556169541ddf0b02172aa13ff9cc49909c39b7c7b2632592883905c4d61a81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ll3q95tWY56fQ0ctB2jgGevwEUyUQYMhcJFeUOyufIsgmftlMUjE9ieRhiFtE56qZqOUXblZrCNoSKaCnKRFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T15:47:06.046427Z","bundle_sha256":"30e5b30f7c5e234d6031cfa3ffcee90e37d7010a0e30ebcb394d52df707ed54c"}}