{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2X55UJCSAGHI3PCFIYEHKPJ7HC","short_pith_number":"pith:2X55UJCS","schema_version":"1.0","canonical_sha256":"d5fbda2452018e8dbc454608753d3f389deb5f11a36f861d8c2a27f938e7faf5","source":{"kind":"arxiv","id":"2506.12149","version":1},"attestation_state":"computed","paper":{"title":"Maximally-Informative Retrieval for State Space Model Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Bowman, Evan Becker, Luca Zancato, Matthew Trager, Stefano Soatto, Tian Yu Liu, Wei Xia","submitted_at":"2025-06-13T18:08:54Z","abstract_excerpt":"Given a query and dataset, the optimal way of answering the query is to make use all the information available. Modern LLMs exhibit impressive ability to memorize training data, but data not deemed important during training is forgotten, and information outside that training set cannot be made use of. Processing an entire dataset at inference time is infeasible due to the bounded nature of model resources (e.g. context size in transformers or states in state space models), meaning we must resort to external memory. This constraint naturally leads to the following problem: How can we decide bas"},"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":"2506.12149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T18:08:54Z","cross_cats_sorted":[],"title_canon_sha256":"bd59d84e4932452b2cdf62227718b85c0e23e3407a579ecaa91b8e493eda800b","abstract_canon_sha256":"2b88f857f2f7dcd08d2f698d3ec002704c223249fc2a950fea37c7d95d91cf37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:22.036569Z","signature_b64":"26GopAsZ9aZPY4tAkwildMQZe+xL95NVq80ynuto9rjKnu8fnut6Den+rJpJsn9mT/9dkZ/mMlZ5zdmUhN/ABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5fbda2452018e8dbc454608753d3f389deb5f11a36f861d8c2a27f938e7faf5","last_reissued_at":"2026-07-05T11:21:22.036078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:22.036078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximally-Informative Retrieval for State Space Model Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Bowman, Evan Becker, Luca Zancato, Matthew Trager, Stefano Soatto, Tian Yu Liu, Wei Xia","submitted_at":"2025-06-13T18:08:54Z","abstract_excerpt":"Given a query and dataset, the optimal way of answering the query is to make use all the information available. Modern LLMs exhibit impressive ability to memorize training data, but data not deemed important during training is forgotten, and information outside that training set cannot be made use of. Processing an entire dataset at inference time is infeasible due to the bounded nature of model resources (e.g. context size in transformers or states in state space models), meaning we must resort to external memory. This constraint naturally leads to the following problem: How can we decide bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12149","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/2506.12149/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":"2506.12149","created_at":"2026-07-05T11:21:22.036135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12149v1","created_at":"2026-07-05T11:21:22.036135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12149","created_at":"2026-07-05T11:21:22.036135+00:00"},{"alias_kind":"pith_short_12","alias_value":"2X55UJCSAGHI","created_at":"2026-07-05T11:21:22.036135+00:00"},{"alias_kind":"pith_short_16","alias_value":"2X55UJCSAGHI3PCF","created_at":"2026-07-05T11:21:22.036135+00:00"},{"alias_kind":"pith_short_8","alias_value":"2X55UJCS","created_at":"2026-07-05T11:21:22.036135+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/2X55UJCSAGHI3PCFIYEHKPJ7HC","json":"https://pith.science/pith/2X55UJCSAGHI3PCFIYEHKPJ7HC.json","graph_json":"https://pith.science/api/pith-number/2X55UJCSAGHI3PCFIYEHKPJ7HC/graph.json","events_json":"https://pith.science/api/pith-number/2X55UJCSAGHI3PCFIYEHKPJ7HC/events.json","paper":"https://pith.science/paper/2X55UJCS"},"agent_actions":{"view_html":"https://pith.science/pith/2X55UJCSAGHI3PCFIYEHKPJ7HC","download_json":"https://pith.science/pith/2X55UJCSAGHI3PCFIYEHKPJ7HC.json","view_paper":"https://pith.science/paper/2X55UJCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12149&json=true","fetch_graph":"https://pith.science/api/pith-number/2X55UJCSAGHI3PCFIYEHKPJ7HC/graph.json","fetch_events":"https://pith.science/api/pith-number/2X55UJCSAGHI3PCFIYEHKPJ7HC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2X55UJCSAGHI3PCFIYEHKPJ7HC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2X55UJCSAGHI3PCFIYEHKPJ7HC/action/storage_attestation","attest_author":"https://pith.science/pith/2X55UJCSAGHI3PCFIYEHKPJ7HC/action/author_attestation","sign_citation":"https://pith.science/pith/2X55UJCSAGHI3PCFIYEHKPJ7HC/action/citation_signature","submit_replication":"https://pith.science/pith/2X55UJCSAGHI3PCFIYEHKPJ7HC/action/replication_record"}},"created_at":"2026-07-05T11:21:22.036135+00:00","updated_at":"2026-07-05T11:21:22.036135+00:00"}