{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:77FJE42PVUVLT4EANKNPKNIDMA","short_pith_number":"pith:77FJE42P","canonical_record":{"source":{"id":"2502.13791","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T14:58:04Z","cross_cats_sorted":[],"title_canon_sha256":"ab8a3c4345024b76a911032a4d667a21f908082878e936cf776c407b235e3695","abstract_canon_sha256":"f6bea23d87e348150ab17155d29aabc0b0534179cbf0011d929fdb1863e1b42a"},"schema_version":"1.0"},"canonical_sha256":"ffca92734fad2ab9f0806a9af53503601672d1526dd4f4a32451c5ea7367ad75","source":{"kind":"arxiv","id":"2502.13791","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13791","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13791v2","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13791","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"pith_short_12","alias_value":"77FJE42PVUVL","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"pith_short_16","alias_value":"77FJE42PVUVLT4EA","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"pith_short_8","alias_value":"77FJE42P","created_at":"2026-07-05T11:17:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:77FJE42PVUVLT4EANKNPKNIDMA","target":"record","payload":{"canonical_record":{"source":{"id":"2502.13791","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T14:58:04Z","cross_cats_sorted":[],"title_canon_sha256":"ab8a3c4345024b76a911032a4d667a21f908082878e936cf776c407b235e3695","abstract_canon_sha256":"f6bea23d87e348150ab17155d29aabc0b0534179cbf0011d929fdb1863e1b42a"},"schema_version":"1.0"},"canonical_sha256":"ffca92734fad2ab9f0806a9af53503601672d1526dd4f4a32451c5ea7367ad75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:41.662358Z","signature_b64":"F5gNyHEBJxk4Bf08mDaiM0Ec2+3yg1fVKStH5lddlltxQALnbRfSmVsy4dOyh/xkqzspo0z2jZXc+N8tTFehBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffca92734fad2ab9f0806a9af53503601672d1526dd4f4a32451c5ea7367ad75","last_reissued_at":"2026-07-05T11:17:41.661842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:41.661842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.13791","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZgIZjzW+BcMgiaF7JShS9U2pyT9jpTk/k1s9ShJer3CQM38y+Dr6s91kavPL4QY4GTt2wqDJiZNxdHWBh4MVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:07:32.921300Z"},"content_sha256":"9570598675e84b8d4246bc33f89feaf5091f71c54045e4f3c95a98d306cf653a","schema_version":"1.0","event_id":"sha256:9570598675e84b8d4246bc33f89feaf5091f71c54045e4f3c95a98d306cf653a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:77FJE42PVUVLT4EANKNPKNIDMA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Testoni, Jon Ander Campos, Lucas Weber, Marco Del Tredici, Marzieh Fadaee, Mohammed Hamdy, Nathana\\\"el Carraz Rakotonirina, Sandro Pezzelle","submitted_at":"2025-02-19T14:58:04Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in working environments for a wide range of tasks, excelling at solving individual problems in isolation. However, are they also able to effectively collaborate over long-term interactions? To investigate this, we introduce MemoryCode, a synthetic multi-session dataset designed to test LLMs' ability to track and execute simple coding instructions amid irrelevant information, simulating a realistic setting. While all the models we tested handle isolated instructions well, even the performance of state-of-the-art models like GPT-4o deteriorates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13791","kind":"arxiv","version":2},"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/2502.13791/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":"2026-07-05T11:17:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bKL7Re2bORww1MtEd+rSBn7igETX0ZML09H0VjBVmftQDCu3BFEw9Mpz6f38954dft5tPnjjgb6FYn7BCNpFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:07:32.921679Z"},"content_sha256":"403f3c488af30f928a57b93c2b6a5a966ee31fde1a01596bd40da5f19b9a7c1f","schema_version":"1.0","event_id":"sha256:403f3c488af30f928a57b93c2b6a5a966ee31fde1a01596bd40da5f19b9a7c1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77FJE42PVUVLT4EANKNPKNIDMA/bundle.json","state_url":"https://pith.science/pith/77FJE42PVUVLT4EANKNPKNIDMA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77FJE42PVUVLT4EANKNPKNIDMA/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":"2026-07-07T09:07:32Z","links":{"resolver":"https://pith.science/pith/77FJE42PVUVLT4EANKNPKNIDMA","bundle":"https://pith.science/pith/77FJE42PVUVLT4EANKNPKNIDMA/bundle.json","state":"https://pith.science/pith/77FJE42PVUVLT4EANKNPKNIDMA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77FJE42PVUVLT4EANKNPKNIDMA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:77FJE42PVUVLT4EANKNPKNIDMA","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":"f6bea23d87e348150ab17155d29aabc0b0534179cbf0011d929fdb1863e1b42a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T14:58:04Z","title_canon_sha256":"ab8a3c4345024b76a911032a4d667a21f908082878e936cf776c407b235e3695"},"schema_version":"1.0","source":{"id":"2502.13791","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13791","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13791v2","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13791","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"pith_short_12","alias_value":"77FJE42PVUVL","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"pith_short_16","alias_value":"77FJE42PVUVLT4EA","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"pith_short_8","alias_value":"77FJE42P","created_at":"2026-07-05T11:17:41Z"}],"graph_snapshots":[{"event_id":"sha256:403f3c488af30f928a57b93c2b6a5a966ee31fde1a01596bd40da5f19b9a7c1f","target":"graph","created_at":"2026-07-05T11:17:41Z","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/2502.13791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly used in working environments for a wide range of tasks, excelling at solving individual problems in isolation. However, are they also able to effectively collaborate over long-term interactions? To investigate this, we introduce MemoryCode, a synthetic multi-session dataset designed to test LLMs' ability to track and execute simple coding instructions amid irrelevant information, simulating a realistic setting. While all the models we tested handle isolated instructions well, even the performance of state-of-the-art models like GPT-4o deteriorates ","authors_text":"Alberto Testoni, Jon Ander Campos, Lucas Weber, Marco Del Tredici, Marzieh Fadaee, Mohammed Hamdy, Nathana\\\"el Carraz Rakotonirina, Sandro Pezzelle","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T14:58:04Z","title":"From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13791","kind":"arxiv","version":2},"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":"sha256:9570598675e84b8d4246bc33f89feaf5091f71c54045e4f3c95a98d306cf653a","target":"record","created_at":"2026-07-05T11:17:41Z","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":"f6bea23d87e348150ab17155d29aabc0b0534179cbf0011d929fdb1863e1b42a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T14:58:04Z","title_canon_sha256":"ab8a3c4345024b76a911032a4d667a21f908082878e936cf776c407b235e3695"},"schema_version":"1.0","source":{"id":"2502.13791","kind":"arxiv","version":2}},"canonical_sha256":"ffca92734fad2ab9f0806a9af53503601672d1526dd4f4a32451c5ea7367ad75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffca92734fad2ab9f0806a9af53503601672d1526dd4f4a32451c5ea7367ad75","first_computed_at":"2026-07-05T11:17:41.661842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:41.661842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F5gNyHEBJxk4Bf08mDaiM0Ec2+3yg1fVKStH5lddlltxQALnbRfSmVsy4dOyh/xkqzspo0z2jZXc+N8tTFehBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:41.662358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13791","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9570598675e84b8d4246bc33f89feaf5091f71c54045e4f3c95a98d306cf653a","sha256:403f3c488af30f928a57b93c2b6a5a966ee31fde1a01596bd40da5f19b9a7c1f"],"state_sha256":"32320bd569bc8fd3c8c83a52c59267aa3d73f1f16e7f9d4af4cdf001e1af15bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h32ZBL8DVcmt7UZfWAmrwEmyt9SxSBT/h4qD84uTw8MC6MRmL9QzUE7JmvVCKkW8HZgoKYHPPATXqWPOVYEAAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:07:32.926960Z","bundle_sha256":"49dcdfb4e25e3468c80a34aaa43e0afd5da07d0b83c53ca3978995ddf48fc567"}}