{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FZF5HK53T5BHTHTV5AX6NEHRMO","short_pith_number":"pith:FZF5HK53","canonical_record":{"source":{"id":"2112.05787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-04T13:17:07Z","cross_cats_sorted":[],"title_canon_sha256":"9d761a68bf3f39ee21e42a4d0c028aa8d6218735ee818dd12865f227b4b8b13c","abstract_canon_sha256":"7a74eeabe34d57ec6939f2c5ae5a44e522021cc71e16d82720b72c2fdc1c6c05"},"schema_version":"1.0"},"canonical_sha256":"2e4bd3abbb9f42799e75e82fe690f163ab9f96dfab022f0aa94f577f00f96c6c","source":{"kind":"arxiv","id":"2112.05787","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05787","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05787v2","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05787","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"pith_short_12","alias_value":"FZF5HK53T5BH","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"pith_short_16","alias_value":"FZF5HK53T5BHTHTV","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"pith_short_8","alias_value":"FZF5HK53","created_at":"2026-07-05T04:19:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FZF5HK53T5BHTHTV5AX6NEHRMO","target":"record","payload":{"canonical_record":{"source":{"id":"2112.05787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-04T13:17:07Z","cross_cats_sorted":[],"title_canon_sha256":"9d761a68bf3f39ee21e42a4d0c028aa8d6218735ee818dd12865f227b4b8b13c","abstract_canon_sha256":"7a74eeabe34d57ec6939f2c5ae5a44e522021cc71e16d82720b72c2fdc1c6c05"},"schema_version":"1.0"},"canonical_sha256":"2e4bd3abbb9f42799e75e82fe690f163ab9f96dfab022f0aa94f577f00f96c6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:49.761614Z","signature_b64":"S8dM2rd/q8mSTCPBGaMeuBffAPTGaCpkG1wCcAuYfWy98fVbO8s7iDbJg7iIbprXyNKhDbGxmUoWx06xsFdZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e4bd3abbb9f42799e75e82fe690f163ab9f96dfab022f0aa94f577f00f96c6c","last_reissued_at":"2026-07-05T04:19:49.761125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:49.761125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.05787","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":"2026-07-05T04:19:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFDvcxgT187O0uO8S5TIObEF2xv2LLmM+mlzmAvkhkTRyongKzu8jsY4nrSHgMXFNCAPurW7m+YqB/p4Pun8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:13:30.790327Z"},"content_sha256":"31a826f53bab7cd4b8a33981aa63ca98418c99a2a5cb6a07583fbb89036d869a","schema_version":"1.0","event_id":"sha256:31a826f53bab7cd4b8a33981aa63ca98418c99a2a5cb6a07583fbb89036d869a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FZF5HK53T5BHTHTV5AX6NEHRMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aishik Mandal, Atharva Naik, Bishal Santra, Manish Gupta, Pawan Goyal, Sumegh Roychowdhury, Vasu Gurram","submitted_at":"2021-12-04T13:17:07Z","abstract_excerpt":"Although many pretrained models exist for text or images, there have been relatively fewer attempts to train representations specifically for dialog understanding. Prior works usually relied on finetuned representations based on generic text representation models like BERT or GPT-2. But such language modeling pretraining objectives do not take the structural information of conversational text into consideration. Although generative dialog models can learn structural features too, we argue that the structure-unaware word-by-word generation is not suitable for effective conversation modeling. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05787","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/2112.05787/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":"2026-07-05T04:19:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"umKE710DLpwpms6aOBRYBuCzJJ8WBTv5vx0nLGX/oi8DU4zmr+kmKrNZa+tsf4YEwvVdTdRhak1vKNE39sM2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:13:30.790860Z"},"content_sha256":"8be19af2af14e17673054743c3045653e33eff3b490c9d48648bd7f13df4a9a5","schema_version":"1.0","event_id":"sha256:8be19af2af14e17673054743c3045653e33eff3b490c9d48648bd7f13df4a9a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZF5HK53T5BHTHTV5AX6NEHRMO/bundle.json","state_url":"https://pith.science/pith/FZF5HK53T5BHTHTV5AX6NEHRMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZF5HK53T5BHTHTV5AX6NEHRMO/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":"2026-08-04T05:13:30Z","links":{"resolver":"https://pith.science/pith/FZF5HK53T5BHTHTV5AX6NEHRMO","bundle":"https://pith.science/pith/FZF5HK53T5BHTHTV5AX6NEHRMO/bundle.json","state":"https://pith.science/pith/FZF5HK53T5BHTHTV5AX6NEHRMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZF5HK53T5BHTHTV5AX6NEHRMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FZF5HK53T5BHTHTV5AX6NEHRMO","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":"7a74eeabe34d57ec6939f2c5ae5a44e522021cc71e16d82720b72c2fdc1c6c05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-04T13:17:07Z","title_canon_sha256":"9d761a68bf3f39ee21e42a4d0c028aa8d6218735ee818dd12865f227b4b8b13c"},"schema_version":"1.0","source":{"id":"2112.05787","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05787","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05787v2","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05787","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"pith_short_12","alias_value":"FZF5HK53T5BH","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"pith_short_16","alias_value":"FZF5HK53T5BHTHTV","created_at":"2026-07-05T04:19:49Z"},{"alias_kind":"pith_short_8","alias_value":"FZF5HK53","created_at":"2026-07-05T04:19:49Z"}],"graph_snapshots":[{"event_id":"sha256:8be19af2af14e17673054743c3045653e33eff3b490c9d48648bd7f13df4a9a5","target":"graph","created_at":"2026-07-05T04:19:49Z","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/2112.05787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although many pretrained models exist for text or images, there have been relatively fewer attempts to train representations specifically for dialog understanding. Prior works usually relied on finetuned representations based on generic text representation models like BERT or GPT-2. But such language modeling pretraining objectives do not take the structural information of conversational text into consideration. Although generative dialog models can learn structural features too, we argue that the structure-unaware word-by-word generation is not suitable for effective conversation modeling. We","authors_text":"Aishik Mandal, Atharva Naik, Bishal Santra, Manish Gupta, Pawan Goyal, Sumegh Roychowdhury, Vasu Gurram","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-04T13:17:07Z","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05787","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":"sha256:31a826f53bab7cd4b8a33981aa63ca98418c99a2a5cb6a07583fbb89036d869a","target":"record","created_at":"2026-07-05T04:19:49Z","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":"7a74eeabe34d57ec6939f2c5ae5a44e522021cc71e16d82720b72c2fdc1c6c05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-04T13:17:07Z","title_canon_sha256":"9d761a68bf3f39ee21e42a4d0c028aa8d6218735ee818dd12865f227b4b8b13c"},"schema_version":"1.0","source":{"id":"2112.05787","kind":"arxiv","version":2}},"canonical_sha256":"2e4bd3abbb9f42799e75e82fe690f163ab9f96dfab022f0aa94f577f00f96c6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e4bd3abbb9f42799e75e82fe690f163ab9f96dfab022f0aa94f577f00f96c6c","first_computed_at":"2026-07-05T04:19:49.761125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:49.761125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S8dM2rd/q8mSTCPBGaMeuBffAPTGaCpkG1wCcAuYfWy98fVbO8s7iDbJg7iIbprXyNKhDbGxmUoWx06xsFdZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:49.761614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.05787","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31a826f53bab7cd4b8a33981aa63ca98418c99a2a5cb6a07583fbb89036d869a","sha256:8be19af2af14e17673054743c3045653e33eff3b490c9d48648bd7f13df4a9a5"],"state_sha256":"2332597454f08608cc2fd61c5036af90232d5d8da95cfa23525ad65f50b7580c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ss8lUq6ImIXfJbqYtc1UBmZ9qyoMDbsFz4jlv227zDm8gWDuYYqu5MmB7ZAVIoXtTKtwkqTVwV1TEsoHfHIAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:13:30.796757Z","bundle_sha256":"7cc74b6950948ba8ef9703b55710234dcbc7f0f73769eb7e7f5ef4e1a721380a"}}