{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AV4FU57V3JX7RN7JKWZEVTWYOZ","short_pith_number":"pith:AV4FU57V","schema_version":"1.0","canonical_sha256":"05785a77f5da6ff8b7e955b24aced87649550506e8c3f530c65a43511978e917","source":{"kind":"arxiv","id":"2606.00559","version":1},"attestation_state":"computed","paper":{"title":"Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Peng, Chenhao Zhang, Chenyang Xu, Irene Zheng, Jiafu Huang, Kecheng Cai, Wanqin Zhou, Yi Wang, Yiwei Gong, Zhengfeng Yang","submitted_at":"2026-05-30T06:23:30Z","abstract_excerpt":"Neural algorithmic reasoning has emerged as a popular research direction. It aims to train neural networks to mimic the step-by-step behavior of classical rule-based algorithms. More specifically, the execution of such algorithms can be abstracted as a sequence of states, where each state represents the intermediate outcome after an execution step. The training objective is to generate state sequences that replicate the underlying algorithmic process. A common framework for this task adopts an encoder-processor-decoder architecture, where the encoder learns representations of states, the proce"},"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":"2606.00559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T06:23:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22490bb10356a2bfca719b68b9078b0902e18ba17311cd499d02eb69e5ff2a7d","abstract_canon_sha256":"e22446f2171e18995d72d35d4bd61a654ba45e56b36fbe63c7131c4e6ff1e48a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:58.271572Z","signature_b64":"Qe27t14C1wQdQ3BHmWD9msACB2vY438SuJMSemxmL84xHTW9I9Jz8pOUsZrZXUXEl6nBN0ij21MZObGFLPWBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05785a77f5da6ff8b7e955b24aced87649550506e8c3f530c65a43511978e917","last_reissued_at":"2026-06-02T01:03:58.271146Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:58.271146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Peng, Chenhao Zhang, Chenyang Xu, Irene Zheng, Jiafu Huang, Kecheng Cai, Wanqin Zhou, Yi Wang, Yiwei Gong, Zhengfeng Yang","submitted_at":"2026-05-30T06:23:30Z","abstract_excerpt":"Neural algorithmic reasoning has emerged as a popular research direction. It aims to train neural networks to mimic the step-by-step behavior of classical rule-based algorithms. More specifically, the execution of such algorithms can be abstracted as a sequence of states, where each state represents the intermediate outcome after an execution step. The training objective is to generate state sequences that replicate the underlying algorithmic process. A common framework for this task adopts an encoder-processor-decoder architecture, where the encoder learns representations of states, the proce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00559","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/2606.00559/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":"2606.00559","created_at":"2026-06-02T01:03:58.271213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00559v1","created_at":"2026-06-02T01:03:58.271213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00559","created_at":"2026-06-02T01:03:58.271213+00:00"},{"alias_kind":"pith_short_12","alias_value":"AV4FU57V3JX7","created_at":"2026-06-02T01:03:58.271213+00:00"},{"alias_kind":"pith_short_16","alias_value":"AV4FU57V3JX7RN7J","created_at":"2026-06-02T01:03:58.271213+00:00"},{"alias_kind":"pith_short_8","alias_value":"AV4FU57V","created_at":"2026-06-02T01:03:58.271213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AV4FU57V3JX7RN7JKWZEVTWYOZ","json":"https://pith.science/pith/AV4FU57V3JX7RN7JKWZEVTWYOZ.json","graph_json":"https://pith.science/api/pith-number/AV4FU57V3JX7RN7JKWZEVTWYOZ/graph.json","events_json":"https://pith.science/api/pith-number/AV4FU57V3JX7RN7JKWZEVTWYOZ/events.json","paper":"https://pith.science/paper/AV4FU57V"},"agent_actions":{"view_html":"https://pith.science/pith/AV4FU57V3JX7RN7JKWZEVTWYOZ","download_json":"https://pith.science/pith/AV4FU57V3JX7RN7JKWZEVTWYOZ.json","view_paper":"https://pith.science/paper/AV4FU57V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00559&json=true","fetch_graph":"https://pith.science/api/pith-number/AV4FU57V3JX7RN7JKWZEVTWYOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/AV4FU57V3JX7RN7JKWZEVTWYOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AV4FU57V3JX7RN7JKWZEVTWYOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AV4FU57V3JX7RN7JKWZEVTWYOZ/action/storage_attestation","attest_author":"https://pith.science/pith/AV4FU57V3JX7RN7JKWZEVTWYOZ/action/author_attestation","sign_citation":"https://pith.science/pith/AV4FU57V3JX7RN7JKWZEVTWYOZ/action/citation_signature","submit_replication":"https://pith.science/pith/AV4FU57V3JX7RN7JKWZEVTWYOZ/action/replication_record"}},"created_at":"2026-06-02T01:03:58.271213+00:00","updated_at":"2026-06-02T01:03:58.271213+00:00"}