{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GJKMI7XQBSF2ZASILV5GB3EYIZ","short_pith_number":"pith:GJKMI7XQ","canonical_record":{"source":{"id":"2307.04114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-09T08:07:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.MM"],"title_canon_sha256":"b4d39cdeb68e33e53c9831fb2654a4928bc52a7b440f61d258950830e533437c","abstract_canon_sha256":"5742f634294ee588142d6c4c5d61e0c45e6eacc67c64018e0c819d5a778cfa06"},"schema_version":"1.0"},"canonical_sha256":"3254c47ef00c8bac82485d7a60ec984654b5a26bde00e1110a28e3c758a07a2d","source":{"kind":"arxiv","id":"2307.04114","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04114","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04114v1","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04114","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"pith_short_12","alias_value":"GJKMI7XQBSF2","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"pith_short_16","alias_value":"GJKMI7XQBSF2ZASI","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"pith_short_8","alias_value":"GJKMI7XQ","created_at":"2026-07-05T06:29:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GJKMI7XQBSF2ZASILV5GB3EYIZ","target":"record","payload":{"canonical_record":{"source":{"id":"2307.04114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-09T08:07:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.MM"],"title_canon_sha256":"b4d39cdeb68e33e53c9831fb2654a4928bc52a7b440f61d258950830e533437c","abstract_canon_sha256":"5742f634294ee588142d6c4c5d61e0c45e6eacc67c64018e0c819d5a778cfa06"},"schema_version":"1.0"},"canonical_sha256":"3254c47ef00c8bac82485d7a60ec984654b5a26bde00e1110a28e3c758a07a2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:08.937808Z","signature_b64":"kRd1i2qhow+bvly5RVxd6TbFfjVELORbpC/8tWvKgSSu5Nhcy44G1ZHHBltvJw5rs/fInUIAcDSn17rkZBYGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3254c47ef00c8bac82485d7a60ec984654b5a26bde00e1110a28e3c758a07a2d","last_reissued_at":"2026-07-05T06:29:08.936947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:08.936947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.04114","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:29:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3eiVHDXAKom9ZeQ4aOpiLJv79Ij2jMBy1BWGRyV3x+Xz4iYpRDxVnOHK/oExH+AQ6J7fTyi1piOJhZPzOU0RBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:47:29.642697Z"},"content_sha256":"cb1c8f2dd51d6afec2df7d5f8b766c4e2cdace25257c01fd8ac6bd66967e1092","schema_version":"1.0","event_id":"sha256:cb1c8f2dd51d6afec2df7d5f8b766c4e2cdace25257c01fd8ac6bd66967e1092"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GJKMI7XQBSF2ZASILV5GB3EYIZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.MM"],"primary_cat":"cs.LG","authors_text":"Dong Pang, Huishuai Zhang, Weiran Huang, Yunkai Dang, Zihao Jiang","submitted_at":"2023-07-09T08:07:43Z","abstract_excerpt":"Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However, these works focus on improving existing modules such as visual prototypes and feature extractors of the standard few-shot learning framework. This limits the full potential use of semantic information. In this paper, we propose a novel few-shot learning framework that uses pre-trained language models based on contrastive learning. To address the challenge of al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04114","kind":"arxiv","version":1},"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/2307.04114/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":"2026-07-05T06:29:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ncEf84W2Hclz+OBFzSYXa/YHAIn0cmDI8u77PpUvooG1MBTN4IaJ5aKxwA5xSttm9rhosuF3dbJC0cHPu2E9Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:47:29.643237Z"},"content_sha256":"a0fa8ff5ac5041a58fcb59cede2b4259ad362fe4cf66cfd6e98d070fa7513330","schema_version":"1.0","event_id":"sha256:a0fa8ff5ac5041a58fcb59cede2b4259ad362fe4cf66cfd6e98d070fa7513330"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJKMI7XQBSF2ZASILV5GB3EYIZ/bundle.json","state_url":"https://pith.science/pith/GJKMI7XQBSF2ZASILV5GB3EYIZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJKMI7XQBSF2ZASILV5GB3EYIZ/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":"2026-08-19T07:47:29Z","links":{"resolver":"https://pith.science/pith/GJKMI7XQBSF2ZASILV5GB3EYIZ","bundle":"https://pith.science/pith/GJKMI7XQBSF2ZASILV5GB3EYIZ/bundle.json","state":"https://pith.science/pith/GJKMI7XQBSF2ZASILV5GB3EYIZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJKMI7XQBSF2ZASILV5GB3EYIZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GJKMI7XQBSF2ZASILV5GB3EYIZ","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":"5742f634294ee588142d6c4c5d61e0c45e6eacc67c64018e0c819d5a778cfa06","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-09T08:07:43Z","title_canon_sha256":"b4d39cdeb68e33e53c9831fb2654a4928bc52a7b440f61d258950830e533437c"},"schema_version":"1.0","source":{"id":"2307.04114","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04114","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04114v1","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04114","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"pith_short_12","alias_value":"GJKMI7XQBSF2","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"pith_short_16","alias_value":"GJKMI7XQBSF2ZASI","created_at":"2026-07-05T06:29:08Z"},{"alias_kind":"pith_short_8","alias_value":"GJKMI7XQ","created_at":"2026-07-05T06:29:08Z"}],"graph_snapshots":[{"event_id":"sha256:a0fa8ff5ac5041a58fcb59cede2b4259ad362fe4cf66cfd6e98d070fa7513330","target":"graph","created_at":"2026-07-05T06:29:08Z","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/2307.04114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However, these works focus on improving existing modules such as visual prototypes and feature extractors of the standard few-shot learning framework. This limits the full potential use of semantic information. In this paper, we propose a novel few-shot learning framework that uses pre-trained language models based on contrastive learning. To address the challenge of al","authors_text":"Dong Pang, Huishuai Zhang, Weiran Huang, Yunkai Dang, Zihao Jiang","cross_cats":["cs.AI","cs.CL","cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-09T08:07:43Z","title":"FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04114","kind":"arxiv","version":1},"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:cb1c8f2dd51d6afec2df7d5f8b766c4e2cdace25257c01fd8ac6bd66967e1092","target":"record","created_at":"2026-07-05T06:29:08Z","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":"5742f634294ee588142d6c4c5d61e0c45e6eacc67c64018e0c819d5a778cfa06","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-09T08:07:43Z","title_canon_sha256":"b4d39cdeb68e33e53c9831fb2654a4928bc52a7b440f61d258950830e533437c"},"schema_version":"1.0","source":{"id":"2307.04114","kind":"arxiv","version":1}},"canonical_sha256":"3254c47ef00c8bac82485d7a60ec984654b5a26bde00e1110a28e3c758a07a2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3254c47ef00c8bac82485d7a60ec984654b5a26bde00e1110a28e3c758a07a2d","first_computed_at":"2026-07-05T06:29:08.936947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:08.936947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kRd1i2qhow+bvly5RVxd6TbFfjVELORbpC/8tWvKgSSu5Nhcy44G1ZHHBltvJw5rs/fInUIAcDSn17rkZBYGAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:08.937808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04114","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb1c8f2dd51d6afec2df7d5f8b766c4e2cdace25257c01fd8ac6bd66967e1092","sha256:a0fa8ff5ac5041a58fcb59cede2b4259ad362fe4cf66cfd6e98d070fa7513330"],"state_sha256":"2b55ff8c7c938b330e32fbf1fa37fe40b29607e7b13d3d9134d4fd2c87ccfd58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eJ6Mrr3pOewEXqVJrd9NnZyRYTLemcQyEX7aj5/kdTm37cRgqVTMomkMINpSoD2TSffNLP9jcFu0JSfYMTheCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:47:29.648961Z","bundle_sha256":"db1830968c74992e76cf07ff72a6f823ef4e723514cecf9a0fe7d5d7ef4443c8"}}