{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MEBBIQRQ3C4NNDJ2X3TBH3KI2Z","short_pith_number":"pith:MEBBIQRQ","canonical_record":{"source":{"id":"2212.09246","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T04:47:49Z","cross_cats_sorted":[],"title_canon_sha256":"bfcb0d5c783a16cf63dc8c4e43df908cabe338fa3a454e7a57843902929d386c","abstract_canon_sha256":"cff4c0c04f4dbe1c6be1d6a28c5c5110269f832337305fa188ee01482a4ef24d"},"schema_version":"1.0"},"canonical_sha256":"6102144230d8b8d68d3abee613ed48d6475be886374de2e768360711ad777a54","source":{"kind":"arxiv","id":"2212.09246","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09246","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09246v3","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09246","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"MEBBIQRQ3C4N","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"MEBBIQRQ3C4NNDJ2","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"MEBBIQRQ","created_at":"2026-07-05T06:14:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MEBBIQRQ3C4NNDJ2X3TBH3KI2Z","target":"record","payload":{"canonical_record":{"source":{"id":"2212.09246","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T04:47:49Z","cross_cats_sorted":[],"title_canon_sha256":"bfcb0d5c783a16cf63dc8c4e43df908cabe338fa3a454e7a57843902929d386c","abstract_canon_sha256":"cff4c0c04f4dbe1c6be1d6a28c5c5110269f832337305fa188ee01482a4ef24d"},"schema_version":"1.0"},"canonical_sha256":"6102144230d8b8d68d3abee613ed48d6475be886374de2e768360711ad777a54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:07.407577Z","signature_b64":"i3Pd7ceffkuxOa32oN95SarpdBSgt+3g+u61vOdoSLIxXnb0GHKSEkbNi2HMeSK2gkUgRDKk6S9u0s+t1JEAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6102144230d8b8d68d3abee613ed48d6475be886374de2e768360711ad777a54","last_reissued_at":"2026-07-05T06:14:07.407091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:07.407091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.09246","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":"2026-07-05T06:14:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ruIFcb0mJZESiaUrnazI5hU6jfA5QpEFLqofABc7Y6rsNt/XuXHEDc5mHQhCoCLtTER+pe4XU/ObRqRgFBnqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:17:30.159485Z"},"content_sha256":"13047197ada867a18bde31c2bd7a4e3d0a665972a798d107a4bd3e05f8063401","schema_version":"1.0","event_id":"sha256:13047197ada867a18bde31c2bd7a4e3d0a665972a798d107a4bd3e05f8063401"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MEBBIQRQ3C4NNDJ2X3TBH3KI2Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandra Bhagavatula, Doug Downey, Jena D. Hwang, Keisuke Sakaguchi, Lianhui Qin, Peter West, Ronan Le Bras, Swabha Swayamdipta, Ximing Lu, Yejin Choi","submitted_at":"2022-12-19T04:47:49Z","abstract_excerpt":"Commonsense capabilities of pre-trained language models dramatically improve with scale, leading many to believe that scale is the only winning recipe. But is it? Here, we investigate an alternative that a priori seems impossible: can smaller language models (e.g., GPT-2) win over models that are orders of magnitude larger and better (e.g., GPT-3), if powered with novel commonsense distillation algorithms? The key intellectual challenge is to design a learning algorithm that achieve a competitive level of commonsense acquisition, without relying on the benefits of scale. In particular, we stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09246","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/2212.09246/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":"2026-07-05T06:14:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1t6yApAUMCZSO2ME8BbGrbsFJ+4e9u61Cy8qZpHc7T/9j9efdqMhHsHaosWBdcSznpZqBUOiT+bJAPkO99VNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:17:30.159979Z"},"content_sha256":"a37dd6f89e592b1e3643e4fe463bd2707067a3c05c674e6cc611a00d341d9807","schema_version":"1.0","event_id":"sha256:a37dd6f89e592b1e3643e4fe463bd2707067a3c05c674e6cc611a00d341d9807"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MEBBIQRQ3C4NNDJ2X3TBH3KI2Z/bundle.json","state_url":"https://pith.science/pith/MEBBIQRQ3C4NNDJ2X3TBH3KI2Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MEBBIQRQ3C4NNDJ2X3TBH3KI2Z/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":"2026-08-03T19:17:30Z","links":{"resolver":"https://pith.science/pith/MEBBIQRQ3C4NNDJ2X3TBH3KI2Z","bundle":"https://pith.science/pith/MEBBIQRQ3C4NNDJ2X3TBH3KI2Z/bundle.json","state":"https://pith.science/pith/MEBBIQRQ3C4NNDJ2X3TBH3KI2Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MEBBIQRQ3C4NNDJ2X3TBH3KI2Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MEBBIQRQ3C4NNDJ2X3TBH3KI2Z","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":"cff4c0c04f4dbe1c6be1d6a28c5c5110269f832337305fa188ee01482a4ef24d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T04:47:49Z","title_canon_sha256":"bfcb0d5c783a16cf63dc8c4e43df908cabe338fa3a454e7a57843902929d386c"},"schema_version":"1.0","source":{"id":"2212.09246","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09246","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09246v3","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09246","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"MEBBIQRQ3C4N","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"MEBBIQRQ3C4NNDJ2","created_at":"2026-07-05T06:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"MEBBIQRQ","created_at":"2026-07-05T06:14:07Z"}],"graph_snapshots":[{"event_id":"sha256:a37dd6f89e592b1e3643e4fe463bd2707067a3c05c674e6cc611a00d341d9807","target":"graph","created_at":"2026-07-05T06:14:07Z","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/2212.09246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Commonsense capabilities of pre-trained language models dramatically improve with scale, leading many to believe that scale is the only winning recipe. But is it? Here, we investigate an alternative that a priori seems impossible: can smaller language models (e.g., GPT-2) win over models that are orders of magnitude larger and better (e.g., GPT-3), if powered with novel commonsense distillation algorithms? The key intellectual challenge is to design a learning algorithm that achieve a competitive level of commonsense acquisition, without relying on the benefits of scale. In particular, we stud","authors_text":"Chandra Bhagavatula, Doug Downey, Jena D. Hwang, Keisuke Sakaguchi, Lianhui Qin, Peter West, Ronan Le Bras, Swabha Swayamdipta, Ximing Lu, Yejin Choi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T04:47:49Z","title":"I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09246","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":"sha256:13047197ada867a18bde31c2bd7a4e3d0a665972a798d107a4bd3e05f8063401","target":"record","created_at":"2026-07-05T06:14:07Z","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":"cff4c0c04f4dbe1c6be1d6a28c5c5110269f832337305fa188ee01482a4ef24d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T04:47:49Z","title_canon_sha256":"bfcb0d5c783a16cf63dc8c4e43df908cabe338fa3a454e7a57843902929d386c"},"schema_version":"1.0","source":{"id":"2212.09246","kind":"arxiv","version":3}},"canonical_sha256":"6102144230d8b8d68d3abee613ed48d6475be886374de2e768360711ad777a54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6102144230d8b8d68d3abee613ed48d6475be886374de2e768360711ad777a54","first_computed_at":"2026-07-05T06:14:07.407091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:07.407091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i3Pd7ceffkuxOa32oN95SarpdBSgt+3g+u61vOdoSLIxXnb0GHKSEkbNi2HMeSK2gkUgRDKk6S9u0s+t1JEAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:07.407577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09246","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13047197ada867a18bde31c2bd7a4e3d0a665972a798d107a4bd3e05f8063401","sha256:a37dd6f89e592b1e3643e4fe463bd2707067a3c05c674e6cc611a00d341d9807"],"state_sha256":"28db2f45e949d2ee5ae0582254506d964243925b752094b0d6a7a7a0db308431"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U4cN1gW/pahz6fv+0ezeXKEMG8F/68HeWFLEIByva2ZyeoReTYyzz5S6GzxtX07RWAFcbUEtRPeQdfp+bGeoBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:17:30.163977Z","bundle_sha256":"96028c3effc6e5890a2cf552f4cebfbbf075173b16e27f1287bf522219551cf0"}}