{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TP2ZU43W577MTTMTIFTEOAO7ZP","short_pith_number":"pith:TP2ZU43W","schema_version":"1.0","canonical_sha256":"9bf59a7376effec9cd9341664701dfcbda01ad0f274ea05324f5b43e2e4e8c2f","source":{"kind":"arxiv","id":"2504.14597","version":1},"attestation_state":"computed","paper":{"title":"a1: Steep Test-time Scaling Law via Environment Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baolong Bi, Jun Wan, Lingrui Mei, Shenghua Liu, Xueqi Cheng, Yiwei Wang, Yurong Wu, Yuyao Ge","submitted_at":"2025-04-20T12:55:59Z","abstract_excerpt":"Large Language Models (LLMs) have made remarkable breakthroughs in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during complex multi-step tasks. Current approaches like chain-of-thought prompting offer limited reasoning capabilities that fail when precise step validation is required. We propose Environment Augmented Generation (EAG), a framework that enhances LLM reasoning through: (1) real-time environmental feedback validating each reasoning step, (2) dynamic branch exploration for investigating alternative solution paths when faced w"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.14597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-20T12:55:59Z","cross_cats_sorted":[],"title_canon_sha256":"dae28d40ee37abc74ec7061f8c15f8ebd3cf6d4b9d4dd4104aae4df6d3ba451f","abstract_canon_sha256":"6e8ed8d2be5178b49e3f993ccfedbf4084618857064b3225aeb670162c223db1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:46.927877Z","signature_b64":"RhwV6RVbXUbvRs9+K+jtBHboQkBiVj8N0kIOCuNC7huRNr7nsQM80MQ7uMGXO7kHcZkpTrCfz04SXgc7zU+NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bf59a7376effec9cd9341664701dfcbda01ad0f274ea05324f5b43e2e4e8c2f","last_reissued_at":"2026-07-05T10:51:46.927340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:46.927340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"a1: Steep Test-time Scaling Law via Environment Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baolong Bi, Jun Wan, Lingrui Mei, Shenghua Liu, Xueqi Cheng, Yiwei Wang, Yurong Wu, Yuyao Ge","submitted_at":"2025-04-20T12:55:59Z","abstract_excerpt":"Large Language Models (LLMs) have made remarkable breakthroughs in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during complex multi-step tasks. Current approaches like chain-of-thought prompting offer limited reasoning capabilities that fail when precise step validation is required. We propose Environment Augmented Generation (EAG), a framework that enhances LLM reasoning through: (1) real-time environmental feedback validating each reasoning step, (2) dynamic branch exploration for investigating alternative solution paths when faced w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14597","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/2504.14597/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.14597","created_at":"2026-07-05T10:51:46.927405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14597v1","created_at":"2026-07-05T10:51:46.927405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14597","created_at":"2026-07-05T10:51:46.927405+00:00"},{"alias_kind":"pith_short_12","alias_value":"TP2ZU43W577M","created_at":"2026-07-05T10:51:46.927405+00:00"},{"alias_kind":"pith_short_16","alias_value":"TP2ZU43W577MTTMT","created_at":"2026-07-05T10:51:46.927405+00:00"},{"alias_kind":"pith_short_8","alias_value":"TP2ZU43W","created_at":"2026-07-05T10:51:46.927405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.00181","citing_title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05418","citing_title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TP2ZU43W577MTTMTIFTEOAO7ZP","json":"https://pith.science/pith/TP2ZU43W577MTTMTIFTEOAO7ZP.json","graph_json":"https://pith.science/api/pith-number/TP2ZU43W577MTTMTIFTEOAO7ZP/graph.json","events_json":"https://pith.science/api/pith-number/TP2ZU43W577MTTMTIFTEOAO7ZP/events.json","paper":"https://pith.science/paper/TP2ZU43W"},"agent_actions":{"view_html":"https://pith.science/pith/TP2ZU43W577MTTMTIFTEOAO7ZP","download_json":"https://pith.science/pith/TP2ZU43W577MTTMTIFTEOAO7ZP.json","view_paper":"https://pith.science/paper/TP2ZU43W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14597&json=true","fetch_graph":"https://pith.science/api/pith-number/TP2ZU43W577MTTMTIFTEOAO7ZP/graph.json","fetch_events":"https://pith.science/api/pith-number/TP2ZU43W577MTTMTIFTEOAO7ZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TP2ZU43W577MTTMTIFTEOAO7ZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TP2ZU43W577MTTMTIFTEOAO7ZP/action/storage_attestation","attest_author":"https://pith.science/pith/TP2ZU43W577MTTMTIFTEOAO7ZP/action/author_attestation","sign_citation":"https://pith.science/pith/TP2ZU43W577MTTMTIFTEOAO7ZP/action/citation_signature","submit_replication":"https://pith.science/pith/TP2ZU43W577MTTMTIFTEOAO7ZP/action/replication_record"}},"created_at":"2026-07-05T10:51:46.927405+00:00","updated_at":"2026-07-05T10:51:46.927405+00:00"}