{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PQ3K6FQURTRXNALCG36BXQ73IN","short_pith_number":"pith:PQ3K6FQU","canonical_record":{"source":{"id":"2504.02273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T04:46:17Z","cross_cats_sorted":[],"title_canon_sha256":"099778b486cc52a57993d5e7933e1d376601d9632063288890b74c7c4235334c","abstract_canon_sha256":"96c5fba4d9d06348a3ddcaf3f84e70d5030a9dd7a78d7f4295c469a8cdacf944"},"schema_version":"1.0"},"canonical_sha256":"7c36af16148ce376816236fc1bc3fb4362e82f5757fb4532bcc79cc5ec92a9d2","source":{"kind":"arxiv","id":"2504.02273","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02273","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02273v1","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02273","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"pith_short_12","alias_value":"PQ3K6FQURTRX","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"pith_short_16","alias_value":"PQ3K6FQURTRXNALC","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"pith_short_8","alias_value":"PQ3K6FQU","created_at":"2026-07-05T10:43:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PQ3K6FQURTRXNALCG36BXQ73IN","target":"record","payload":{"canonical_record":{"source":{"id":"2504.02273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T04:46:17Z","cross_cats_sorted":[],"title_canon_sha256":"099778b486cc52a57993d5e7933e1d376601d9632063288890b74c7c4235334c","abstract_canon_sha256":"96c5fba4d9d06348a3ddcaf3f84e70d5030a9dd7a78d7f4295c469a8cdacf944"},"schema_version":"1.0"},"canonical_sha256":"7c36af16148ce376816236fc1bc3fb4362e82f5757fb4532bcc79cc5ec92a9d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:53.989814Z","signature_b64":"MV5E576U5Poub+XnDnqQRwjOX13PpcKUdViMEThuUbUPnX7XkhsOTLFzDfg/mV+sNP/TQdU4XkCd7Vtp2mx6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c36af16148ce376816236fc1bc3fb4362e82f5757fb4532bcc79cc5ec92a9d2","last_reissued_at":"2026-07-05T10:43:53.989303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:53.989303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.02273","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":"2026-07-05T10:43:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FAUwBkysfzP9qNaAcahSdge0pPDcKbCJG/j5/o2f7kMo6rVrgxcYQtT7aKuYY58HPqVDl/GbEB07gHvPKwyHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:46:27.465515Z"},"content_sha256":"9c1760fc5d1ca16856424a0a66a4bb081df2e01aa3d0c3026138db1b9584e32f","schema_version":"1.0","event_id":"sha256:9c1760fc5d1ca16856424a0a66a4bb081df2e01aa3d0c3026138db1b9584e32f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PQ3K6FQURTRXNALCG36BXQ73IN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dai Do, Dung Nguyen, Hung Le, Svetha Venkatesh","submitted_at":"2025-04-03T04:46:17Z","abstract_excerpt":"Recent advances in fine-tuning large language models (LLMs) with reinforcement learning (RL) have shown promising improvements in complex reasoning tasks, particularly when paired with chain-of-thought (CoT) prompting. However, these successes have been largely demonstrated on large-scale models with billions of parameters, where a strong pretraining foundation ensures effective initial exploration. In contrast, RL remains challenging for tiny LLMs with 1 billion parameters or fewer because they lack the necessary pretraining strength to explore effectively, often leading to suboptimal reasoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02273","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/2504.02273/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":"2026-07-05T10:43:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LhvkwHhYeNTbiFzH3SY37cpOon2FuOaEwko7rCn5tMMbLc2oc7dKsKGuA5fFUdwltIdzYqzcd0CodLOFo6wBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:46:27.466015Z"},"content_sha256":"ad317c8bac89424ef9f9623af7efc2381156a6f557e18e0e790aeea15756b9ac","schema_version":"1.0","event_id":"sha256:ad317c8bac89424ef9f9623af7efc2381156a6f557e18e0e790aeea15756b9ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQ3K6FQURTRXNALCG36BXQ73IN/bundle.json","state_url":"https://pith.science/pith/PQ3K6FQURTRXNALCG36BXQ73IN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQ3K6FQURTRXNALCG36BXQ73IN/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":"2026-08-11T00:46:27Z","links":{"resolver":"https://pith.science/pith/PQ3K6FQURTRXNALCG36BXQ73IN","bundle":"https://pith.science/pith/PQ3K6FQURTRXNALCG36BXQ73IN/bundle.json","state":"https://pith.science/pith/PQ3K6FQURTRXNALCG36BXQ73IN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQ3K6FQURTRXNALCG36BXQ73IN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PQ3K6FQURTRXNALCG36BXQ73IN","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":"96c5fba4d9d06348a3ddcaf3f84e70d5030a9dd7a78d7f4295c469a8cdacf944","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T04:46:17Z","title_canon_sha256":"099778b486cc52a57993d5e7933e1d376601d9632063288890b74c7c4235334c"},"schema_version":"1.0","source":{"id":"2504.02273","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02273","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02273v1","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02273","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"pith_short_12","alias_value":"PQ3K6FQURTRX","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"pith_short_16","alias_value":"PQ3K6FQURTRXNALC","created_at":"2026-07-05T10:43:53Z"},{"alias_kind":"pith_short_8","alias_value":"PQ3K6FQU","created_at":"2026-07-05T10:43:53Z"}],"graph_snapshots":[{"event_id":"sha256:ad317c8bac89424ef9f9623af7efc2381156a6f557e18e0e790aeea15756b9ac","target":"graph","created_at":"2026-07-05T10:43:53Z","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/2504.02273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in fine-tuning large language models (LLMs) with reinforcement learning (RL) have shown promising improvements in complex reasoning tasks, particularly when paired with chain-of-thought (CoT) prompting. However, these successes have been largely demonstrated on large-scale models with billions of parameters, where a strong pretraining foundation ensures effective initial exploration. In contrast, RL remains challenging for tiny LLMs with 1 billion parameters or fewer because they lack the necessary pretraining strength to explore effectively, often leading to suboptimal reasoni","authors_text":"Dai Do, Dung Nguyen, Hung Le, Svetha Venkatesh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T04:46:17Z","title":"Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02273","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":"sha256:9c1760fc5d1ca16856424a0a66a4bb081df2e01aa3d0c3026138db1b9584e32f","target":"record","created_at":"2026-07-05T10:43:53Z","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":"96c5fba4d9d06348a3ddcaf3f84e70d5030a9dd7a78d7f4295c469a8cdacf944","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-03T04:46:17Z","title_canon_sha256":"099778b486cc52a57993d5e7933e1d376601d9632063288890b74c7c4235334c"},"schema_version":"1.0","source":{"id":"2504.02273","kind":"arxiv","version":1}},"canonical_sha256":"7c36af16148ce376816236fc1bc3fb4362e82f5757fb4532bcc79cc5ec92a9d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c36af16148ce376816236fc1bc3fb4362e82f5757fb4532bcc79cc5ec92a9d2","first_computed_at":"2026-07-05T10:43:53.989303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:53.989303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MV5E576U5Poub+XnDnqQRwjOX13PpcKUdViMEThuUbUPnX7XkhsOTLFzDfg/mV+sNP/TQdU4XkCd7Vtp2mx6Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:53.989814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02273","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c1760fc5d1ca16856424a0a66a4bb081df2e01aa3d0c3026138db1b9584e32f","sha256:ad317c8bac89424ef9f9623af7efc2381156a6f557e18e0e790aeea15756b9ac"],"state_sha256":"7fb5b95eebd3bf4bd837cf7704bc2725627afe249b7ff4fe5201b187c38d8e8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSDPBXjycC7xvjlM2kx44/dIBP7SQpePwCEKQt7iBz0gE9sU3iuIbxMU45SbQiri2gHRADuZukx3XogsOXvjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:46:27.470175Z","bundle_sha256":"d731a93bc2ee27802b78f08b8692f154aa5c2ad986249d007de8b9a0038974ba"}}