{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VFMVDFTG5G53MXMXAZ6GPFKQGN","short_pith_number":"pith:VFMVDFTG","canonical_record":{"source":{"id":"2403.08715","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T17:17:48Z","cross_cats_sorted":[],"title_canon_sha256":"c540b4721266e55c210227ca64462b952d31427544b024c9eed5788c62c081ec","abstract_canon_sha256":"81a030155cfce96842e3f5d0f196f16b949e3120929c4b057e8f245165cd6222"},"schema_version":"1.0"},"canonical_sha256":"a959519666e9bbb65d97067c679550335872268023bbf355c700ba16822bd3dc","source":{"kind":"arxiv","id":"2403.08715","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08715","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08715v3","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08715","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"pith_short_12","alias_value":"VFMVDFTG5G53","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"pith_short_16","alias_value":"VFMVDFTG5G53MXMX","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"pith_short_8","alias_value":"VFMVDFTG","created_at":"2026-07-05T08:12:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VFMVDFTG5G53MXMXAZ6GPFKQGN","target":"record","payload":{"canonical_record":{"source":{"id":"2403.08715","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T17:17:48Z","cross_cats_sorted":[],"title_canon_sha256":"c540b4721266e55c210227ca64462b952d31427544b024c9eed5788c62c081ec","abstract_canon_sha256":"81a030155cfce96842e3f5d0f196f16b949e3120929c4b057e8f245165cd6222"},"schema_version":"1.0"},"canonical_sha256":"a959519666e9bbb65d97067c679550335872268023bbf355c700ba16822bd3dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:15.177487Z","signature_b64":"M0m0XUdLYvTsRWQRZsXv4g5XUv4LogJFdJaAB2+AXHzBO0CQNSHX+ZZ5CScZ3eWDlaGuiCvsR78dcf1KZGGqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a959519666e9bbb65d97067c679550335872268023bbf355c700ba16822bd3dc","last_reissued_at":"2026-07-05T08:12:15.176942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:15.176942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.08715","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:12:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZmbC7gmsH9wghXe0h6+i5xeiRSaAH+eNrhsksm2GZ0K1uUEDaGNnVAzS3oiCrvjTLXdO4lPTk1E4U8X7oF76Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:55:21.029474Z"},"content_sha256":"ec2dad65402be351228d4d7e7945d7504ed0e88b5a4f37f76649468dca9026b4","schema_version":"1.0","event_id":"sha256:ec2dad65402be351228d4d7e7945d7504ed0e88b5a4f37f76649468dca9026b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VFMVDFTG5G53MXMXAZ6GPFKQGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Haofei Yu, Hao Zhu, Maarten Sap, Ruiyi Wang, Wenxin Zhang, Yonatan Bisk, Zhengyang Qi","submitted_at":"2024-03-13T17:17:48Z","abstract_excerpt":"Humans learn social skills through both imitation and social interaction. This social learning process is largely understudied by existing research on building language agents. Motivated by this gap, we propose an interactive learning method, SOTOPIA-$\\pi$, improving the social intelligence of language agents. This method leverages behavior cloning and self-reinforcement training on filtered social interaction data according to large language model (LLM) ratings. We show that our training method allows a 7B LLM to reach the social goal completion ability of an expert model (GPT-4-based agent),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08715","kind":"arxiv","version":3},"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/2403.08715/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":"2026-07-05T08:12:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mY0uhojqbR5UvNqhtRWydTXFQ6ussDx38RFjW8xEajQvBbMLOedUmq6AWroF9DKQ/GOcYxgt/ynZzdJwiK3HCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:55:21.029980Z"},"content_sha256":"402fbe41a137fabd448747e3f882193351bb709982036afbe1eed96b2ef61204","schema_version":"1.0","event_id":"sha256:402fbe41a137fabd448747e3f882193351bb709982036afbe1eed96b2ef61204"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFMVDFTG5G53MXMXAZ6GPFKQGN/bundle.json","state_url":"https://pith.science/pith/VFMVDFTG5G53MXMXAZ6GPFKQGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFMVDFTG5G53MXMXAZ6GPFKQGN/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":"2026-08-04T04:55:21Z","links":{"resolver":"https://pith.science/pith/VFMVDFTG5G53MXMXAZ6GPFKQGN","bundle":"https://pith.science/pith/VFMVDFTG5G53MXMXAZ6GPFKQGN/bundle.json","state":"https://pith.science/pith/VFMVDFTG5G53MXMXAZ6GPFKQGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFMVDFTG5G53MXMXAZ6GPFKQGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VFMVDFTG5G53MXMXAZ6GPFKQGN","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":"81a030155cfce96842e3f5d0f196f16b949e3120929c4b057e8f245165cd6222","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T17:17:48Z","title_canon_sha256":"c540b4721266e55c210227ca64462b952d31427544b024c9eed5788c62c081ec"},"schema_version":"1.0","source":{"id":"2403.08715","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08715","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08715v3","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08715","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"pith_short_12","alias_value":"VFMVDFTG5G53","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"pith_short_16","alias_value":"VFMVDFTG5G53MXMX","created_at":"2026-07-05T08:12:15Z"},{"alias_kind":"pith_short_8","alias_value":"VFMVDFTG","created_at":"2026-07-05T08:12:15Z"}],"graph_snapshots":[{"event_id":"sha256:402fbe41a137fabd448747e3f882193351bb709982036afbe1eed96b2ef61204","target":"graph","created_at":"2026-07-05T08:12:15Z","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/2403.08715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans learn social skills through both imitation and social interaction. This social learning process is largely understudied by existing research on building language agents. Motivated by this gap, we propose an interactive learning method, SOTOPIA-$\\pi$, improving the social intelligence of language agents. This method leverages behavior cloning and self-reinforcement training on filtered social interaction data according to large language model (LLM) ratings. We show that our training method allows a 7B LLM to reach the social goal completion ability of an expert model (GPT-4-based agent),","authors_text":"Graham Neubig, Haofei Yu, Hao Zhu, Maarten Sap, Ruiyi Wang, Wenxin Zhang, Yonatan Bisk, Zhengyang Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T17:17:48Z","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08715","kind":"arxiv","version":3},"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:ec2dad65402be351228d4d7e7945d7504ed0e88b5a4f37f76649468dca9026b4","target":"record","created_at":"2026-07-05T08:12:15Z","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":"81a030155cfce96842e3f5d0f196f16b949e3120929c4b057e8f245165cd6222","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T17:17:48Z","title_canon_sha256":"c540b4721266e55c210227ca64462b952d31427544b024c9eed5788c62c081ec"},"schema_version":"1.0","source":{"id":"2403.08715","kind":"arxiv","version":3}},"canonical_sha256":"a959519666e9bbb65d97067c679550335872268023bbf355c700ba16822bd3dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a959519666e9bbb65d97067c679550335872268023bbf355c700ba16822bd3dc","first_computed_at":"2026-07-05T08:12:15.176942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:15.176942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M0m0XUdLYvTsRWQRZsXv4g5XUv4LogJFdJaAB2+AXHzBO0CQNSHX+ZZ5CScZ3eWDlaGuiCvsR78dcf1KZGGqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:15.177487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08715","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec2dad65402be351228d4d7e7945d7504ed0e88b5a4f37f76649468dca9026b4","sha256:402fbe41a137fabd448747e3f882193351bb709982036afbe1eed96b2ef61204"],"state_sha256":"2fb34e1f68a73fffa33107da5a7ec2e660fc838a9e2523d0b8379be71a80858a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wj2BhjUjbd4wqFDLFtK1Y9aJdqTWhnO1lR00+/s7N9Jf2G59VJR9EtSUbKzzxap6+EedHAmk0f2/589GVqzbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:55:21.033350Z","bundle_sha256":"ff67e5551c33f9e3d11be77dad0c808b93ae71149408470ac7faef537b65a76a"}}