{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GFXOXDCP6JXOWH3Y5KS56QS3KR","short_pith_number":"pith:GFXOXDCP","canonical_record":{"source":{"id":"1910.09451","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-21T15:31:29Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"685487f46d9862ff008d352d7d9ea2594e015f0151b509fd3ae8ad7e0475fb7e","abstract_canon_sha256":"7d952a42953cec805fa0a25d889e40b53cce75e6202762835331860bffca4381"},"schema_version":"1.0"},"canonical_sha256":"316eeb8c4ff26eeb1f78eaa5df425b5478fcee8ac0476bf4b43328ef9b7f093d","source":{"kind":"arxiv","id":"1910.09451","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.09451","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"1910.09451v3","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09451","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"GFXOXDCP6JXO","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"pith_short_16","alias_value":"GFXOXDCP6JXOWH3Y","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"pith_short_8","alias_value":"GFXOXDCP","created_at":"2026-07-05T01:58:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GFXOXDCP6JXOWH3Y5KS56QS3KR","target":"record","payload":{"canonical_record":{"source":{"id":"1910.09451","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-21T15:31:29Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"685487f46d9862ff008d352d7d9ea2594e015f0151b509fd3ae8ad7e0475fb7e","abstract_canon_sha256":"7d952a42953cec805fa0a25d889e40b53cce75e6202762835331860bffca4381"},"schema_version":"1.0"},"canonical_sha256":"316eeb8c4ff26eeb1f78eaa5df425b5478fcee8ac0476bf4b43328ef9b7f093d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:29.209086Z","signature_b64":"cRibIVLHKZIlxwvlDmod13mkiF3Bg6FcNEXLsDpyHFxpBmYQCD778qESvspKbQwUJqVvWqXXDK9IuEKOOphjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"316eeb8c4ff26eeb1f78eaa5df425b5478fcee8ac0476bf4b43328ef9b7f093d","last_reissued_at":"2026-07-05T01:58:29.208502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:29.208502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.09451","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":"2026-07-05T01:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N9DG8BgU/BZ/9vMSycn5tMDb4ExS+UDQSYR1xRUen4Oc4pZQ12m1zIHFudBXoSn6ZdJ57/ym2b8EJTL3vDVGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:48:45.864097Z"},"content_sha256":"76c3503e2ef49efb92feee162650499e5364799b9b396de0c51de0144d8bd5cd","schema_version":"1.0","event_id":"sha256:76c3503e2ef49efb92feee162650499e5364799b9b396de0c51de0144d8bd5cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GFXOXDCP6JXOWH3Y5KS56QS3KR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HIGhER : Improving instruction following with Hindsight Generation for Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Florian Strub, Geoffrey Cideron, Mathieu Seurin, Olivier Pietquin","submitted_at":"2019-10-21T15:31:29Z","abstract_excerpt":"Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive agent behavior, it remains an open-problem to correctly relate language understanding and reinforcement learning in even simple instruction following scenarios. This joint learning problem is alleviated through expert demonstrations, auxiliary losses, or neural inductive biases. In this paper, we propose an orthogonal approach called Hindsight Generation fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09451","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/1910.09451/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":"2026-07-05T01:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QF7/NZ1VnRzjdlwyQ3Z8x9645AwU4kRlJlCiXn9WhyhoZNJoRZyw+4U0A8/ETqbo9w3I5qbwkX24ueDRlt9+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:48:45.865126Z"},"content_sha256":"722bd784c2c8fae7369a432647f73f6a071e43cfeb8dd039088ed7961cee3c72","schema_version":"1.0","event_id":"sha256:722bd784c2c8fae7369a432647f73f6a071e43cfeb8dd039088ed7961cee3c72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFXOXDCP6JXOWH3Y5KS56QS3KR/bundle.json","state_url":"https://pith.science/pith/GFXOXDCP6JXOWH3Y5KS56QS3KR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFXOXDCP6JXOWH3Y5KS56QS3KR/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":"2026-08-11T11:48:45Z","links":{"resolver":"https://pith.science/pith/GFXOXDCP6JXOWH3Y5KS56QS3KR","bundle":"https://pith.science/pith/GFXOXDCP6JXOWH3Y5KS56QS3KR/bundle.json","state":"https://pith.science/pith/GFXOXDCP6JXOWH3Y5KS56QS3KR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFXOXDCP6JXOWH3Y5KS56QS3KR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GFXOXDCP6JXOWH3Y5KS56QS3KR","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":"7d952a42953cec805fa0a25d889e40b53cce75e6202762835331860bffca4381","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-21T15:31:29Z","title_canon_sha256":"685487f46d9862ff008d352d7d9ea2594e015f0151b509fd3ae8ad7e0475fb7e"},"schema_version":"1.0","source":{"id":"1910.09451","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.09451","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"1910.09451v3","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09451","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"GFXOXDCP6JXO","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"pith_short_16","alias_value":"GFXOXDCP6JXOWH3Y","created_at":"2026-07-05T01:58:29Z"},{"alias_kind":"pith_short_8","alias_value":"GFXOXDCP","created_at":"2026-07-05T01:58:29Z"}],"graph_snapshots":[{"event_id":"sha256:722bd784c2c8fae7369a432647f73f6a071e43cfeb8dd039088ed7961cee3c72","target":"graph","created_at":"2026-07-05T01:58:29Z","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/1910.09451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive agent behavior, it remains an open-problem to correctly relate language understanding and reinforcement learning in even simple instruction following scenarios. This joint learning problem is alleviated through expert demonstrations, auxiliary losses, or neural inductive biases. In this paper, we propose an orthogonal approach called Hindsight Generation fo","authors_text":"Florian Strub, Geoffrey Cideron, Mathieu Seurin, Olivier Pietquin","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-21T15:31:29Z","title":"HIGhER : Improving instruction following with Hindsight Generation for Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09451","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":"sha256:76c3503e2ef49efb92feee162650499e5364799b9b396de0c51de0144d8bd5cd","target":"record","created_at":"2026-07-05T01:58:29Z","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":"7d952a42953cec805fa0a25d889e40b53cce75e6202762835331860bffca4381","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-21T15:31:29Z","title_canon_sha256":"685487f46d9862ff008d352d7d9ea2594e015f0151b509fd3ae8ad7e0475fb7e"},"schema_version":"1.0","source":{"id":"1910.09451","kind":"arxiv","version":3}},"canonical_sha256":"316eeb8c4ff26eeb1f78eaa5df425b5478fcee8ac0476bf4b43328ef9b7f093d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"316eeb8c4ff26eeb1f78eaa5df425b5478fcee8ac0476bf4b43328ef9b7f093d","first_computed_at":"2026-07-05T01:58:29.208502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:29.208502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cRibIVLHKZIlxwvlDmod13mkiF3Bg6FcNEXLsDpyHFxpBmYQCD778qESvspKbQwUJqVvWqXXDK9IuEKOOphjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:29.209086Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.09451","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76c3503e2ef49efb92feee162650499e5364799b9b396de0c51de0144d8bd5cd","sha256:722bd784c2c8fae7369a432647f73f6a071e43cfeb8dd039088ed7961cee3c72"],"state_sha256":"06e1e31221e0a1643bb2a0d4f9cc106a91065936d6cf4a940f92c1872086be29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LwllZh9I+aKO8lk6SpVLWxKRLfzao4WVh2uOQmiA3ao4pKkQQHp263QE61mg+5mVpJdz/FFby1nuUyrBX7SwCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T11:48:45.870998Z","bundle_sha256":"2441b2834b62fed4f2428f07ddaf3872467f6b441ea07bced02bea152f3bb308"}}